Eng 05 00071

See discussions, stats, and author profiles for this publication at: https://www.researchgate.
net/publication/382002175
Business Process Reengineering Projects: Application in Automotive Sector
Article in Eng—Advances in Engineering · July 2024

DOI: 10.3390/eng5030071
CITATIONS READS
0 47
3 authors, including:
Hicham Raffak
Université Hassan 1er
4 PUBLICATIONS 0 CITATIONS
SEE PROFILE
All content following this page was uploaded by Hicham Raffak on 05 July 2024.
The user has requested enhancement of the downloaded file.

Article
Risk Management and Assessment Hybrid Framework for
Business Process Reengineering Projects: Application in
Automotive Sector
Raffak Hicham 1, * , Lakhouili Abdallah 1 and Mansouri Mohamed 2
1 Faculty of Sciences and Techniques, Hassan First University of Settat, Settat, Morocco;
[email protected]
2 National School of Applied Sciences, Hassan First University of Settat, Settat, Morocco;
[email protected]
* Correspondence: [email protected]
Abstract: This study introduces an integrated method for managing process risks in a business process
reengineering (BPR) project using robust data envelopment analysis (RDEA) and machine learning
(ML). The goal is to prioritize risks based on three standard factors of PFMEA (severity, occurrence
and detection (S-O-D)) and incorporating two additional factors (breakdown cost and breakdown
duration) seen as undesirable outputs. The model also accounts for the effect of uncertainty on
expert-estimated values by applying disturbance percentages in the linear PFMEA-RDEA model. A
machine-learning model is proposed to predict new values if partial or total modifications have been
made to the processes. The approach was implemented in an automotive sector company, and the
results showed the impact of uncertainty on values by comparing different approaches, such as RPN,
PFMEA-DEA and PFMEA-RDEA. A new reduced risk categorization was achieved, which allowed
for decision makers to focus on the necessary actions for reengineering.
Keywords: BPR; DEA; RDEA; machine learning; FMEA; PFMEA; risk prioritization; ANN
Citation: Hicham, R.; Abdallah, L.;

Mohamed, M. Risk Management and
1. Introduction
Assessment Hybrid Framework for Globalization has significantly transformed the business world, leading to rapid
Business Process Reengineering changes in operations and client demands. In this dynamic environment, commercial
Projects: Application in Automotive organizations face intense competition and significant challenges. The demands of the
Sector. Eng 2024, 5, 1360–1381. modern business environment highlight the necessity for adopting robust strategies to
https://doi.org/10.3390/ drive radical improvements in operational performance, efficiency and value creation [1].
eng5030071 Companies that fail to implement changes, often imposed by customers or the general
Academic Editor: Jingzheng Ren environment, are at risk of losing their competitiveness and might even disappear from
the market [2]. Business process management therefore serves as a systematic approach
Received: 31 May 2024 essential for accomplishing work and achieving set objectives [3].
Revised: 1 July 2024
Reorganizing and redesigning traditional business processes are key steps for manu-
Accepted: 2 July 2024
facturing organizations aiming to improve operational efficiency, adapt to changing market
Published: 5 July 2024
demands and maintain or boost their competitive advantage. Business process reengineer-
ing (BPR) is recognized as the best method in response to these needs. Its main goals are to
cut costs, meet deadlines and enhance the overall quality of manufacturing. If implemented
Copyright: © 2024 by the authors.
correctly, it is the only method capable of delivering exceptional results [4,5]. Currently,
Licensee MDPI, Basel, Switzerland. BPR is the most popular approach for driving changes and has garnered considerable
This article is an open access article attention from academics and practitioners [6–9]. Numerous studies have revealed that
distributed under the terms and implementing BPR is highly risky, with 80% of projects failing [10,11]. Other research
conditions of the Creative Commons shows that the success rate of BPR projects is only 30% [7,12]. Additionally, 70% of projects
Attribution (CC BY) license (https:// do not achieve the expected outcomes [13]. The challenge of defining the success factors
creativecommons.org/licenses/by/ creates significant difficulties in developing frameworks and methodologies. Moreover,
4.0/). implementing a robust risk management strategy is crucial [14].
Eng 2024, 5, 1360–1381. https://doi.org/10.3390/eng5030071 https://www.mdpi.com/journal/eng

Eng 2024, 5 1361
Numerous methods exist for assessing risks; yet, an effective evaluation technique
must be customized and simple to reflect the specific activities, culture, processes and
other characteristics of an organization. Risk assessment involves a methodical approach to
determining both quantitative and qualitative risks tied to hazardous processes, materials,
activities or events that could impact humans, materials, equipment and the environ-
ment [15]. Among the various methods for risk assessment, the failure mode and effects
analysis (FMEA) is distinguished by its proactive approach to identifying potential issues,
as opposed to reactive methods. FMEA entails the identification of possible problems and
the assessment of their associated risks, followed by both formulation and implementation
of corrective measures to minimize or eliminate these risks. Numerous studies employ-
ing FMEA utilize the conventional risk priority number (RPN) to identify and prioritize
risks [16–18]. This score directs improvement initiatives toward risks with a higher RPN,
although potentially less severe, compared to other risks with a lower RPN [19]. Traditional
FMEA incorporates just three metrics (severity, occurrence and detection—“S-O-D”) as
the key elements for calculating the RPN in risk assessments, which present a limit for the
traditional RPN’s effectiveness. Consequently, in employing FMEA for evaluating process
risks, it is essential to include additional factors beyond the classic S-O-D metrics. To
surmount the FMEA limitations, this study integrates two extra variables: the cost and the
duration of process breakdown. Nonetheless, based on the specific nature of the risk and
the circumstances of its occurrence, these additional variables can fluctuate and introduce
a level of uncertainty that can make prioritization unreliable and even impractical when
fixed values are assigned to these variables.
Data envelopment analysis (DEA) is extensively utilized to evaluate the efficiency
of decision-making units (DMUs) across diverse sectors, aiming to boost organizational
performance in various activity areas [20]. DEA has also been employed in evaluating
organizational risks [21]. There has been considerable investigation into deterministic
DEA methods to understand the connection between various risk facets and efficiency.
DEA enhances the analysis and assessment of an organization’s risk levels in activities by
either extending or incorporating other methodologies, thereby assigning an appropriate
prioritization score [22]. A notable drawback of DEA and linear programming models is
their reliance on deterministic data that match nominal values, which overlooks the impact
of data uncertainty on the model’s effectiveness [23]. Consequently, robust optimization has
emerged as an effective and reliable solution, presenting a strong alternative to stochastic
programming and sensitivity analysis [24].
When an organization uses DEA to assess risks and has already evaluated the risk
level for a large number of decision-making units (DMUs), reapplying DEA can lead
to different results [25]. This occurs because DEA uses data that evolve over time to
perform the internal evaluation of DMUs. If it is necessary to recalculate only certain
DMUs based on their new efficiency to represent their updated risk level, managers often
reapply the DEA methodology in its entirety. This can change the efficiency scores of
all DMUs, which can cause confusion in the process of decision making, especially for
risk treatment. Hence, this research introduces a machine-learning (ML) approach to
forecast new risk levels using efficiency scores. While earlier methods have merged DEA
and ML to assess the efficiency of DMUs across different fields, their application in risk
management remains unexplored. Risk treatment and monitoring are crucial components of
risk management, involving the choice of suitable treatment strategies and the evaluation of
their effectiveness, respectively [26]. To improve the risk management process, it is essential
to devise effective methods and tools that can predict the potential outcomes of treatment
strategies, leading to a more robust and comprehensive approach. Artificial intelligence
(AI) manifests itself as a useful methodology to monitor the impact of strategy variations
on the predicted variables [27]. For example, neural networks are a powerful tool in terms
of risk monitoring [28,29]. There are two key advantages of using neural networks for
estimation or prediction tasks. First, they are capable of processing large volumes of data
Eng 2024, 5 1362
for output estimation. Second, they can provide high accuracy in predictions. Moreover,
the operational speed of neural networks is fast [30].
To address all these issues, this study proposes an approach based on robust DEA
(RDEA) to obtain efficiency scores that prioritize risks, taking as inputs the critical factors
of RPN from the FMEA process as well as the cost and duration of process downtime
as undesirable outputs. This can provide reliable and realistic data that enable decision
makers to make informed decisions during the reengineering of the operational processes
in question. The application of neural network models for forecasting in risk treatment and
analysis is another result of this study. The proposed approach is applied to the assessment
of process risks in an automotive spare parts company, and the results are analyzed.
2. Literature Review
2.1. BPR
BPR has been a popular topic since it first came up in the early 1990s. Both re-
searchers and professionals have explored its importance, methods, effects and what makes
it successful [31].
BPR started in the early 1990s as an innovative method to rethink and revamp business
processes for substantial improvements in areas like cost, quality, service and speed [32].
Reengineering involves a thorough reengineering of business processes [33]. BPR is
seen as a strategy where processes are reshaped to maximize an organization’s effective-
ness [34]. Another description of BPR is a management approach focused on completely
revamping or replacing inefficient procedures to achieve significant results [35]. This
method can be applied to one or several processes. According to Bhaskar, BPR is cus-
tomized for each organization; therefore, they use it in their own way to meet their specific
goals. This approach works for businesses of all sizes, whether they are in manufacturing
or services [36].
BPR is a complete overhaul of a business, changing everything from processes and
technologies to organizational structures, values and management systems. The aim is
to greatly improve performance throughout the company. BPR needs to work together
with other parts of the organization, use advanced technology and incorporate different
methods. It does not work well on its own. IT plays a key role in BPR by providing the
tools needed for major improvements in how the organization functions, although its role
can sometimes be misunderstood [37,38].
To successfully complete an implementation project is a commendable feat for any
team. Nonetheless, business process reengineering projects frequently experience varying
degrees of success. This inconsistency often stems from the application of best practices
or standards from other industries without adequately considering the specific needs of
the targeted industry. Notably, around 70% of these projects fail due to the lack of an
appropriate framework or methodology [9].
Many factors affect the outcome of a project. These factors are important for predicting
whether a project will succeed or fail. BPR projects come with their own risks. Whether
BPR is successful depends on several key factors [39].
By reviewing the research, we identified eleven main factors that determine the success
of BPR projects and pinpointed the major reasons why BPR projects fail [40] (Table 1).
Although numerous factors influence the success of BPR projects, the human element
is the most crucial [41]. Leveraging data and analytics to guide decision making through-
out the project can significantly impact its success. By understanding the variables that
contribute to success or failure and using data science and machine-learning techniques, it
becomes possible to predict the outcomes of a BPR project.
The reengineering process is structured into stages, where the output from one stage
serves as the input for the next. Before any implementation can begin, both the diagnostic
and transformation steps must be completed, allowing little room for flexibility. Numerous
frameworks and strategies have been devised for carrying out BPR, with a common concern
among practitioners being the choice of methodology or model to follow. It has been
Eng 2024, 5 1363
observed that many companies engaging in BPR tend to adopt conventional methodologies
that use linear lifecycle models, influenced by traditional practices in engineering and
software development. These approaches have faced criticism for their inconsistency and
the variability of their stages [42].
Table 1. BPR success and failure factors.
Category Factor Success Failure

Readiness for change, courage Lack of readiness and resistance
Strategic Focus on change
and willpower to change
Selecting the best methodology Lack of suitable and effective BPR
Driver Methodology and framework
and framework for the project framework and methodology
Collaborative and working
Enabler Working environment toward shared objectives Lack of collaborative working
and targets
Highly engaged, supportive Lack of top management
Strategic Top management
and committed commitment
BPR strategies, IT capabilities
Lack of reliable advanced
Driver (IT integration, IT infrastructure Aligned strategies
technology (IT)
and redesign, etc.)
Data-driven change based on
Enabler Data Not having sufficient data
facts and figures
Flat and less bureaucratic
Enabler Culture Poor leadership style
structure
Effective communication, Lack of communication with
Enabler Communication
motivation all stakeholders
Strategic Financial support Adequate financial support Inadequate financial support
Inadequate business case: unclear,
unreasonable, unrealistic scope and
Driver Business needs analysis Customer focus
unjustifiable expectations from the
BPR project
Effective and skilled BPR team
Lack of training and education and
Enabler BPR team training, education, fair reward
fair reward
system provided at all levels
A comprehensive six-phase framework BPR was introduced [43]. The first phase
requires top management to acknowledge their goals and motivations while committing
fully to the initiative. In the second phase, the management must establish a clear vision and
set objectives to guide the company’s activities. The third phase involves benchmarking
to assess current processes and identify critical issues, establishing a baseline for the
BPR project. The fourth phase entails conducting a pilot study to determine necessary
resources and the extent of changes required. The fifth phase, implementation, is vital and
necessitates support from middle managers and top management to lead, adjust reward
systems, realign structures, educate employees and implement IT for successful integration.
Effective and ongoing communication throughout the organization is crucial to mitigate
resistance. The final phase focuses on monitoring and evaluating the project, tracking
progress and identifying the areas for adjustment.
Other researchers have explored the development of frameworks to aid in selecting
appropriate BPR modeling methods in response to heightened competition and a dynamic
business environment [44]. Successful BPR planning requires comprehensive information
and the right tools. Business process modeling (BPM) is highlighted as a technique for
describing and analyzing business processes, with various methods and software available
to assist practitioners and researchers in designing BPM.
Eng 2024, 5, FOR PEER REVIEW 5
Eng 2024, 5 1364
BPR
BPR isis aa distinctive, one-timeevent
distinctive, one-time eventand
andshould
shouldbe,be,like
like any
any critical
critical project,
project, managed,
managed,
as it is essential for the future of an organization. It involves the phases of analysis,
as it is essential for the future of an organization. It involves the phases of analysis, design design
and implementation, as depicted in the flow diagram in Figure
and implementation, as depicted in the flow diagram in Figure 1 [14]. 1 [45].
Figure1.
Figure Proposed framework
1.Proposed framework for
forthe
thestudy.
study.
The goal
The goal of
of this
this BPR
BPR framework
frameworkand andmethodology
methodologyis istoto
assist
assistorganizations
organizations in their
in their
efforts. The stages of the model are detailed below.
efforts. The stages of the model are detailed below.
In the phase of analysis, it is crucial to prepare for change by thoroughly understanding
In the phase of analysis, it is crucial to prepare for change by thoroughly understand-
the market and the requirements of customers. This step involves a detailed examination
ing the market and the requirements of customers. This step involves a detailed examina-
of current internal processes to determine their effectiveness in achieving competitive
tion of currentlevels.
performance internal processes toagainst
Benchmarking determine theirbest
industry effectiveness
practices isinoften
achieving
includedcompetitive
in this
performance levels. Benchmarking against industry best practices is often
phase. Early in the process, decisions are made regarding which processes are most suitableincluded in this
phase. Early in the process, decisions are made regarding which processes
for reengineering and which areas require immediate focus. It is noted that one of the most are most suit-
able
frequently suggested research areas for addressing the challenges of implementing BPR of
for re-engineering and which areas require immediate focus. It is noted that one
the most is
projects frequently suggested
the application of riskresearch areas and
management for addressing thebefore,
its techniques challenges
during of and
implement-
after
ing
theBPR projects
project phasesis[14].
the application of risk management and its techniques before, during
and after the project phases [45].
2.2. Risk Management and Methodologies
Risk
2.2. Risk is present in
Management andalmost every aspect of life. People try to reduce it, sometimes
Methodologies
intentionally and sometimes because they have to, although completely getting rid of it is
Risk is present in almost every aspect of life. People try to reduce it, sometimes inten-
not possible. In the industrial world, the pursuit of significant investment returns has led
tionally and sometimes because they have to, although completely getting rid of it is not
to the development of many analysis methods.
possible. In the industrial world, the pursuit of significant investment returns has led to
To begin discussing risk and how it is managed, it is important to first understand
the
what risk means.ofThe
development manytermanalysis methods.
“risk” does not have a single, fixed definition; its meaning
Toacross
varies begindifferent
discussing risk
fields and
like how it social
business, is managed,
contexts,it economics,
is important to first
safety, understand
investment,
what risk means. The term “risk” does not have a single, fixed definition;
military and politics [45]. In project management, risk is usually defined as the chance its meaning
that
varies across different fields like business, social contexts, economics,
something might occur that could either help (as an opportunity) or hurt (as a threat) the safety, investment,
military
goals of and politics
a project. [46]. In for
However, project
thosemanagement,
working in the risk is usually
field, managing defined as the involves
risk mainly chance that
something
finding andmight occur
reducing that could
potential eitherInhelp
dangers. (as an opportunity)
the context or hurtreengineering,
of business process (as a threat) the
risk follows
goals the ISO
of a project. 31000 standard
However, definition:
for those working “the effect
in the of uncertainty
field, managing on objectives”
risk [46].
mainly involves
This effect refers to any variation from what was expected, whether good
finding and reducing potential dangers. In the context of business process re-engineering, or bad. These
objectives
risk follows can beISO
the diverse,
31000covering
standard financial, time-related,
definition: “the effecttechnical, commercial,
of uncertainty on environ-
objectives”
mental aspects, and more, and they can apply to different
[47]. This effect refers to any variation from what was expected, whether goodlevels of operation, suchorasbad.
strategic, organizational, product or process levels.
These objectives can be diverse, covering financial, time-related, technical, commercial,
environmental aspects, and more, and they can apply to different levels of operation, such
as strategic, organizational, product or process levels.
Eng 2024, 5 1365
In the context of enterprise operations, risk management typically entails four key
activities: (i) risk identification, which determines the events that could adversely affect
operational goals; (ii) risk assessment, an ongoing process that encompasses risk analysis
and risk evaluation; (iii) risk treatment, the response to identified risks; and (iv) risk
monitoring to oversee risk dynamics over time [26,47,48]. The risk management process
advances to risk evaluation, where the magnitude and priority of each risk are determined
based on benchmarking criteria set within the defined context [48]. The third stage, risk
treatment, involves devising, choosing and executing a plan of action. This pivotal phase
necessitates the identification of suitable strategies to address the risks, particularly those
deemed unacceptable after evaluation [49]. Finally, risk monitoring involves the ongoing
oversight and reassessment of risk sources, as well as the effectiveness of risk treatment
strategies. This step is critical because risk is dynamic, not static, necessitating periodic
adjustments to management approaches as circumstances change [26].
Risk management frameworks usually integrate both quantitative and qualitative
methods for identifying and assessing risks. These two approaches can sometimes produce
conflicting recommendations in practice [50]. When ample data are available, quantitative
methods for assessments are favored, but such comprehensive data are often lacking. In
these instances, while qualitative methods alone may not be ideal, developing a combined
model to enhance qualitative risk management becomes essential. Techniques like multi-
criteria decision making have been employed in various situations involving risk and
uncertainty, supporting the structured approach of risk management [51,52].
2.3. FMEA
In recent years, several risk assessment methods have been developed, including
FMEA. Originally introduced in the aerospace industry, FMEA focuses on identifying
potential failures and their consequences to prevent defects, enhance safety and boost
customer satisfaction [53,54]. This method has gained widespread acceptance across
various industries due to its utility for designers [55,56]. FMEA is a qualitative technique
used in risk management and decision making [57]. It prioritizes potential failures by
assigning a RPN to each one [58]. The RPN is instrumental in improving production or
services by managing, reducing or eliminating failures. A higher RPN indicates a more
urgent need for corrective or preventive measures [59]. The RPN is derived by multiplying
three factors (S * O * D) denoting the frequency of a potential failure; “S” reflects the severity
of its impact, and “D” gauges the likelihood of detecting the failure before it leads to further
problems [60].
To prioritize risks in FMEA, a weight-restricted DEA method is used in a pressurized
water reactor power plant [61]. Other studies combined a fuzzy belief TOPSIS approach
with FMEA to enhance risk assessment in steel production [62]. Other authors introduced
a hybrid method that combines gray relational analysis and interval DEA and applied it
to process failure analysis for assessing and prioritizing risks in auto parts manufacturing
processes [63]. Another approach involved a new hybrid model using FMEA, TOPSIS,
AHP and GRA for risk assessment in the production of automotive dust caps [64]. Razi
and Hoseini conducted a study on clustering and classification in a production process and
introduced a new method of FMEA by grouping failure modes using a KOHNEN neural
network and SBM-DEA model to assess them within their classes [65].
In 2017, a study utilized a combination of TOPSIS and FMEA for risk analysis [66]. In
place of the RPN, an ELECTRE TRI-based method was used to categorize failure modes
in dairy manufacturing, considering the importance and uncertainty of risk factors [67].
A novel approach introduced in 2018 combined FMEA, extended MULTIMOORA and
AHP within a fuzzy environment to assess risks in the steel industry [68]. Another hy-
brid method merged fault tree analysis (FTA) with FMEA, applied recursively in a metal
printing additive manufacturing system [69]. Additionally, a strategy integrating FMEA
with RDEA aimed at managing health, safety and environment (HSE) risks by targeting
undesirable outputs [70]. Further studies highlighted productivity improvements in au-
Eng 2024, 5 1366
tomotive manufacturing through the combined use of GRA and FMEA, while another
methodology incorporated QFD, VSM, plant layout and fuzzy FMEA to select lean tools in
manufacturing organizations [71,72].
2.4. PFMEA
FMEA is a prevalent technique used to detect and mitigate defects and failures in
systems by evaluating their impact on performance and implementing measures to reduce
their likelihood and consequences. There are four primary types of FMEA: system FMEA,
design FMEA, process FMEA (PFMEA) and machinery FMEA. PFMEA specifically targets
potential failure factors in production or assembly processes, aiming to decrease product
failure rates early in the product lifecycle by addressing defects. In this method, the most
critical failures are identified based on team member insights, resulting in a prioritized
list of potential issues. Corrective and preventive actions are then devised and executed
either prior to or during the process. Consequently, PFMEA is regarded as a dynamic
document that must be continuously updated with recent changes and actions, including
those implemented after production and any new RPNs [73].
As mentioned earlier, the RPN is determined by multiplying the factors of “S-O-D” as
part of the PFMEA process. Each factor is rated on a scale from 1 to 10, with 1 representing
the lowest risk and 10 the highest. For severity, a higher score indicates a “very dangerous”
failure. For occurrence, it signifies that the failure is “almost certain to happen”, and for
detection, it means the failure is “unlikely to be recognized” [58].
2.5. DEA
Research has highlighted several issues with the RPN used in the FMEA model [60].
The calculation method for RPN can lead to misleading statistics, and it fails to consider
the interconnections between failure modes, especially in complex systems with numerous
components [54,74].
While FMEA is a valuable risk assessment tool, it does not consider the relative
importance of the “S-O-D” factors. To address this, many multi-criteria decision-making
(MCDM) techniques have been used to evaluate the failure modes and enhance FMEA
outcomes (DEA). DEA evaluates the relative performance of different decision-making
units (DMUs). In this context, potential risks or failure modes in FMEA are treated as
DMUs, with the S-O-D ratings from FMEA serving as inputs for the DEA. This integration
forms a cohesive model combining FMEA and DEA [75].
In FMEA, risk factor weights are often assigned directly or confirmed through expert
judgment. MCDM methods, such as AHP and ANP, are established techniques for this
purpose [76]. DEA, however, offers an alternative method for assigning weights, enhancing
FMEA by improving the assessment capabilities and providing precise information on
factors like severity, occurrence and detection. Unlike other methods, DEA does not rely
on subjective judgments about the relative importance of risk factor weights. Instead, it
determines weights based on the interrelationships within the process [58]. The efficiency of
a DMU is measured by comparing its performance to the best-performing unit, calculated
as the ratio of the weighted sum of outputs to the weighted sum of inputs [77]. Additionally,
DEA assesses the importance of risk factors through their weights and ranks failure modes
by considering both the direct effects of individual failure indices and their impact relative
to the efficiency scores of other DMUs. This makes DEA effective for adjusting the weights
of risk factors by accounting for both indirect and direct relationships among failure
modes [78]. The core principle of DEA is to optimize weights for each DMU to maximize
the output-to-input ratio while ensuring the ratios of all DMUs remain close to one.
2.6. Machine Learning in Risk Management

ML can be applied across various fields, such as approximation, statistics, algorithm
complexity, analysis and probability. Recent progress in deep learning, a subset of ML, has
Eng 2024, 5 1367
produced outstanding results. ML algorithms simulate human learning behaviors to gain

new knowledge and continuously improve prediction accuracy [25].
ML, as a part of AI, leverages the rapid expansion of data. It excels in predictive and
classification analytics, essential for making informed decisions based on data [78]. ML is
increasingly influential in business, with numerous applications already in place and many
more in development [79].
The core function of ML is to use algorithms to analyze and learn from data, allowing
these algorithms to make predictions on new data, thus aiding decision making for various
scenarios. ML encompasses unsupervised, semi-supervised, supervised and intensive
learning methods. Supervised learning, one of the most common approaches, trains neural
networks on known data patterns for tasks such as classification and regression [25].
In predictive tasks, ML algorithms utilize historical data to forecast future events,
improving their accuracy as they process more data [80]. This predictive accuracy is vital
for effective performance.
In the business sector, ML has been particularly useful in risk management, such as
assessing and predicting risk probabilities. For instance, ML has significantly impacted the
financial sector, managing risks like credit, liquidity, operational and market risks. Studies
have demonstrated its application in banking risk management [81].
Additionally, ML has been employed in risk management systems to enhance in-
vestment portfolio performance by predicting potential losses [82]. ML’s capabilities also
extend to industrial risk assessment, where, for example, deep neural networks have been
used to evaluate risks in scenarios such as oil and gas drilling operations [83].
Moreover, ML’s predictive capabilities support evidence-based decision making in the
construction industry, enabling the development of proactive strategies based on dynamic
risk factors. This facilitates more effective project risk management [84].
3. Proposed Approach
3.1. RDEA
DEA techniques for handling uncertain data were first introduced in 1978, aiming to
assess the relative efficiency of distribution companies [85]. This non-parametric method
creates a piecewise linear efficiency frontier, derived from the most efficient companies, to
evaluate the relative efficiency of other firms. DEA is widely used in the electricity sector
due to its straightforward application and ease of interpretation.
Within this context, two modeling options are available: constant returns to scale
(CRS) and variable returns to scale (VRS). The CRS model assumes that companies can scale
their operations proportionally to achieve the optimal firm size. In contrast, the VRS model
offers greater flexibility by comparing the productivity of companies with others of similar
operational scale. In the conventional DEA, a group of DMUs is established using inputs
X1 , X2 , . . . , Xm to produce outputs Y1 , Y2 , . . . , Ys , where m and s represent, respectively, the
number of inputs and outputs. For a DMU j, xij represents the ith input used, and yrj
represents the rth output produced:
∑rs=1 µr yr
θ= (1)
∑im=1 νi xi
In this model, µr and νi represent the weights assigned to outputs and inputs, respec-
tively. The multiplier formulation for an input-oriented approach that assumes constant
returns to scale (CRS) is depicted in Model (2):
Eng 2024, 5 1368
s
maxθ = ∑µr yr0
r =1
s.t. ∑rs=1 µr yrj − ∑im=1 νi xij ≤ 0
m (2)
∑νi xi0 = 1
i =1
µr , νi ≥ 0
As previously noted, DEA results and rankings are unreliable when data are uncertain.
In real-world scenarios, it is often difficult to obtain precise data for inputs and outputs
in DEA applications. Traditional operational research modeling methods that address
uncertainty typically rely on a complete description in terms of probabilities. However,
uncertainty is often completely overlooked in many models. Recently, the emergence
of robust optimization has offered another alternative to sensitivity analysis and linear
programming [24,86]. The initial approach was introduced in 1973, which proposed a
model that handles uncertainty on a column-by-column basis. This model tended to be
overly conservative, adjusting the optimal solution to maintain feasibility [87].
maxc′ x
s.t. ∑ aij x j + ∑
âij y j ≤ bi ∀i
j j∈ Ji
(3)
−y j ≤ x j ≤ y j ∀ j
l≤x≤u
y≥0
Although the Soyster method from 1973 offers the highest level of protection, in
practice, it is the most conservative method. While robust solutions are generally more
resilient to uncertainty and parameter change, they often have a worse objective function
value compared to solutions obtained by standard linear optimization. A study from the
year 2000 proposed the following robust problem [88]:
maxc′ x s
s.t. ∑aij xj + ∑ â2ij yij + Ωi ∑â2ij zij ≤ bi ∀i
j j∈ Ji j∈ Ji
(4)
−y j ≤ x j − zij ≤ y j ∀ j
l≤x≤u
y≥0
Under the data uncertainty model, the probability of violating constraint i is at most
exp −λ2i /2 . Compared to Model (3), Model (4) is robust and less conservative, as every
feasible solution for Model (4) is also viable for Model (3).
A new approach proposed a non-linear formulation [24]:
maxc′ x
s.t. ∑
aij x j
j
∑ aij yj + (Γi − ⌊Γi ⌋)ait yt } ≤ bi ∀i

ˆ ˆ
+ max { i (5)
{Si ∪{ti }|Si ⊆ Ji ,|Si |=⌊Γi ⌋,ti ∈ Ji ∖Si }
j ∈ Si
−y j ≤ x j ≤ y j ∀ j
l≤x≤u
y≥0
For the ith constraint of the standard problem, the expression a′ i x ≤ bi is considered.
Here, Ji represents the set of coefficients aij , with j ∈ Ji , which are subject to parameter
Eng 2024, 5 1369
∼
uncertainty; in this scenario, a ij , j ∈ Ji fluctuates within
a symmetric distribution centered
around the nominal coefficient aij within the bounds aij − âij , aij + âij . A parameter Γi is

introduced for each i as a robustness budget, which takes values within [0, | Ji |] and serves
to modulate the robustness of the methodology relative to the conservatism of the resulting
solution. Practically, it is improbable that every aij , j ∈ Ji will vary simultaneously. The
objective is to protect the solution against scenarios where up to ⌊Γi ⌋ of these coefficients
might alter, specifically one coefficient ait changing by ( Γi − ⌊Γi ⌋) âit . In other words,
nature will only allow a subset of the coefficients to change to adversely affect the solution.
In this case, the robust solution will certainly be feasible. Furthermore, the robust solution
maintains a high probability of feasibility even if the extent of changes surpasses ⌊Γi ⌋.
A linear formulation of the model is
∑ aij x∗j zij s.t.j∈∑J zij ≤ Γi , i ≤ zij ≤ 1 ∀ j ∈ Ji

ˆ
β i ( x ∗ , Γi ) = max (6)
j∈ Ji i
If ⌊Γi ⌋ takes an integer value, constraint i will be protected by the following expression:
β i ( x ∗ , Γi ) = max { ∑ aij′ | x j |} (7)

{Si |Si ⊆ Ji ,Si |=Γi } j∈Si
By using the duality form and applying it to Model (2), we obtain the following linear
model:
m s
maxθ0 s.t. ∑vi xi0 = 1, ∑ur yr0 − θ0 − Γ0 p0 − ∑ qi 0
≥0
i =1 r =1 j∈ J0
m s
∑ vi xij − ∑ur yrj − Γj pj − ∑qij ≥ 0, (8)

i =1 r =1 j∈ Ji
∀ jp j + qij ≥ eyrj zr , ∀ij
− zr ≤ ur ≤ zr ∀r
p j qij ≥ 0 ∀i, j
µr , νi ≥ 0, ∀r, i
where p j and qrj are dual variables; eij represent the percentage of perturbation in aij ; and z
represents the efficiency of risk under consideration.
In this study, the model is solved using Pulp python library for linear programing and
python solver.
3.2. ML Application
Supervised learning algorithms allow machine-learning models to learn autonomously
from a set of data. Among the many models developed recently are artificial neural net-
works. Through the input layer, the network receives a data sample, then undergoes
operations with activation functions in the hidden layers and finally produces a corre-
sponding target category through its output layer [25,89].
Figure 2 illustrates a basic structure of an artificial neural network (ANN). It includes
the neural connections, the biases allocated to each neuron and the weights assigned
to these connections, depicting a multi-layer model [25]. Neuron k is defined by two
equations [90]:
y k = f ( u k + bk ) (9)
N
uk = ∑i wki xi (10)
where x1 , x2 , . . . , xn is the set of inputs, and wk1 , wk2 , . . . , wkn are the neuron weights; uk is
the computation outcome of weight inputs; bk is the bias term; f is the activation function;
and yk is the output.
𝑢 = ∑ 𝑤 𝑥 (10)
where 𝑥 , 𝑥 , . . . , 𝑥 is the set of inputs, and 𝑤 , 𝑤 , . . . , 𝑤 are the neuron weights; 𝑢
Eng 2024, 5 is the computation outcome of weight inputs; 𝑏 is the bias term; f is the activation func-
1370
tion; and 𝑦 is the output.
Figure 2. Architecture of a neural network.

Figure 2. Architecture of a neural network.
In this research, N risks are analyzed, where each risk j is characterized by five inputs
InD,
(O, S, thisBDCOST,
research,BDDURATION).
N risks are analyzed, where each
Additionally, riskrisk
each j is characterized
j is associatedby fiveainputs
with target
(O, S, D, BDCOST, BDDURATION). Additionally, each risk j
variable, which is the score determined through RDEA. The combination of the weighted is associated with a target
variable,
inputs andwhich the isRDEA
the score
score determined through relationship
forms a mapping RDEA. The combination
via an activation of thefunction.
weightedy
inputs and the
examining RDEA
N risks score
with forms ainputs
specified mappingand relationship
corresponding via RDEA
an activation function.the
score outputs, y
examining N risks with specified inputs and corresponding
weights and the bias term can be identified using Equations (9) and (10) throughout theRDEA score outputs, the
weights and theprocess
model training bias term can be identified using Equations (9) and (10) throughout the
[25].
modelIntraining process [25].
this study, a random forest regressor with 100 trees was used to predict the RDEA
In this
scores fromstudy, a random
the input forest
features. regressor
Using withseed
a random 100 trees was used to predict
for reproducibility, the RDEA
the dataset was
scores from
split into the input
training features.
(90%) Using (10%)
and testing a randomsets.seed for reproducibility,
We configured the dataset
a multi-layer was
perceptron
split into training
regressor to determine(90%) its
andarchitecture
testing (10%) sets. We configured
dynamically a multi-layer
with optimization perceptron
through particle
regressor to determine its architecture dynamically with optimization
swarm optimization (PSO). We aimed to minimize the mean squared error (MSE) of the through particle
swarm optimization
predictions in the test(PSO).
set basedWeon aimed
the PSOto minimize
by adjusting thethe
mean
number squared error (MSE)
of neurons of the
and learning
predictions in the test set based on the PSO by adjusting the number
rate of the MLP. The PSO was implemented with social and specific cognitive parameters, of neurons and learn-
ing rateoptimized
which of the MLP. theThe PSO was implemented
configuration with social
of the MLP model. and specific
To ensure cognitiveefficiency,
computational param-
eters, whichspace
the search optimized the configuration
was constrained of the
to [1, 100] for MLP model.of
the number Toneurons.
ensure computational ef-
ficiency, the search space was constrained to [1, 100] for the number of neurons.
4. Case Study
4. Case Study
The proposed approach, shown in Figure 3, was implemented in a plastic injection
company operatingapproach,
The proposed in the automotive
shown insectorFigurewith the implemented
3, was aim of obtaining in aaplastic
robustinjection
score for
process risks
company in order
operating to redesign
in the automotive andsector
enhance withperformance. Initially, the
the aim of obtaining BPR team
a robust score was
for
formed, incorporating members of the AMDEC PROCESS team.
process risks in order to redesign and enhance performance. Initially, the BPR team was Based on the existing
AMDECincorporating
formed, register, the costs and process
members of thedowntime were determined
AMDEC PROCESS team. Basedas scores, according
on the existingto
the approach defined in Table 2.
Table 2. Scores of output costs and duration.
BD-Cost BD-Duration
Score
(EUR) (Day)
1 ≤100 ≤1
2 ]100, 500] ]1, 3]
3 ]500, 3000] ]3, 5]
4 ]3000, 6000] ]5, 6]
5 >6000 >6
Potential process risks identified during the execution of the BPR method were added
to the already defined risks. The primary goal of BPR is to reduce costs and delays, which
is why these will not be considered as desirable outputs for DEA but rather as undesirable
outputs [91]. The new values for outputs, according to the Seiford and Zhu approach, are
calculated and presented in Table 3. The three approaches—RPN, conventional DEA and
RDEA—will be applied and compared. The proposed ML model will be applied with
the role of predicting new scores in case of improvements applied and also predicting the
scores for new risks.
Eng 2024, 5 1371
Proposedapproach.
Figure3.3.Proposed
Figure approach.
It is important to note that the FMEA method is initially designed for preventive mea-
To apply RDEA effectively, it is essential to first set the values of Γ (j = 1, 2, …, n)
sures. Therefore, some process risks may not manifest within an organization. Additionally,
and Γ for each constraint. When a constraint experiences less uncertainty, complete pro-
the costs and duration of treatments can vary based on individuals’ physical and mental
tection becomes crucial. Given that uncertainty impacts both output parameters across all
conditions. As a result, the output values of the DEA model, established from field studies
constraints, the values of Γ (j = 1, 2, …, n) and Γ are established at 2 to guarantee com-
under the supervision of BPR-TEAM and PFMEA-TEAM, contain a degree of uncertainty.
prehensive protection against this uncertainty. In such cases, if all parameters shift to their
Due to this data uncertainty, using conventional DEA for evaluating and prioritizing risks
least favorable conditions, the model remains fully protected against uncertainties.
is considered unreliable. Therefore, to accommodate data uncertainty, enhance solution
The regression model for predicting values is implemented using Python and several
robustness and address the limitations of the RPN score, adopting the score based on the
machine-learning libraries. “sklearn.model_selection” is used to split the data into train-
PFMEA-RDEA method to classify risk is a recommendation.
ing and testing sets. “sklearn.ensemble” imports the RandomForestRegressor. “numpy”
To apply RDEA effectively, it is essential to first set the values of Γi (j = 1, 2, . . .,
isn)aand
library foreach
Γ0 for advanced numerical
constraint. When operations.
a constraint“sklearn.neural_network”
experiences less uncertainty, imports the
complete
MLPRegressor. “pyswarms” is a library for particle swarm optimization,
protection becomes crucial. Given that uncertainty impacts both output parameters across used here to op-
timize the hyperparameters ofΓthe neural network.
all constraints, the values of i (j = 1, 2, . . ., n) and Γ0 are established at 2 to guarantee
comprehensive protection against this uncertainty. In such cases, if all parameters shift to
5.their
Results
least favorable conditions, the model remains fully protected against uncertainties.
To
The categorize
regressionprocess
model risks, the PFMEA,
for predicting values DEA-PFMEA and using
is implemented RDEA-PFMEA
Python and methods
several
are each applied independently.
machine-learning The traditional FMEA
libraries. “sklearn.model_selection” method
is used ranks
to split the risks using
data into RPN
training
scores, which
and testing are“sklearn.ensemble”
sets. calculated by multiplyingimportsthe theinput values in Table 3 and“numpy”
RandomForestRegressor. consideringis a
only
librarythefor
S-O-D valuesnumerical
advanced for the final scores. Table
operations. 4 shows the prioritization
“sklearn.neural_network” importsofthe
identified
MLPRe-
risks based
gressor. on these RPN
“pyswarms” scores. for particle swarm optimization, used here to optimize the
is a library
hyperparameters of the neural network.
Eng 2024, 5 1372
Table 3. Undesirable values of outputs.
Undesirable Undesirable
S O D BD-Cost BD-Duration
BD-Cost BD-Duration
6 6 3 1 1 428 155
9 2 2 1 1 440 182
8 2 2 1 2 440 182
8 2 2 1 1 443 179
8 2 2 1 1 443 179
8 2 2 3 2 433 180
8 2 2 1 1 443 179
8 2 2 1 1 443 179
9 2 2 1 1 440 182
9 2 2 1 1 440 182
6 2 3 3 4 302 107
6 2 3 3 4 302 107
6 2 3 4 4 433 182
6 2 2 1 1 424 180
6 2 3 1 1 427 173
6 2 3 1 1 427 173
6 2 3 1 1 427 173
6 2 3 1 1 427 173
6 2 3 1 1 427 173
6 2 3 1 1 427 173
6 2 3 1 1 427 173
6 2 3 1 1 427 173
6 2 3 1 1 427 173
6 2 3 1 1 427 173
6 2 3 1 1 427 173
6 2 3 1 1 427 173
6 2 3 1 1 427 173
9 2 2 1 1 440 182
8 2 2 1 1 443 179
8 2 2 1 1 443 179
9 2 2 1 1 440 182
6 2 3 1 1 427 173
6 2 3 1 1 427 173
6 2 3 1 1 427 173
6 2 3 3 1 302 107
6 2 3 4 2 255 125
6 2 3 3 1 349 131
6 2 2 1 1 424 180
6 2 3 1 1 427 173
6 2 3 1 1 427 173
6 2 3 1 1 427 173
6 2 3 1 1 427 173
6 2 3 1 1 427 173
6 2 3 1 1 427 173
6 2 3 5 3 427 173
6 2 3 4 2 255 125
6 3 3 1 1 417 173
9 2 3 3 2 437 173
6 2 3 5 3 423 173
6 2 3 4 2 417 169
6 7 5 4 2 418 170
9 3 5 5 2 412 171
9 2 10 5 3 477 123
9 2 2 5 3 447 73
Eng 2024, 5 1373
5. Results
To categorize process risks, the PFMEA, DEA-PFMEA and RDEA-PFMEA methods
are each applied independently. The traditional FMEA method ranks risks using RPN
scores, which are calculated by multiplying the input values in Table 3 and considering
only the S-O-D values for the final scores. Table 4 shows the prioritization of identified
risks based on these RPN scores.
Table 4. Risk prioritization using the PFMEA-RDEA approach.
RPN Conventional DEA RDEA (e1 = e2 = 0.5) RDEA (e1 = 0.3 e2 = 0.4)
Risks
Score Priority Score Priority Score Priority Score Priority
R1 108 4 0.87 53 0.9000000000000004 52 0.8500000000000003 21
R2 36 7 0.77 22 0.8300000000000001 22 0.8800000000000001 28
R3 32 45 0.65 13 0.5 6 0.44999999999999996 6
R4 32 45 0.65 13 0.7999999999999998 13 0.8499999999999999 15
R5 32 45 0.65 13 0.7999999999999998 13 0.8499999999999999 15
R6 32 45 0.89 54 0.8200000000000003 20 0.8700000000000003 25
R7 32 45 0.65 13 0.7999999999999998 13 0.8499999999999999 15
R8 32 45 0.65 13 0.7999999999999998 13 0.8499999999999999 15
R9 36 7 0.77 22 0.8300000000000001 22 0.8800000000000001 28
R10 36 7 0.77 22 0.8300000000000001 22 0.8800000000000001 28
R11 36 7 0.18 2 0.05252000000000123 1 0.0025200000000012157 1
R12 36 7 0.18 2 0.0525200000000123 1 0.0025200000000012157 1
R13 36 7 0.45 8 0.1999999999999993 5 0.2499999999999993 5
R14 24 53 0.38 6 0.7699999999999996 10 0.8199999999999996 12
R15 36 7 0.81 29 0.8999999999999986 30 0.8999999999999986 33
R16 36 7 0.81 29 0.8999999999999986 30 0.8999999999999986 33
R17 36 7 0.81 29 0.8999999999999986 30 0.8999999999999986 33
R18 36 7 0.81 29 0.8999999999999986 30 0.8999999999999986 33
R19 36 7 0.81 29 0.8999999999999986 30 0.8999999999999986 33
R20 36 7 0.81 29 0.8999999999999986 30 0.8999999999999986 33
R21 36 7 0.81 29 0.8999999999999986 30 0.8999999999999986 33
R22 36 7 0.81 29 0.8999999999999986 30 0.8999999999999986 33
R23 36 7 0.81 29 0.8999999999999986 30 0.8999999999999986 33
R24 36 7 0.81 29 0.8999999999999986 30 0.8999999999999986 33
R25 36 7 0.81 29 0.8999999999999986 30 0.8999999999999986 33
R26 36 7 0.81 29 0.8999999999999986 30 0.8999999999999986 33
R27 36 7 0.81 29 0.8999999999999986 30 0.8999999999999986 33
R28 36 7 0.77 22 0.8300000000000001 22 0.8800000000000001 28
R29 32 45 0.65 13 0.7999999999999998 13 0.8499999999999999 15
R30 32 45 0.65 13 0.7999999999999998 13 0.8499999999999999 15
R31 36 7 0.77 22 0.8300000000000001 22 0.8800000000000001 28
R32 36 7 0.81 29 0.8999999999999986 30 0.8999999999999986 33
R33 36 7 0.81 29 0.8999999999999986 30 0.8999999999999986 33
R34 36 7 0.81 29 0.8999999999999986 30 0.8999999999999986 33
R35 36 7 0.18 2 0.05252000000000123 1 0.0025200000000012157 1
R36 36 7 0.57 10 0.9199999999999999 53 0.8699999999999999 22
R37 36 7 0.23 5 0.05252000000000123 1 0.0025200000000012157 1
R38 24 53 0.38 6 0.7699999999999996 10 0.8199999999999996 12
R39 36 7 0.81 29 0.8999999999999986 30 0.8999999999999986 33
R40 36 7 0.81 29 0.8999999999999986 30 0.8999999999999986 33
R41 36 7 0.81 29 0.8999999999999986 30 0.8999999999999986 33
R42 36 7 0.81 29 0.8999999999999986 30 0.8999999999999986 33
R43 36 7 0.81 29 0.8999999999999986 30 0.8999999999999986 33
R44 36 7 0.81 29 0.8999999999999986 30 0.8999999999999986 33
R45 36 7 0.8077 27 0.8769999999999989 28 0.8769999999999989 25
R46 36 7 0.5700 10 0.9199999999999999 53 0.8699999999999999 22
R47 54 5 0.8541 52 0.8655000000000008 27 0.8655000000000008 22
R48 54 5 0.71 20 0.7403200000000005 9 0.7403200000000005 9
R49 36 7 0.8077 27 0.8769999999999989 28 0.8769999999999989 25
R50 36 7 0.09998 1 0.6589999999999989 8 0.6589999999999989 8
R51 210 1 0.71 20 0.8240000000000016 20 0.8240000000000016 14
R52 135 3 0.6 12 0.8000000000000007 19 0.8000000000000007 11
R53 180 2 0.54381 9 0.7654899999999998 10 0.7654899999999998 10
R54 36 7 0.843221 51 0.5413899999999998 7 0.5413899999999998 7
R54 36 7 0.843221 51 0.5413899999999998 7 0.5413899999999998 7

Eng 2024, 5 1374
Based on the RPN score, as shown in the table, Risk 51 with an RPN of 210 has the
highestBased
priority, followed
on the by Risks
RPN score, 52, in
as shown 53the
and 4, with
table, RPN
Risk 51 withscores
an RPN of of
180,
210135hasand
the 108,
respectively. Risks 14 and 38 have the lowest priority, each with a score
highest priority, followed by Risks 52, 53 and 4, with RPN scores of 180, 135 and 108, of 24. By adding
therespectively.
outputs of Risks
BD-COTS
14 andand BD-DURATION
38 have to the
the lowest priority, eachthree
withinputs
a score of S-O-D
of 24. and applying
By adding the
theoutputs
DEA-PFMEA
of BD-COTSapproach with undesirable
and BD-DURATION outputs,
to the a different
three inputs of S-O-Dpriority rankingthe
and applying is gen-
DEA-PFMEA approach with undesirable outputs, a different priority ranking
erated; the priority of Risk 51 becomes 20, while Risks 52, 53 and 54 receive the following is generated;
the priority
priorities: 12, of Risk 53,
9 and 51 becomes 20, while
respectively. Risks 52, 53
Regarding and 14
Risks 54 and
receive
38,the following
they become priorities:
more prior-
12, 9 and 53, respectively. Regarding Risks 14 and 38, they become more prioritized,
itized, ranking at 6. With this approach, the first priority is related to Risk 50, followed by ranking
at 6. With this approach, the first priority is related to Risk 50, followed by Risks 11 and
Risks 11 and 12. Now, the lowest priority is related to Risk 1. This shows the effect of
12. Now, the lowest priority is related to Risk 1. This shows the effect of breakdown
breakdown cost and breakdown
cost and breakdown duration. Theduration.
comparisonThebetween
comparison betweenofthe
the priorities RPNpriorities
scores andof RPN
scores and DEA-PFMEA scores is presented in the
DEA-PFMEA scores is presented in the following Figure 4. following Figure 4.
Figure 4. Prioritization
Figure 4. Prioritizationbased
basedon
on the score
scoreofofthe
thePFMEA-DEA
PFMEA-DEA approach
approach and and
RPNRPN
score.score.
In In
thethefollowing
following step,
step,the
theperturbation
perturbation level should
level be considered
should for outputs.
be considered Initially, Ini-
for outputs.
this is applied to two outputs of the RDEA model, with e1 = e2 = 0.5; later, the perturbation
tially, this is applied to two outputs of the RDEA model, with e1 = e2 = 0.5; later, the per-
levels are set to e = 0.3 and e = 0.4. The initial percentages are chosen randomly to
turbation levels are1 set to 𝑒 = 20.3 and 𝑒 = 0.4. The initial percentages are chosen ran-
demonstrate the effect of perturbation on the outputs. The latter percentages were selected
domly to demonstrate
and approved the effect
by the FMEA of perturbation
and BPR team involved oninthe
thisoutputs.
study basedTheon latter
theirpercentages
expert
were selected and approved by the FMEA and BPR
judgment according to the specific case study and field of activity.team involved in this study based on
their expert judgment
As Table 4 shows,according
the order of topriorities
the specific case study
changes, and field
demonstrating theofstrong
activity.
impact of
As Table on
uncertainty 4 shows,
the data,the order of priorities
represented changes,ofdemonstrating
by the percentages perturbations inthe thestrong impact of
undesirable
outputs ofon
uncertainty thethesystem.
data, Risks 11, 12, 35
represented byand
the 37 become theof
percentages highest priority, followed
perturbations by
in the undesira-
other risks. Another advantage is that the classification categories are
ble outputs of the system. Risks 11, 12, 35 and 37 become the highest priority, followed reduced, providing a by
clearer picture of the project’s risk status. This serves as a more robust decision-making
other risks. Another advantage is that the classification categories are reduced, providing tool
for redesigning the studied process, thereby planning the necessary action plan to address
a clearer picture of the project’s risk status. This serves as a more robust decision-making
these risks and enhance the process’s performance, aligning with the initial goal of the
toolBPR
formethod.
redesigning the studied process, thereby planning the necessary action plan to
addressThe these risks and
following enhance
figures present the process’s performance,
comparisons aligning
of the scores obtained with
using thethe initial goal
different
of the BPR method.
approaches applied in this study.
The Asfollowing figures5present
shown in Figure there is acomparisons of the scores
significant volatility obtained
in the RPN scores, using
which the different
could
indicate that
approaches this method
applied in this isstudy.
highly sensitive to the specific risk factors for each risk. The
PFMEA-RDEA method appears more conservative, potentially smoothing out the extreme
variations seen in RPN due to its consideration of perturbations in the model.
Eng
Eng 2024,
2024, 5,
5, FOR
FOR PEER
PEER REVIEW
REVIEW 17
17
Eng 2024, 5 1375
Figure 5.
5. Prioritization
Figure
Prioritization basedon
based on the
on score
scoreofof
the score the
ofthe PFMEA-RDEA
thePFMEA-RDEA
PFMEA-RDEA approach
approach and and
approach RPNRPN
and score.score.
RPN score.
The conventional
There PFMEA-DEA method shows substantial fluctuations in risk pri- this
There is is aa significant
significant volatility
volatility in
in the
the RPN
RPN scores,
scores, which
which could
could indicate
indicate that
that this
orities.
method is The PFMEA-RDEA
highly sensitive tomethod,
the with
specific specific
risk perturbation
factors for each percentage,
risk. The provides
PFMEA-RDEAa
method is highly sensitive to the specific risk factors for each risk. The PFMEA-RDEA
more moderate distribution of risk priorities. This method does not reach as high as the
method
method appears more
more conservative,
appearsPFMEA-DEA conservative, potentially smoothing out the
the extreme variations seen
conventional in most potentially smoothing
cases, suggesting a moreout extreme
tempered variations
response to the seen
in RPN
in RPN due to
due risk
perceived its consideration
to itsseverity
consideration of perturbations in the model.
of perturbations in the model.
(Figure 6).
Figure 6.
6. Prioritization
Figure
Prioritization basedon
based on the
on score
scoreofof
the score the
ofthe PFMEA-RDEA
thePFMEA-RDEA
PFMEA-RDEA approach
approach and and
approach PFMEA-DEA
PFMEA-DEA
and score. score.
PFMEA-DEA score.
This comparison (Figure

The 7) highlights howshows
small changes in perturbation parameters
The conventional
conventional PFMEA-DEA
PFMEA-DEA method method shows substantial
substantial fluctuations
fluctuations inin risk
risk prior-
prior-
within
ities. The the same methodological framework can lead to different prioritizations of risks.
ities. The PFMEA-RDEA method, with specific perturbation percentage, provides a more
PFMEA-RDEA method, with specific perturbation percentage, provides
This could influence strategic decisions in environments where the understanding and
a more
moderate
moderate distribution
distribution of risk priorities. This method does not reach as high as the conven-
mitigation of risks areof risk priorities.
crucial This performance
for operational method does andnotefficiency.
reach as high as the conven-
tional
tional PFMEA-DEA
PFMEA-DEA in
in most
most cases,
cases, suggesting
suggesting aa more
more tempered
tempered response
response to
to the
the perceived
perceived
risk severity.
risk severity.
Eng 2024, 5 1376
Figure
Figure 7. 7. Prioritizationbased
Prioritization based on
onthe
thescore
scoreof of
thethe
PFMEA-RDEA
PFMEA-RDEA approach with different
approach perturbation
with different perturba-
tionpercentages.
Figure 7. Prioritization based on the score of the PFMEA-RDEA approach with different perturba-
percentages.
tion percentages.
The comparison of these risk assessment methods (Figure 8) illustrates how each
This comparison highlights how small changes in perturbation parameters within
method interprets and prioritizes risks differently based on its underlying assumptions
theand This methodological
same comparison highlights how can small changes in perturbation parameters within
calculations. The RPNframework lead
method tends to highlight to different
risks moreprioritizations
dramatically. Byof risks.
contrast, This
thethe
could same
PFMEA-DEA and PFMEA-RDEA methods offer a more balanced and potentially This
methodological
influence strategic framework
decisions in can lead
environments to different
where theprioritizations
understanding of risks.
and mitiga-
could
tionmore influence
of risks strategic
are view
realistic crucial decisions
for
of risk insuitable
operational
priorities, environments
performance where thewhere
understanding
and efficiency.
for environments resources mustand be
mitiga-
tion of risksefficiently.
allocated are crucial for operational performance and efficiency.
Figure 8. Prioritization of risks based on the score of the PFMEA-DEA and PFMEA-RDEA ap-
Figure
proaches8.8.
Figure Prioritization
with different of
Prioritization ofrisks
risks based
perturbation
based onscore
the of
score
percentages.
on the of the PFMEA-DEA
the PFMEA-DEA and PFMEA-RDEA
and PFMEA-RDEA approaches ap-
proaches with different
with different perturbation
perturbation percentages.
percentages.
The comparison of these risk assessment methods illustrates how each method inter-
pretsTheUsing
and the proposed
comparison
prioritizes risksANN
of these model,
risk the obtained
assessment
differently based on itsMSE
methods is 0.002145834611031225,
illustrates
underlying which
how each method
assumptions and inter-
calcula-
indicates
prets and high performance
prioritizes risks (Table 5).
differently Therefore,
based on the
its designed
underlying artificial neural
assumptions network
and calcula-
tions. The RPN method tends to highlight risks more dramatically. By contrast, the
model is useful for prediction purposes. The main goal of this study is to develop the
tions. The RPN
PFMEA-DEA andmethod tends tomethods
PFMEA-RDEA highlightoffer
risks more balanced
a more dramatically. By contrast,
and potentially the
more
methods for predicting modified risk values when process reengineering strategies are
PFMEA-DEA and PFMEA-RDEA methods offer a more balanced and potentially
realistic view of risk priorities, suitable for environments where resources must be allo- more
realistic
cated view of risk priorities, suitable for environments where resources must be allo-
efficiently.
cated efficiently.
Eng 2024, 5 1377
implemented. This allows for the generation of new scores that aid in managing the BPR
Table 5. Average efficiency scores based on the criteria.
project to avoid surprises.
RDEA Score ML Score Error
Table 5. Average efficiency
0.8500000000000003 scores based on the criteria.
0.8514999999999994 0.001
0.8800000000000001
RDEA Score
0.8804196522776031
ML Score
0.0004
Error
0.44999999999999996 0.4746742857142863 0.02
0.8500000000000003 0.8514999999999994 0.001
0.8499999999999999
0.8800000000000001
0.8628437016205744
0.8804196522776031
0.01
0.0004
0.8700000000000003
0.44999999999999996 0.8658000000000005
0.4746742857142863 0.0050.02
0.8800000000000001
0.8499999999999999 0.8804196522776031
0.8628437016205744 0.00050.01
0.8700000000000003
0.8800000000000001 0.8658000000000005
0.8804196522776031 0.005
0.0005
0.8800000000000001 0.8804196522776031 0.0005
0.0025200000000012157 0.0049948000000000015 0.002
0.8800000000000001 0.8804196522776031 0.0005
0.2499999999999993
0.0025200000000012157 0.2475252
0.0049948000000000015 0.0020.002
0.8199999999999996
0.2499999999999993 0.8423190166500167
0.2475252 0.010.002
0.8199999999999996
0.8999999999999986 0.8423190166500167
0.8398135963221486 0.050.01
0.8999999999999986 0.8398135963221486 0.05
Using the proposed ANN model, the obtained MSE is 0.002145834611031225, which
indicates
The high performance.
Figure 9 shows thatTherefore,
there is athe designed
high degreeartificial
of overlapneural network
between the model is
two lines,
useful for prediction
indicating purposes.
a good general The main
agreement goal of
between thethis study isand
predicted to develop the methods
actual values for
across most
samples. modified
predicting The closerisk
tracking
valuesbetween the predicted
when process and actual
re-engineering values
strategies areinimplemented.
most parts of
the allows
This graph suggests that the machine-learning
for the generation of new scores that model is performing
aid in managing well.
the BPR However,
project the
to avoid
instances of underprediction are due to the insufficiency of training data.
surprises.
AverageML
Figure9.9.Average
Figure MLefficiency
efficiencyscores.
scores.
6. Discussion and Conclusions

There is a high degree of overlap between the two lines, indicating a good general
This study
agreement betweenintroduces a new and
the predicted integrated risk analysis
actual values acrossapproach—PFMEA-RDEA-ML—
most samples. The close track-
designed
ing between to the
prioritize process
predicted andrisks in values
actual a business process
in most reengineering
parts of the graphproject by introduc-
suggests that the
ing BD-COST and BD-DURATION as undesirable outputs to the conventional
machine-learning model is performing well. However, the instances of underprediction PFMEA-DEA
system.
are due toThis
the pushes the analysis
insufficiency to another
of training data. dimension, allowing for the consideration of
uncertainty by integrating the coefficients of perturbation in the parameter values of the
6.system, typically
Discussion and based on expert judgment.
Conclusions
As mentioned in the Literature Review, over 70% of projects fail, and among the
This study introduces a new integrated risk analysis approach—PFMEA-RDEA-
reasons are the inapplicability of management strategies, including risk management (RM),
ML—designed to prioritize process risks in a business process re-engineering project by
as well as the failure to consider various factors during the analysis. As shown in the
introducing BD-COST and BD-DURATION as undesirable outputs to the conventional
figure, risk prioritization using the RPN approach differs completely from prioritization
PFMEA-DEA system. This pushes the analysis to another dimension, allowing for the
according to other approaches (Figure 10). This approach enables decision makers to have
consideration of uncertainty by integrating the coefficients of perturbation in the param-
a clearer and more multi-dimensional view of process management and reengineering,
eter values of the system, typically based on expert judgment.
given the verified relationship between added parameters and operational performance.
The results obtained allow decision makers to redesign the process by focusing on ac-
tivities that generate the highest risks according to this new approach and taking the
necessary measures.
Eng 2024, 5 1378
Figure
Figure 10.
10. Average
Average efficiency
efficiency scores
scores of
of the
the proposed approaches.
Moreover,
As mentioned the rapid
in the development of machine-learning
Literature Review, prediction
over 70% of projects fail, algorithms
and amongprovides
the rea-
the possibility
sons of continuous
are the inapplicability ofexecution
management of this approach,
strategies, thus allowing
including for the automatic
risk management (RM),
generation
as well as the of failure
new scores and priorities
to consider variousonce
factorspartial or complete
during reengineering
the analysis. As shown in actions or
the fig-
processes are established. The application of this approach in
ure, risk prioritization using the RPN approach differs completely from prioritization ac-a company operating in
the highly competitive automotive sector highlights the distinction
cording to other approaches. This approach enables decision makers to have a clearer and and observation of
the effect
more of integrating view
multi-dimensional new parameters in risk analysis
of process management andand also the perception
re-engineering, given theofver-
the
uncertainty
ified effect between
relationship modeled added by the perturbation
parameters and percentages
operational in the RDEA model.
performance. The results
However,
obtained allow we were not
decision able to
makers to redesign
address alltherisks but only
process the riskson
by focusing of activities
a part of the
thatwhole
gen-
process to highlight the importance of the added factors. Another
erate the highest risks according to this new approach and taking the necessary measures. limitation is the size of
the database to better train the model and further minimize errors.
Moreover, the rapid development of machine-learning prediction algorithms pro-
videsIn future
the work,of
possibility it continuous
would be interesting
execution of to this
extend the analysis
approach, to financial
thus allowing for risks and
the auto-
product risks, as well as to benchmark the process with other internal
matic generation of new scores and priorities once partial or complete re-engineering ac- or external processes.
Another
tions research direction
or processes would be
are established. Theto application
explore newofAIthis technologies,
approach in such as reinforcement
a company operat-
learning and deep learning, in this type of application.
ing in the highly competitive automotive sector highlights the distinction and observation
of the effect of integrating new parameters in risk analysis and also the perception of the
Author Contributions: Conceptualization, R.H., M.M. and L.A.; methodology, R.H., M.M. and L.A.;
uncertainty effect modeled by the perturbation percentages in the RDEA model.
software, R.H., M.M. and L.A.; validation, R.H., M.M. and L.A.; formal analysis, R.H., M.M. and
However, we were not able to address all risks but only the risks of a part of the
L.A.; investigation, R.H., M.M. and L.A.; resources, R.H., M.M. and L.A.; data curation, R.H., M.M.
whole
and L.A.;process to highlightdraft
writing—original the preparation,
importance R.H.;of thewriting—review
added factors.and Another limitation
editing, R.H., M.M. is and
the
size
L.A.;of the database
visualization, to supervision,
R.H.; better train M.M.
the model andproject
and L.A.; further minimize errors.
administration, M.M. and L.A.; funding
In future
acquisition, work,
R.H., M.M.it andwouldL.A.beAllinteresting
authors have to extend
read and the analysis
agreed to published
to the financial risks and
version of
product risks, as well as to benchmark the process with other internal or external pro-
the manuscript.
cesses. Another research direction would be to explore new AI technologies, such as rein-
Funding: This research received no external funding.
forcement learning and deep learning, in this type of application.
Institutional Review Board Statement: Not applicable.
Author
InformedContributions: Conceptualization,
Consent Statement: R.H., M.M. and L.A.; methodology, R.H., M.M. and L.A.;
Not applicable.
software, R.H., M.M. and L.A.; validation, R.H., M.M. and L.A.; formal analysis, R.H., M.M. and
Data investigation,
L.A.; R.H., M.M.Data
Availability Statement: and are available
L.A.; on R.H.,
resources, request dueand
M.M. to restrictions.
L.A.; data curation, R.H., M.M.
and L.A.; writing—original draft preparation, R.H.; writing—review and editing, R.H., M.M. and
Conflicts of Interest: The authors declare no conflicts of interest.
L.A.; visualization, R.H.; supervision, M.M. and L.A.; project administration, M.M. and L.A.; fund-
References ing acquisition, R.H., M.M. and L.A. All authors have read and agreed to the published version of
the manuscript.
1. Harmon, P. Business Process Change: A Business Process Management Guide for Managers and Process Professionals; Morgan Kaufmann
Publishers: Burlington, MA,Funding: This research received no external funding.
USA, 2019.
2. Nisar, Q.A.; Ahmad, S.; Ahmad, U. Exploring factors that contribute to success of business process reengineering and impact of
Institutional Review Board Statement: Not applicable.
business process reengineering on organizational performance: A qualitative descriptive study on banking sector at Pakistan.
Informed
Asian J. Multidiscip. Stud. 2014, Consent Statement: Not applicable.
2, 219–224.
Data Availability Statement: Data are available on request due to restrictions.
Eng 2024, 5 1379
3. Tsakalidis, G.; Vergidis, K. Towards a Comprehensive Business Process Optimization Framework. In Proceedings of the 2017
IEEE 19th Conference on Business Informatics (CBI), Thessaloniki, Greece, 24–27 July 2017; IEEE: Piscataway, NJ, USA, 2017;
Volume 1, pp. 129–134. [CrossRef]
4. Ghanadbashi, S.; Ramsin, R. Towards a method engineering approach for business process reengineering. IET Softw. 2016, 10,
27–44. [CrossRef]
5. Weerakkody, V.; Janssen, M.; Dwivedi, Y.K. Transformational change and business process reengineering (BPR): Lessons from the
British and Dutch public sector. Gov. Inf. Q. 2011, 28, 320–328. [CrossRef]
6. Erim, A.; Vayvay, O. Is the business process reengineering (BPR) proved itself to be a trustable change management approach for
multinational corporations’ case studies from the literature. J. Aeronaut. Space Technol. 2010, 4, 23–30.
7. Goksoy, A.; Ozsoy, B.; Vayvay, O. Business process reengineering: Strategic tool for managing organizational change an application
in a multinational company. Int. J. Bus. Manag. 2012, 7, 89–112. [CrossRef]
8. Razalli, M.R.; Ringim, K.J.; Hasnan, N.; Hassan, M.G. A framework of best practices in managing business reengineering for
Islamic. J. Adv. Manag. Sci. 2015, 3, 22–25. [CrossRef]
9. Bhaskar, H.L. A critical analysis of information technology and business process reengineering. Int. J. Product. Qual. Manag. 2016,
19, 98–115. [CrossRef]
10. Chiplunkar, C.; Deshmukh, S.G.; Chattopadhyay, R. Application of principles of event related open systems to business process
reengineering. Comput. Ind. Eng. 2003, 45, 347–374. [CrossRef]
11. Hussain, M.; Saleh, M.; Akbar, S.; Jan, Z. Factors affecting readiness for business process reengineering-developing and proposing
a conceptual model. Eur. J. Bus. Manag. 2014, 6, 55–60.
12. Habib, M.N.; Shah, A. Business process reengineering: Literature review of approaches and applications. In Proceedings of the
3rd Asia-Pacific Business Research Conference, Kuala Lumpur, Malaysia, 25–26 February 2013; pp. 1–25, ISBN 978-1-922069-19-1.
13. Alghamdi, H.A.; Alfarhan, M.A.; Abdullah, A.L. BPR: Evaluation of existing methodologies and limitations. Int. J. Comput. Trends
Technol. 2014, 7, 224–227. [CrossRef]
14. Bhaskar, H.L. Business process reengineering framework and methodology: A critical study. Int. J. Serv. Oper. Manag. 2018, 29,
527–556. [CrossRef]
15. Covello, V.T.; Merkhoher, M.W. Risk Assessment Methods: Approaches for Assessing Health and Environmental Risks; Springer Science
& Business Media: New York, NY, USA, 2013.
16. Arabian-Hoseynabadi, H.; Oraee, H.; Tavner, P.J. Failure modes and effects analysis (FMEA) for wind turbines. Int. J. Electr. Power
Energy Syst. 2010, 32, 817–824. [CrossRef]
17. Feili, H.R.; Akar, N.; Lotfizadeh, H.; Bairampour, M.; Nasiri, S. Risk analysis of geothermal power plants using Failure Modes and
Effects Analysis (FMEA) technique. Energy Convers. Manag. 2013, 72, 69–76. [CrossRef]
18. Trafialek, J.; Kolanowski, W. Application of Failure Mode and Effect Analysis (FMEA) for audit of HACCP system. Food Control
2014, 44, 35–44. [CrossRef]
19. Rezaee, M.J.; Yousefi, S.; Babaei, M. Multi-stage cognitive map for failures assessment of production processes: An extension in
structure and algorithm. Neurocomputing 2017, 232, 69–82. [CrossRef]
20. An, Q.; Meng, F.; Ang, S.; Chen, X. A new approach for fair efficiency decomposition in two-stage structure system. Oper. Res.
2018, 18, 257–272. [CrossRef]
21. Yan, L.; Tong, W.; Hui, D.; Zongzhi, W. Research and application on risk assessment DEA model of crowd crushing and trampling
accidents in subway stations. Procedia Eng. 2012, 43, 494–498. [CrossRef]
22. Rezaee, M.J.; Salimi, A.; Yousefi, S. Identifying and managing failures in stone processing industry using cost-based FMEA. Int. J.
Adv. Manufact. Technol. 2017, 88, 3329–3342. [CrossRef]
23. Sadjadi, S.J.; Omrani, H. Data envelopment analysis with uncertain data: An application for Iranian electricity distribution
companies. Energy Policy 2008, 36, 4247–4254. [CrossRef]
24. Bertsimas, D.; Sim, M. The price of robustness. Operat. Res. 2004, 52, 35–53. [CrossRef]
25. Zhu, N.; Zhu, C.; Emrouznejad, A. A combined machine learning algorithms and DEA method for measuring and predicting the
efficiency of Chinese manufacturing listed companies. J. Manag. Sci. Eng. 2020, 6, 435–448. [CrossRef]
26. Fan, Y.; Stevenson, M. A review of supply chain risk management: Definition, theory, and research agenda. Int. J. Phys. Distrib.
Logist. Manag. 2018, 48, 205–230. [CrossRef]
27. Abidoye, R.B.; Chan, A.P.C.; Abidoye, F.A.; Oshodi, O.S. Predicting property price index using artificial intelligence techniques.
Int. J. Hous. Mark. Anal. 2019, 12, 1072–1092. [CrossRef]
28. Sun, T.; Sales, L.J. Predicting public procurement irregularity: An application of neural networks. J. Emerg. Technol. Account. 2018,
15, 141–154. [CrossRef]
29. Zhang, W.; Feng, X.; Goerlandt, F.; Liu, Q. Towards a convolutional neural network model for classifying regional ship collision
risk levels for waterway risk analysis. Rel. Eng. Syst. Saf. 2020, 204, 107127. [CrossRef]
30. Salehi, V.; Veitch, B.; Musharraf, M. Measuring and improving adaptive capacity in resilient systems by means of an integrated
DEA-machine learning approach. Appl. Ergonom. 2020, 82, 102975. [CrossRef]
31. Yin, G. BPR application. Mod. Appl. Sci. 2010, 4, 96–101. [CrossRef]
32. Hammer, M.; Champy, J. Reengineering the corporation: A manifesto for business revolution. Bus. Horiz. 1993, 36, 90–91.
[CrossRef]
Eng 2024, 5 1380
33. Hammer, M. Reengineering work: Don’t automate, obliterate. Harv. Bus. Rev. 1990, 68, 104–112.
34. Kontio, J. Business process re-engineering: A case study at Turku University of Applied Sciences. In Proceedings of the European
and Mediterranean Conference on Information Systems, Valencia, Spain, 24–26 June 2007; pp. 24–26.
35. Setegn, D.; Ensermu, M.; Moorthy, P.K. Assessing the effect of business process reengineering on organizational performance:
A case study of Bureau of Finance and Economic Development (BOFED), Oromia Regional State, Ethiopia. Res. World 2013, 4,
115–123.
36. Bhaskar, H.L.; Singh, R.P. Business process reengineering: A recent review. Glob. J. Bus. Manag. 2014, 8, 24–51.
37. Eke, G.J.; Achilike, A.N. Business process reengineering in organizational performance in Nigerian banking sector. Acad. J.
Interdiscip. Stud. 2014, 3, 113–124. [CrossRef]
38. Mlay, S.V.; Zlotnikova, I.; Watundu, S. A quantitative analysis of business process reengineering and organizational resistance:
The case of Uganda. Afr. J. Inf. Syst. 2013, 5, 1–26.
39. Jamali, G.; Abbaszadeh, M.A.; Ebrahimi, M.; Maleki, T. Business process reengineering implementation: Developing a causal
model of critical success factors. Int. J. E-Educ. E-Bus. E-Manag. E Learn. 2011, 1, 354–358. [CrossRef]
40. Al-Anqoudi, Y.; Al-Hamdani, A.; Al-Badawi, M.; Hedjam, R. Using Machine Learning in Business Process Re-Engineering. Big
Data Cogn. Comput. 2021, 5, 61. [CrossRef]
41. Omidi, A.; Khoshtinat, B. Factors Affecting the Implementation of Business Process Reengineering: Taking into Account the
Moderating Role of Organizational Culture (Case Study: Iran Air). Procedia Econ. Financ. 2016, 36, 425–432. [CrossRef]
42. Hussein, B.; Hammoud, M.; Bazzi, H.; Haj-Ali, A. PRISM—Process reengineering integrated spiral model: An agile approach to
business process reengineering (BPR). Int. J. Bus. Manag. 2014, 9, 134–142. [CrossRef]
43. Motwani, J.; Kumar, A.; Jiang, J.; Youssef, M. Business process reengineering: A theoretical framework and an integrated model.
Int. J. Oper. Prod. Manag. 1998, 18, 964–977. [CrossRef]
44. Luo, W.; Tung, Y.A. A framework for selecting business process modeling methods. Ind. Manag. Data Syst. 1999, 99, 312–319.
[CrossRef]
45. Project Management Institute. A Guide to the Project Management Body of Knowledge: PMBOK Guide, 4th ed.; Project Management
Institute: Newtown Square, PA, USA, 2009.
46. ISO 31000:2009; Risk Management. ISO: Geneva, Switzerland, 2009.
47. Duhamel, F.; Carbone, V.; Moatti, V. The impact of internal and external collaboration on the performance of supply chain risk
management. Int. J. Logist. Syst. Manag. 2016, 23, 534–557. [CrossRef]
48. Purdy, G. ISO 31000: 2009—Setting a new standard for risk management. Risk Anal. Int. J. 2010, 30, 881–886. [CrossRef] [PubMed]
49. Lyon, B.K.; Popov, G. Risk treatment strategies: Harmonizing the hierarchy of controls and inherently safer design concepts. Prof.
Saf. 2019, 64, 34–43.
50. Cox, L.A., Jr.; Babayev, D.; Huber, W. Some limitations of qualitative risk rating systems. Risk Anal. 2005, 25, 651–662. [CrossRef]
[PubMed]
51. de Almeida, A.T.; Alencar, M.H.; Garcez, T.V.; Ferreira, R.J.P. A systematic literature review of multicriteria and multi-objective
models applied in risk management. IMA J. Manage. Math. 2017, 28, 153–184. [CrossRef]
52. Kaewfak, K.; Huynh, V.-N.; Ammarapala, V.; Ratisoontorn, N. A risk analysis based on a two-stage model of fuzzy AHP-DEA for
multimodal freight transportation systems. IEEE Access 2020, 8, 153756–153773. [CrossRef]
53. Bowles, J.B.; Peláez, C.E. Fuzzy logic prioritization of failures in a system failure mode, effects and criticality analysis. Reliab. Eng.
Syst. Saf. 1995, 50, 203–213. [CrossRef]
54. Wang, Y.M.; Chin, K.S.; Poon, G.K.K.; Yang, J.B. Risk evaluation in failure mode and effects analysis using fuzzy weighted
geometric mean. Expert Syst. Appl. 2009, 36, 1195–1207. [CrossRef]
55. Chang, K.H.; Cheng, C.H. Evaluating the risk of failure using the fuzzy OWA and DEMATEL method. J. Intell. Manuf. 2011, 22,
56. Rakesh, R.; Jos, B.C.; Mathew, G. FMEA analysis for reducing breakdowns of a sub system in the life care product manufacturing
industry. Int. J. Eng. Sci. Innov. Technol. 2013, 2, 218–225.
57. Liu, H.-C.; Liu, L.; Liu, N.; Mao, L.-X. Risk evaluation in failure mode and effects analysis with extended VIKOR method under
fuzzy environment. Expert Syst. Appl. 2012, 39, 12926–12934. [CrossRef]
58. Chin, K.-S.; Wang, Y.-M.; Poon, G.K.K.; Yang, J.-B. Failure mode and effects analysis by data envelopment analysis. Decis. Support
Syst. 2009, 48, 246–256. [CrossRef]
59. Chang, D.S.; Chung, J.H.; Sun, K.L.; Yang, F.C. A novel approach for evaluating the risk of health care failure modes. J. Med. Syst.
2012, 36, 3967–3974. [CrossRef] [PubMed]
60. Chang, D.; Sun, K.P. Applying DEA to enhance assessment capability of FMEA. Int. J. Qual. Rel. Manag. 2009, 26, 629–643.
[CrossRef]
61. Garcia, P.A.D.A.; Junior, L.; Curty, I.; Oliveira, M.A. A weight restricted DEA model for FMEA risk prioritization. Production 2013,
23, 500–507. [CrossRef]
62. Vahdani, B.; Salimi, M.; Charkhchian, M. A new FMEA method by integrating fuzzy belief structure and TOPSIS to improve risk
evaluation process. Int. J. Adv. Manuf. Technol. 2015, 77, 357–368. [CrossRef]
63. Baghery, M.; Yousefi, S.; Rezaee, M.J. Risk measurement and prioritization of auto parts manufacturing processes based on process
failure analysis, interval data envelopment analysis and grey relational analysis. J. Intell. Manuf. 2016, 29, 1803–1825. [CrossRef]
Eng 2024, 5 1381
64. Sakthivel, G.; Ikua, B.W. Failure mode and effect analysis using fuzzy analytic hierarchy process and GRA TOPSIS in manufactur-
ing industry. Int. J. Product. Qual. Manag. 2017, 22, 466–484. [CrossRef]
65. Razi, F.F.; Hoseini, E. Proposing a new model of failure mode and effect analysis for clustering and ranking of manufacturing
process. Int. J. Product. Qual. Manag. 2017, 21, 45–71. [CrossRef]
66. Ahmadi, M.; Molana, S.M.H.; Sajadi, S.M. A hybrid FMEA-TOPSIS method for risk management, case study: Esfahan Mobarakeh
Steel Company. Int. J. Process Manag. Benchmarking 2017, 7, 397–408. [CrossRef]
67. Certa, A.; Enea, M.; Galante, G.M.; La Fata, C.M. ELECTRE TRI-based approach to the failure modes classification on the basis of
risk parameters: An alternative to the risk priority number. Comput. Ind. Eng. 2017, 108, 100–110. [CrossRef]
68. Fattahi, R.; Khalilzadeh, M. Risk evaluation using a novel hybrid method based on FMEA, extended MULTIMOORA, and AHP
methods under fuzzy environment. Saf. Sci. 2018, 102, 290–300. [CrossRef]
69. Peeters, J.F.W.; Basten, R.J.I.; Tinga, T. Improving failure analysis efficiency by combining FTA and FMEA in a recursive manner.
Reliab. Eng. Syst. Saf. 2018, 172, 36–44. [CrossRef]
70. Yousefi, S.; Alizadeh, A.; Hayati, J.; Baghery, M. HSE risk prioritization using robust DEA-FMEA approach with undesirable
outputs: A study of automotive parts industry in Iran. Saf. Sci. 2018, 102, 144–158. [CrossRef]
71. Baynal, K.; Sarı, T.; Akpınar, B. Risk management in automotive manufacturing process based on FMEA and grey relational
analysis: A case study. Adv. Prod. Eng. Manag. 2018, 13, 69–80. [CrossRef]
72. Bhuvanesh Kumar, M.; Parameshwaran, R. Fuzzy integrated QFD, FMEA framework for the selection of lean tools in a
manufacturing organization. Prod. Plan. Control. 2018, 29, 403–417. [CrossRef]
73. Liu, H.C.; Liu, L.; Liu, N. Risk evaluation approaches in failure mode and effects analysis: A literature review. Expert Syst. Appl.
2013, 40, 828–838. [CrossRef]
74. Liu, H.-C.; You, J.-X.; Lin, Q.-L.; Li, H. Risk assessment in system FMEA combining fuzzy weighted average with fuzzy
decision-making trial and evaluation laboratory. Int. J. Comput. Integr. Manuf. 2015, 28, 701–714. [CrossRef]
75. Rezaee, M.J.; Yousefi, S.; Eshkevari, M.; Valipour, M.; Saberi, M. Risk analysis of health, safety and environment in chemical
industry integrating linguistic FMEA, fuzzy inference system and fuzzy DEA. Stochastic Environ. Res. Risk Assess. 2020, 34,
76. Liu, H.-C.; Chen, X.-Q.; Duan, C.-Y.; Wang, Y.-M. Failure mode and effect analysis using multi-criteria decision makin methods: A
systematic literature review. Comput. Ind. Eng. 2019, 135, 881–897. [CrossRef]
77. Norman, M.; Stoker, B. Data Envelopment Analysis: The Assessment of Performance; Wiley: Hoboken, NJ, USA, 1991.
78. Wu, J.; Chu, J.; Sun, J.; Zhu, Q. DEA cross-efficiency evaluation based on Pareto improvement. Eur. J. Oper. Res. 2016, 248, 571–579.
[CrossRef]
79. Ray, A.; Chaudhuri, A.K. Smart healthcare disease diagnosis and patient management: Innovation, improvement and skill
development. Mach. Learn. Appl. 2021, 3, 100011. [CrossRef]
80. Leo, M.; Sharma, S.; Maddulety, K. Machine learning in banking risk management: A literature review. Risks 2019, 7, 29.
[CrossRef]
81. Zhang, J.; Li, Z.; Pu, Z.; Xu, C. Comparing prediction performance for crash injury severity among various machine learning and
statistical methods. IEEE Access 2018, 6, 60079–60087. [CrossRef]
82. Chandrinos, S.K.; Sakkas, G.; Lagaros, N.D. AIRMS: A risk management tool using machine learning. Expert Syst. Appl. 2018, 105,
34–48. [CrossRef]
83. Paltrinieri, N.; Comfort, L.; Reniers, G. Learning about risk: Machine learning for risk assessment. Saf. Sci. 2019, 118, 475–486.
[CrossRef]
84. Gondia, A.; Siam, A.; El-Dakhakhni, W.; Nassar, A.H. Machine learning algorithms for construction projects delay risk prediction.
J. Construct. Eng. Manag. 2020, 146, 04019085. [CrossRef]
85. Charnes, A.; Cooper, W.W.; Rhodes, E. Measuring the efficiency of decision making units. Eur. J. Oper. Res. 1978, 2, 429–444.
[CrossRef]
86. Ben-Tal, A.; Nemirovski, A. Robust solutions to uncertain programs. Oper. Res. Lett. 1999, 25, 1–13. [CrossRef]
87. Soyster, A.L. Technical note—Convex programming with set-inclusive constraints and applications to inexact linear programming.
Operat. Res. 1973, 21, 1154–1157. [CrossRef]
88. Ben-Tal, A.; Nemirovski, A. Robust solutions of linear programming problems contaminated with uncertain data. Math. Program
2000, 88, 411–424. [CrossRef]
89. Lima-Junior, F.R.; Carpinetti, L.C.R. Predicting supply chain performance based on SCOR metrics and multilayer perceptron
neural networks. Int. J. Prod. Econ. 2019, 212, 19–38. [CrossRef]
90. Fath, A.H.; Madanifar, F.; Abbasi, M. Implementation of multilayer perceptron (MLP) and radial basis function (RBF) neural
networks to predict solution gas-oil ratio of crude oil systems. Petroleum 2020, 6, 80–91. [CrossRef]
91. Seiford, L.M.; Zhu, J. Modeling undesirable factors in efficiency evaluation. Eur. J. Oper. Res. 2002, 142, 16–20. [CrossRef]
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual
author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to
people or property resulting from any ideas, methods, instructions or products referred to in the content.
View publication stats

Eng 05 00071

Uploaded by

Copyright:

Available Formats

Eng 05 00071

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Eng 05 00071

Uploaded by

Copyright:

Available Formats

See discussions, stats, and author profiles for this publication at: https://www.researchgate.

Business Process Reengineering Projects: Application in Automotive Sector

Article in Eng—Advances in Engineering · July 2024

The user has requested enhancement of the downloaded file.

Citation: Hicham, R.; Abdallah, L.;

Eng 2024, 5, 1360–1381. https://doi.org/10.3390/eng5030071 https://www.mdpi.com/journal/eng

Table 1. BPR success and failure factors.

Category Factor Success Failure

2.6. Machine Learning in Risk Management

produced outstanding results. ML algorithms simulate human learning behaviors to gain

∑ aij yj + (Γi − ⌊Γi ⌋)ait yt } ≤ bi ∀i

∑ aij x∗j zij s.t.j∈∑J zij ≤ Γi , i ≤ zij ≤ 1 ∀ j ∈ Ji

β i ( x ∗ , Γi ) = max { ∑ aij′ | x j |} (7)

∑ vi xij − ∑ur yrj − Γj pj − ∑qij ≥ 0, (8)

Figure 2. Architecture of a neural network.

Table 2. Scores of output costs and duration.

Table 3. Undesirable values of outputs.

Table 4. Risk prioritization using the PFMEA-RDEA approach.

R54 36 7 0.843221 51 0.5413899999999998 7 0.5413899999999998 7

This comparison (Figure

6. Discussion and Conclusions

View publication stats

You might also like