Predictive Maintenance

SIMAP is the abbreviated name for the Intelligent System for Predictive Maintenance. It is a software application addressed to the diagnosis in real-time of industrial processes. It takes into account the information coming in real-time from different sensors and other information sources and tries to detect possible anomalies in the normal behaviour expected of the industrial components. The incipient detection of anomalies allows for an early diagnosis and the possibility to plan effective maintenance actions. Also, the continuous monitoring performed allows for an estimation in a qualitative form of the health condition of the components. SIMAP is a general tool oriented to the diagnosis and maintenance of industrial processes, however the first experience of its application has been at a windfarm. In this real case, SIMAP is able to optimize and to dynamically adapt a maintenance calendar for a monitored windturbine according to the real needs and operating life of it as well as other technical and economical criteria. In particular this paper presents the application of SIMAP to the health condition monitoring of a windturbine gearbox as an example of its capabilities and main features.

Nowadays, the railway industry is in a position where it is able to exploit the opportunities created by the IIoT (Industrial Internet of Things) and enabling communication technologies under the paradigm of Internet of Trains. This review details the evolution of communication technologies since the deployment of GSM-R, describing the main alternatives and how railway requirements, specifications and recommendations have evolved over time. The advantages of the latest generation of broadband communication systems (e.g., LTE, 5G, IEEE 802.11ad) and the emergence of Wireless Sensor Networks (WSNs) for the railway environment are also explained together with the strategic roadmap to ensure a smooth migration from GSM-R. Furthermore, this survey focuses on providing a holistic approach, identifying scenarios and architectures where railways could leverage better commercial IIoT capabilities. After reviewing the main industrial developments, short and medium-term IIoT-enabled services for smart railways are evaluated. Then, it is analyzed the latest research on predictive maintenance, smart infrastructure, advanced monitoring of assets, video surveillance systems, railway operations, Passenger and Freight Information Systems (PIS/FIS), train control systems, safety assurance, signaling systems, cyber security and energy efficiency. Overall, it can be stated that the aim of this article is to provide a detailed examination of the state-of-the-art of different technologies and services that will revolutionize the railway industry and will allow for confronting today challenges.

Abstract:- Wind Power Plants (WPP) is the fastest growing energy sector. WPP consisting from a single turbine to as many as several hundred turbines. The acceptance of wind-generated power by the financial and developer communities from Romania as a viable enterprise is influenced by the risk associated with the capital equipment reliability. Increased risk or at least the perception of increased risk is generally accompanied by increased financial fees or interest rates. Wind turbine system reliability is considered to be an important component in any wind energy project. All above has developed the interest and need for maintenance services for wind turbines (WT). The aim of this paper is to identify the matters from maintenance in WPP areas and to do a literature review of the major aspects in a wind turbine that should be monitored.

Remaining useful life (RUL) prediction is an advanced technique for system maintenance scheduling. Most of existing RUL prediction methods are only interested in the precision of RUL estimation; the adverse impact of over-estimated RUL on maintenance scheduling is not of concern. In this work, an RUL estimation method with risk-averse adaptation is developed which can reduce the over-estimation rate while maintaining a reasonable under-estimation level. The proposed method includes a module of degradation feature selection to obtain crucial features which reflect system degradation trends. Then, the latent structure between the degradation features and the RUL labels is modeled by a support vector regression (SVR) model and a long short-term memory (LSTM) network, respectively. To enhance the prediction robustness and increase its marginal utility, the SVR model and the LSTM model are integrated to generate a hybrid model via three connection parameters. By designing a cost function with penalty mechanism, the three parameters are determined using a modified grey wolf optimization algorithm. In addition, a cost metric is proposed to measure the benefit of such a risk-averse predictive maintenance method. Verification is done using an aero-engine data set from NASA. The results show the feasibility and effectiveness of the proposed RUL estimation method and the predictive maintenance strategy.

This paper presents results from a case study in predictive maintenance at a distribution warehouse. A simulation model was built with ARENA 5.0 for integrating predictive maintenance strategies with production planning strategies, for a conveyor system. Equipment health was monitored using condition-based parameters such as temperature and vibration for mechanical and electrical components such as rollers, electrical motors, and gearboxes. This diagnostic information was then integrated with a simulation model to simulate various equipment breakdown and failure conditions. Integration of condition-based monitoring of conveying equipment with a simulation model of the distribution system has provided a useful analytical tool for management to reduce production downtime due to unplanned maintenance activities -in this instance, downtime was reduced by more than 50% and work in process inventory was reduced by more than 65%.

Most of the machine learning-based intrusion detection tools developed for Industrial Control Systems (ICS) are trained on network packet captures, and they rely on monitoring network layer traffic alone for intrusion detection. This approach produces weak intrusion detection systems, as ICS cyber-attacks have a real and significant impact on the process variables. A limited number of researchers consider integrating process measurements. However, in complex systems, process variable changes could result from different combinations of abnormal occurrences. This paper examines recent advances in intrusion detection algorithms, their limitations, challenges and the status of their application in critical in-frastructures. We also introduce the discussion on the similarities and conflicts observed in the development of machine learning tools and techniques for fault diagnosis and cybersecurity in the protection of complex systems and the need to establish a clear difference between them. As a case study, we discuss special characteristics in nuclear power control systems and the factors that constraint the direct integration of security algorithms. Moreover, we discuss data reliability issues and present references and direct URL to recent open-source data repositories to aid researchers in developing data-driven ICS intrusion detection systems.

The currently applied maintenance strategies, including Reactive and Preventive maintenance can be considered obsolete. The constant improvements in Information and Communication Technologies as well as in Digital Technologies along with the increase of computational power, have facilitated the development of new Artificial Intelligence algorithms to integrate cognition in computational systems. This trend is posing a great challenge for engineers, as such developments will enable the creation of robust systems that can monitor the current status of the machines and by extension to predict unforeseeable situations. Furthermore, Smart Computers will be capable of examining all possible scenarios and suggest viable solutions in a fraction of time compared to humans. Therefore, in this paper, the modelling, design and development of a Predictive Maintenance and Remote Monitoring system are proposed, based on the utilization of Artificial Intelligence algorithms for data acquisition, fusion, and postprocessing. In addition to that, the proposed framework will integrate a Mixed Reality application for the intuitive visualization of the data, that will ultimately facilitate production and maintenance engineers to monitor the condition of the machines, and most importantly to get an accurate prediction of the oncoming failures.

The practice of predictive maintenance depends significantly on the diagnosis of in-service performance and on the decision criteria for the selection of maintenance tasks. The definition of these criteria is limited because several actors are involved, each with their own perspectives of performance and maintenance needs. This paper discusses a set of 17 criteria to help the maintenance choice for building façades, from three viewpoints: physical performance, risk and costs. A group of experts was surveyed and 30 answers were received. Therefore, each criterion will be discussed according to the answers collected.

Predictive maintenance (PdM) is a successful strategy used to reduce cost by minimizing the breakdown stoppages and production loss. The massive amount of data that results from the integration between the physical and digital systems of the production process makes it possible for deep learning (DL) algorithms to be applied and utilized for fault prediction and diagnosis. This paper presents a hybrid convolutional neural network based and long short-term memory network (CNN-LSTM) approach to a predictive maintenance problem. The proposed CNN-LSTM approach enhances the predictive accuracy and also reduces the complexity of the model. To evaluate the proposed model, two comparisons with regular LSTM and gradient boosting decision tree (GBDT) methods using a freely available dataset have been made. The PdM model based on CNN-LSTM method demonstrates better prediction accuracy compared to the regular LSTM, where the average F-Score increases form 93.34% in the case of regular LSTM to 9...

The accuracy of a predictive system is critical for predictive maintenance and to support the right decisions at the right times. Statistical models, such as ARIMA and SARIMA, are unable to describe the stochastic nature of the data. Neural networks, such as long short-term memory (LSTM) and the gated recurrent unit (GRU), are good predictors for univariate and multivariate data. The present paper describes a case study where the performances of long short-term memory and gated recurrent units are compared, based on different hyperparameters. In general, gated recurrent units exhibit better performance, based on a case study on pulp paper presses. The final result demonstrates that, to maximize the equipment availability, gated recurrent units, as demonstrated in the paper, are the best options.

The Internet of Things (IoT) concept facilitates our life in many areas. One of the facilities provided in this area is undoubtedly condition monitoring. Unlike regular maintenance, IoT systems that perform continuous control operations can provide great advantages to the company with a warning that a serious failure will occur. It is a vital importance to determine defective bearings during the rotation of the power generating and power consuming machines without reaching the critical level. In this study; an experimental setup was created, and a Condition Monitoring Application (CMA) was performed in the laboratory environment which could monitor vibration, temperature, acoustic emission (AE), current and revolution measurements for ORS 6203 type defective bearing detection. In the designed test setup, a microcontroller platform used as a system brain, a direct current machine with a shaft mounted bearing, and miscellaneous sensors used such as 3-axis accelerometer that senses vibrations, a hall sensor module for revolution measure, a microphone module for AE detection, current and voltage sensor modules for power consumption measurement, contactless temperature sensor module for temperature measurement. CMA has been designed for monitoring of system via Bluetooth module. With the help of the microcontroller platform, the data collected from the sensors is transmitted wirelessly to the Android smartphone to be plotted and recorded. After the data exceeds certain thresholds, the control system is able to provide SMS and/or e-mail notification to the related maintenance team with the Android smartphone. Linear Discriminant Analysis (LDA), Random Forest (RF), Support Vector Machine (SVM), k-Nearest Neighbor (kNN), and Decision Tree (DT) algorithms applied to the collected data and models were created. As a result of accuracy analysis over %96 success was achieved for all models.

The current study focuses on the basic role of computers in the areas of maintenance, especially in the application of predictive maintenance systems from the beginning (fault analysis, save information, planning, organization, observation, down to the maintenance team). Computer works to provide full support to the maintenance team through the
prediction of protected machines and equipment needing form signals that arrive from the sensors, to the sensors associated with the system to control panels and control system. The maintenance operated of Mosul Dam as an example for the development of the rest of
hydroelectric stations in Iraq because it's one of the largest of these stations and the most productive electric power. The study aim at the conversion, maintenance system in the Mosul Dam to predictive maintenance by using the computer through the development of system
maintenance current, and post range of machinery and equipment and software after making sure of the safety of the proposed system then calculating the standard credibility for it .The study shows this process of linking, which proposed system-style system ideal multi (overlapped) to achieve optimum performance of the system proposed, it can be can duded that the percentage 8% to 12% reduction in maintenance costs and increase reach to 40% of the value of the total production of electric power dam.

Oil analysis is a long-term program that, where relevant, can eventually be more predictive than any of the other technologies. It can take years for a plant's oil program to reach this level of sophistication and effectiveness. This book includes what all practitioners need to know to build an oil analysis program for their machine inspection. This book includes three real case studies and numerous industrial examples to improve machine reliability and enhance the condition monitoring program.

In this study, a motor condition diagnostic was achieved through the implementation of an Artificial Neural Network (ANN), successfully applying into a predictive maintenance system. Electrical motors were monitored to obtain data to train the ANN. Out of these monitoring, vibration signatures were used as the input layer, and the motor condition was used as the expert training information. The main objective was to apply neural networks to a condition based predictive maintenance in order to detect the type of system's failure. As a result, the expert system can be utilized to decrease the possible failures in operating system and increase the availability and effectiveness of a system.

Partial discharge monitoring is an effective on-line predictive maintenance test for motors and generators, as well as other electrical distribution equipment. The benefits of on-line testing allow for equipment analysis and diagnostics during normal production. Corrective actions can be planned and implemented, resulting in reduced unscheduled downtime. This paper will present a theory to promote the understanding of partial discharge technology, as well as various implementation and measurement techniques that have evolved in the industry. Then insulation modeling and partial discharge modeling in electrical machines will be introduced. At last traditional partial discharge test methods in electric machines will compare to new method of partial discharge monitoring and corrective actions will interpret.

Reliability centered maintenance (RCM) has a key role in the quality system of thermal power plants. Electricity production is definitely not only production of a product, but also becomes a customer service. Reliability is the top quality tier of this service. Incorporation in the Integrated energy system means fast transformations of organization on all levels. The reliability of modern generation components basically influences the efficiency and capacity of a power plant as a whole. This paper presents the results of RCM practice on Unit Two of The Thermal Power Plant ″Nikola Tesla -B″, 2x600 MW, Yugoslavia. RCM implementation on current problems during exploitation emphasized problems with the boiler tubing system. The methodological approach included outages analyses, marking of the most significant ones, determination of main causes of damage (determination of the material exhaustion state based on expert analyses), application of adequate remaining life assessment methodology and finally the recommendations. Based on these analyses, certain technical solutions were performed and as a result, the mean time between failures of the plant increased, as well as its reliability. According to cost efficiency, RCM methodology presented the most effective cost-benefit method for reliability upgrade.

The volume is a theoretical and practical manual for thermographic inspections in electrical and industrial field. It contains 230 pages of theory and practical informations about guidelines, criteria, applications in electrical and industrial surveys.
In the early chapters the book provides the physical basis of thermography, the technical characteristics of the cameras and their meanings, and the basic measurement techniques (emissivity, reflected ambient temperature, transimissivity).
We then move on to the examination of the main applications in the electrical and industrial, where thermography is covering an increasingly important as a technique of predictive maintenance. Through it possible investigations into the electrical connections, phase imbalances, overloads, loss of isolation and physical damage to the conductors, the normal plants in the low voltage transformer substations.
Are also possible investigations on electric motors, where you can find not only the loss of insulation in the windings but also imbalances and other mechanical problems.
Other applications, of growing interesting, concern photovoltaic systems and data centers.
In other industries we examine the applications in the chemical and petrochemical industries, and in general in industrial process control.
The book contains many pictures of real cases and references to foreign technical standards, with criteria for classifying the severity of thermal anomalies and mathematical examples of application: in the US thermography technique has been recognized as valid by the NFPA (National Fire Protection Agency) for preventing fires of electrical origin, and the major insurance companies promote the application of thermography surveys.
Other chapter covers miscellaneous applications such detecting corrosion under insulation, faults in steam traps, measuring furnace tubes, gas leak detection, refractory damage, checking level in vessels, temperature control in moulds, inspecting fiberglass and wooden boats for osmosis and humidity.

For the past few decades, most of the manufacturing plants and factories has been using periodic and preventive maintenance. However, these maintenance techniques sometimes will lead to unnecessary maintenance thus ends up with labor extensive and high cost problems. Predictive maintenance in the other hand allows the users to predictive future possible errors for a particular equipment or instrument. This allows us to reduce the frequency of needed maintenance unlike periodic and preventive maintenance. Besides, Internet of Things (IoT) is becoming trending in the industry due to its capability of providing ease of controlling and monitoring. The merging of both predictive maintenance and IoT will allow us to monitor the plant wirelessly while predicting the future potential failure. However, the initial commercial cost for both predictive maintenance and IoT are very expensive. The goal of this project is to build a low cost open source software based predictive maintenance data analytic toolbox with implementation of IoT. This will allow the user to forecast potential future failure of a particular instrument based on its historical data uploaded either from offline source or an IoT channel with a significantly much lower cost. After the forecast has been done, the result of forecasting can also be uploaded back into an IoT channel for the personnel such as superiors and managers to view wirelessly. Besides, multiple datasets with different data count will also be used in the toolbox to determine the accuracy of forecasting throughout different prediction techniques.

Reliability Centered Maintenance (RCM) is the framework of preserving system functions, rather than preserving physical asset. RCM is used to evaluate planned maintenance schedule that will offers availability of equipment with both reliability and maintainability. This paper presents ABC Automobile Company case, where planned maintenance is possible with application of predictive maintenance strategy, which enables to take decision of maintenance action with evidence and reduce unneeded maintenance. The main principle of predictive maintenance is examining the important performance characteristics of equipment to select the most indicative parameters of condition which reflects functional failures. In proposals, vibration is selected as an important performance characteristic of rotating components. Through vibration monitoring several mechanical failures can be effectively predicted. Signals (such as through the use of vibration monitoring) emanating from the condition monitoring of equipment are frequently interpretative as per manufacturer's recommendations, use of an expert system, or the threshold values established through the experience of inspectors are used (Wiseman and Jardine, 1999). The maintenance strategy adopted by ABC Automobile Company is preventive maintenance with manually collected condition monitoring data. That data usually indicates abnormality when actually failure occurs. This paper includes determination of the effectiveness of existing maintenance strategy and its comparisons with other strategies with improvement proposals. It outlines RCM analysis process and a test case of fans of paint booth process. This study concludes that RCM enables to evaluate planned maintenance action and incase of rotating components the vibration monitoring technique can be effectively used in predictive maintenance strategy. The paper reveals that the ABC Automobile Company can

Se pencher sur une machine pour « écouter » les bruits révélateurs de défauts ou contrôler visuellement l’apparition de fissures sur des pièces délicates représentent des opérations courantes. Pour s’affranchir de ces opérations fastidieuses et plus ou moins efficaces, les entreprises industrielles se tournent vers des systèmes de surveillance automatique de leurs machines. Ils leur permettent d’accroître la rentabilité (en diminuant au maximum le travail de l’opérateur), mais aussi de garantir la qualité des produits fabriqués et la sûreté de fonctionnement.
L’intérêt de ces systèmes est double:
Détecter une anomalie le plus tôt possible
Réaliser un diagnostic complet pour en identifier les causes.
En surveillant l’apparition de défauts critiques, on peut prévoir les pannes et en minimiser les conséquences, les réparations sont réalisées au moment opportun, elles sont moins coûteuses et les arrêts de production sont limités et surtout justifiés. On essaie ainsi d’anticiper les ruptures d’outil qui peuvent endommager la machine.
Cette approche moderne de maintenance consiste à mesurer l’état d’une machine pendant son fonctionnement afin de n’intervenir que lorsque les paramètres l’indiquent. Il s’agit de la maintenance prédictive. Dans le cadre de cette étude, nous nous appesantirons sur le paramètre qui s’avère être le plus fiable dans la mesure où il donne le plus précocement et de la meilleure façon l’état de détérioration d’une machine tournante. Il s’agit des vibrations.
Le présent travail énonce et analyse les principes de mise en oeuvre de la maintenance prédictive, relève son intérêt économique et technique, justifie son choix en regard de toutes les techniques de maintenance. Ils présentent les différentes méthodes utilisées pour la détection des défauts sur les machines industrielles par le contrôle des vibrations.
Pour atteindre les objectifs ci-dessus présentés, le présent travail est structuré selon le plan suivant :
o Le premier chapitre concerne les vibrations mécaniques, leurs évaluations dans le cadre de la maintenance prédictive, l’analyse de ceux-ci ainsi que les informations indispensables pour leurs traitements.
o Le deuxième chapitre présente les concepts nécessaires à la compréhension de la maintenance prédictive par rapport à l’intérêt économique et technique poursuivi parla maintenance des équipements industriels. L’intégration des vibrations dans le cadre de la maintenance prédictive étant mis en évidence.
o Le troisième chapitre concerne les méthodes de détection des défauts. Il présente les principales activités utilisées pour la détection des défauts des machines tournantes.
o Le quatrième chapitre traite des défauts et de leurs manifestations vibratoires. Il présente les principaux défauts observables sur les machines tournantes, leurs manifestations et leurs origines ainsi que le principe d’établissement des niveaux d’alarme et de pré alarme sur les machines.
o Le cinquième chapitre concerne la prédiction de l’amplitude vibratoire à l’aide du logiciel MATLAB. Il présente de quelle manière le diagnostic prédictif peut être réalisé en s’appuyant sur un programme de prédiction qui est présenté.

To cite this Article Lazakis, Iraklis , Turan, Osman and Aksu, Seref(2010) 'Increasing ship operational reliability through the implementation of a holistic maintenance management strategy', Ships and Offshore Structures, 5: 4, 337 -357 To link to this Article:

Total productive maintenance (TPM), total maintenance assurance, preventive maintenance, reliability-centered maintenance (RCM), and many other innovative approaches to maintenance problems all aim at enhancing the effectiveness of machines to ultimately improve productivity. Each of these concepts demands a unique decision support system for maintenance resources planning, and implementing each of them requires a radical restructuring of work. Introducing computer-aided maintenance resources planning (CAMRP) system is a major challenge because the maintenance operations environment is usually traditional and unfavorable to change. This paper presents a computer-aided planning system for a maintenance business unit that serves a number of manufacturing facilities, each consisting of a set of high-precision CNC machining centers. The workforce in the maintenance business unit is responsible for preventive as well as corrective maintenance activities of all CNC machines within the different manufacturing sites. The newly developed decision support tool embodies a set of structured heuristics methods for the coordination of tasks among maintenance crews which will help conduct different maintenance activities of manufacturing units in a more synchronized way. Through what-if-analyses, the tool generates wellfounded decisions for capacity planning are; synchronizes maintenance activities to predict maintenance start and expected finishing times, thereby leads to lower costs. r

Recently, it has been suggested that constructs from different disciplines should be incorporated into Tinto's (1993) sociological model of the determinants of departure from college . We tested the hypothesis that variables derived from social-psychological investment theory contribute, above and beyond variables derived from Tinto's model, to the prediction of maintaining the intent to stay at a university. A sample of 218 first-semester freshmen at a large southwestern university who indicated at the beginning of the fall 2007 semester that they intended to stay subsequently completed a questionnaire assessing integration variables (goal commitment, social integration, and academic integration), investment variables (satisfaction level, investment size, and quality of alternatives), and college graduation intention (stay versus transfer). A binary logistic regression analysis revealed that two variables derived from investment theory--satisfaction level and quality of alternatives-affected the log odds of students maintaining their intent to stay. Investment Theory and Maintaining the Intent to Stay 3

There has been a considerable amount of discussion concerning partial discharge (PD) measurements on medium voltage motors and generators. If one considers the total plant electrical distribution system and production equipment, motors comprise only a small part of the plant electrical equipment. If a motor should fail, part of production will likely be shut down and there will be lost revenue. However, there is a wide variety of other equipment in a facility besides a motor that can fail and can have a much more devastating effect on the plant's production. Additional items to consider for partial discharge monitoring are the plant incoming transformers (they may be owned by the plant if the plant is purchasing primary power), the incoming switchgear, cables, bus duct, other remote substation switchgear and power center transformers. Methods have been developed for monitoring partial discharges in all types of medium voltage equipment. This paper discusses application of sensors, methods of measurement and data interpretation and presents several case studies

The concept of maintenance has advanced significantly over the last decades from a reactive service activity towards a pro-active one with more C-level attention. Among them, predictive maintenance has become a widely used term in industrial arena and academic research. This is being developed constantly by engineers and researchers based on monitoring historical data, modeling, simulation, and failure probabilities to predict fault and system deterioration over their useful life. Generally, the effective lifetime of machines depends on available and accessible data. However, certain unexpected situations may arise that are hard to predict, such as shock damage and unwanted degradation of the tool. Researchers are still working on understanding these problems and their effects on predictive maintenance. This paper presents an overview of condition-based predictive maintenance solutions that aim to avoid unexpected and unplanned failures during the manufacturing and operational process based on advanced data analytics. Furthermore, a brief illustration & discussion is presented on the challenges and opportunities of condition-based predictive maintenance and conclude a summary on future research.

Worry and depressive rumination have both been described as unproductive, repetitive thought which contributes to anxiety or depression, respectively. It was hypothesized that repetitive thought, rather than its specific forms, is a general concomitant of negative mood. Study 1 was a cross-sectional test of the hypothesis. Repetitive thought was positively correlated with anxiety and depression in students (n ϭ 110). In patients (n ϭ 40), repetitive thought was positively correlated with anxiety and depression, and rumination was also specifically correlated with depression. Study 2 was a prospective test of the hypothesis. In students (n ϭ 90), there were significant crosssectional relationships between repetitive thought and both anxiety and depression. In addition, repetitive thought at least partially predicted maintenance of anxious symptoms. Phenomena such as goal interruption, failures of emotional processing, and information processing may lead to repetitive thought which increases negative mood states, including both anxiety and depression.

A novel technique for monitoring the condition of metallized polypropylene film (MPPF) capacitors installed in the dc link of railway power trains is proposed in this paper. The technique is based on the capacitance estimation of the two different capacitors used in the dc link (dc filtering and 2F filter capacitors), and it is done without adding any extra sensor or filter to the respective traction drive scheme. Therefore, the proposed method is implemented using software but not additional hardware for the different trains. Two other important passive component parameters of the traction drive are also monitored, all of them by means of curve fitting based on the least-mean-square (LMS) algorithm. The proposed technique is implemented and validated at simulation and experimental levels, using MATLAB/Simulink and a 1.2-MW traction drive test bench. Very accurate results are obtained, and the predictive maintenance of MPPF capacitors for different topologies of railway power trains can be set through the proposed technique.

Teknik sistemlerin verimliliği, güvenilirliği ve ekonomik ömrü gibi kritik parametreler bakım-onarım faaliyetlerinin etkinliği ile doğrudan ilişkilidir. Pratikte bu süreç; işletilen sistemin karakteristik özellikleri doğrultusunda, Toplam Üretken Bakım, Periyodik Bakım, Önleyici Bakım, Kestirimci Bakım, Arızi Bakım ve Güvenilirlik Merkezli Bakım gibi yaklaşımlarından uygun olanın seçilmesi ile oluşturulan bakım-onarım prosedürleri çerçevesinde yürütülmektedir. Ancak, teknolojik gelişmelerin katkısı nedeni ile artan sistem karmaşıklığı daha ileri bakım-onarım tekniklerinin uygulanmasını gerektirmektedir. Bu çalışmada, Bulanık Bilgi Aksiyomu yöntemi kullanılarak gemi makine dairesindeki farklı nitelikteki sistemler için karakteristik ve fonksiyonel özellikleri doğrultusunda entegre bakım-onarım yönetimi gereksinimi ortaya konulacaktır. Uygulanan karar modeli çıktıları kullanılarak, mevcut durumda planlı bakım sistemi uygulanan ticari gemiler için genişletilmiş ve daha etkin bir bakım-onarım yönetimi sistematiği oluşturulacaktır. ABSTRACT Effectiveness of maintenance management is directly related to critical parameters of technical systems such as efficiency, reliability, and economic life. In practice, this process is executed via procedures on selected adequate maintenance method among which the alternatives such as Total Productive Maintenance, Planned Maintenance, Preventive Maintenance, Predictive Maintenance, Reactive Maintenance, or Reliability Centered Maintenance. However, increasing system complexity due to the contributions of technological developments requires implementing more advance maintenance planning techniques. In this study, an integrated maintenance management system is presented based on Fuzzy Information Axioms methodology for shipboard systems under various characteristics and functional attributes. An extended and more effective maintenance management systematic is developed for merchant ships using applied decision model outcomes.

Makine verileri, her türlü bakım veya sürekli iyileştirme programının önemli bir parçasıdır. Sysmac platformu verilerin güvenle depolanmasını sağlar ve önde gelen birçok markayı destekler. Veriler daha sonra sürekli iyileştirme programının parçası olarak analiz edilip karşılaştırılarak faydalı bilgiler elde edilebilir.

Reliability centered maintenance (RCM) has a key role in the quality system of thermal power plants. Electricity production is definitely not only production of a product, but also becomes a customer service. Reliability is the top quality tier of this service. Incorporation in the Integrated energy system means fast transformations of organization on all levels. The reliability of modern generation components basically influences the efficiency and capacity of a power plant as a whole. This paper presents the results of RCM practice on Unit Two of The Thermal Power Plant ″Nikola Tesla -B″, 2x600 MW, Yugoslavia. RCM implementation on current problems during exploitation emphasized problems with the boiler tubing system. The methodological approach included outages analyses, marking of the most significant ones, determination of main causes of damage (determination of the material exhaustion state based on expert analyses), application of adequate remaining life assessment methodology and finally the recommendations. Based on these analyses, certain technical solutions were performed and as a result, the mean time between failures of the plant increased, as well as its reliability. According to cost efficiency, RCM methodology presented the most effective cost-benefit method for reliability upgrade.

This study presents a RCM program for Turkish National Power Transmission System. Depending upon the information from transmission utility staff, the system is decomposed into functional blocks and failures for each functional block is held individually to attain a reasonable maintenance program for the transmission system.

HVAC (Heating, Ventilation and AirConditioning) systems for space heating, space cooling and ventilation of buildings consume nearly 40% of the world energy demand and present the least expensive opportunities for reducing the greenhouse gases emission. Fault Detection and Diagnosis (FDD) methods could monitor the operation of various processes and/or components allowing to detect and, if possible, even predict the presence of defects (deviations from normal or expected operation) as well as ideally identify (diagnose) the fault and/or its location, giving instructions for undertaking corrective actions. FDD techniques could be successfully used for managing the predictive maintenance and/or optimizing the energy/economic/environmental performance of HVAC units while assuring the comfort of occupants. This paper examines the current state of the art of the research on the development and implementation of FDD systems when applied to Air-Handling Units (AHUs), the main and most important device of HVAC systems. This paper describes the existing methodologies, approaches and tools for the utilization of FDD techniques, summarizes the most important findings available in current literature in reference to several case studies where FDD systems have been applied with reference to AHUs and indicates the main gaps to be further investigated.

Bearing failure is one of the foremost causes of breakdowns in rotating machinery and such failure can be catastrophic, resulting in costly downtime. One of the key issues in bearing prognostics is to detect the defect at its incipient stage and alert the operator before it develops into a catastrophic failure. Signal de-noising and extraction of the weak signature are crucial to bearing prognostics since the inherent deficiency of the measuring mechanism often introduces a great amount of noise to the signal. In addition, the signature of a defective bearing is spread across a wide frequency band and hence can easily become masked by noise and low frequency effects. As a result, robust methods are needed to provide more evident information for bearing performance assessment and prognostics. This paper introduces enhanced and robust prognostic methods for rolling element bearing including a wavelet filter based method for weak signature enhancement for fault identification and Self Organizing Map (SOM) based method for performance degradation assessment. The experimental results demonstrate that the bearing defects can be detected at an early stage of development when both optimal wavelet filter and SOM method are used.

Fault diagnosis and prognosis are important tools for the reliability, availability and survivability of navy all-electric ships. Extending the fault detection and diagnosis into predictive maintenance increases the value of this technology. The traditional diagnosis can be viewed as a single diagnostic agent having a model of the whole system to be diagnosed. This becomes inadequate when the system becomes large and distributed as on the electric ships. For such systems, the software multi-agents may offer a solution. This paper first presents a brief review on the traditional fault diagnosis method with an emphasis on its application to electric motors as important components on the all-electric ship. The software agent technology is then introduced. The discussion is made about how this technology supports the drastic manning reduction requirements for the future navy ships. Examples are given on the existing naval applications of diagnostic and prognostic software agents.

Predictive maintenance (PdM) is a successful strategy used to reduce cost by minimizing the breakdown stoppages and production loss. The massive amount of data that results from the integration between the physical and digital systems of the production process makes it possible for deep learning (DL) algorithms to be applied and utilized for fault prediction and diagnosis. This paper presents a hybrid convolutional neural network based and long short-term memory network (CNN-LSTM) approach to a predictive maintenance problem. The proposed CNN-LSTM approach enhances the predictive accuracy and also reduces the complexity of the model. To evaluate the proposed model, two comparisons with regular LSTM and gradient boosting decision tree (GBDT) methods using a freely available dataset have been made. The PdM model based on CNN-LSTM method demonstrates better prediction accuracy compared to the regular LSTM, where the average F-Score increases form 93.34% in the case of regular LSTM to 97.48% for the proposed CNN-LSTM. Compared to the related works the proposed hybrid CNN-LSTM PdM approach achieved better results in term of accuracy.

A formulation of a discrete-time, discrete-frequency Wigner distribution for analysis of discrete-time, periodic signals is given using an approach involving group representation theory. This approach is motivated by a well-known connection between group theory and the continuous Wigner distribution. The advantage of this approach is that the resulting discrete distribution satisfies mathematical properties analogous to those satisfied by the continuous distribution. After outlining the relationship between group representation theory and time-frequency analysis, we derive the discrete distribution and exhibit many of its mathematical properties. These include time and frequency marginals, the Weyl correspondence, and covariance. In particular, the interpretation of covariance for the discrete distribution is shown to be different than that for the continuous distribution. Finally, we note some unusual features of this discrete distribution, which are a consequence of the group-theoretic derivation.

We describe in this paper a code-excited linear predictive coder in which the optimum innovation sequence is selected from a code book of stored sequences to optimize a given fidelity criterion. Each sample of the innovation sequence is filtered sequentially through two time-varying linear recursive filters, one with a long-delay (related to pitch period) predictor in the feedback loop and the other with a short-delay predictor (related to spectral envelope) in the feedback loop. We code speech, sampled at 8 kHz, in blocks of 5-msec duration. Each block consisting of 40 samples is produced from one of 1024 possible innovation sequences. The bit rate for the innovation sequence is thus 1/4 bit per sample. We compare in this paper several different random and deterministic code books for their effectiveness in providing the optimum innovation sequence in each block. Our results indicate that a random code book has a slight speech quality advantage at low bit rates. Examples of speech produced by the above method will be played at the conference.

This work is concerned with the vibrational and dynamic study of electrical motors located in Cristino Naranjo sugar mill. It is done during the predictive maintenance implementation. At the some time some works are shown during this process as well the failures diagnostic by means of the use of spectrum analysis of vibration. The spectrums shown are related to motors with difficulties or well working.