2019 IEEE 17th International Conference on Industrial Informatics (INDIN), 2019
In the last years the utilization of Multiagent Systems to implement distributed control systems ... more In the last years the utilization of Multiagent Systems to implement distributed control systems in industrial environments was presented as suitable and as a cost-effective solution to deal with the new requirements regarding flexibility and dynamism on the shop-floor. However, the proposed implementation of these distributed Cyber-Physical Production Systems faced some challenges regarding hardware and network requirements. Hence, the proposed work presents one utilization of a Multiagent-based distributed control system running on the fog level and running upon the edge level. This research presents a test and assessment of running intelligent agents outside the edge level but at the same time avoid the deployment of the industrial agents on the cloud level due to time and performance constraints. The proposed test presents a Multiagent architecture responsible for controlling the shop-floor, but the overall architecture was designed to accommodate the agents on the fog level, running upon the edge level composed by industrial controllers running Device Profile Web Services.
IECON 2017 - 43rd Annual Conference of the IEEE Industrial Electronics Society, 2017
Smart grids rely on the integration of distributed energy resources towards an intelligent and di... more Smart grids rely on the integration of distributed energy resources towards an intelligent and distributed manner to organize the electrical power grid enabled by a bidirectional flow of information to improve reliability and robustness, fault detection and system operation, and plug-and-playability of energy devices. The integration of information and communication technologies (ICT), one of the key enablers of smart grids, will ease the deployment of intelligent and distributed systems implementing the automation functions. In this context, there is a need to assess how these systems, developed using these emergent technologies, e.g., multi-agent systems, data analytics and machine learning, will behave and affect the working conditions of the power grid. This paper aims to explore the development of a transparent and loose-coupled interface between the behavioral control system and the physical or simulated power system environment, in a coupled simulation perspective, aiming to assess and improve the development of such systems during the design phase.
Highly flexible manufacturing systems require continuous run-time (self-) optimization of process... more Highly flexible manufacturing systems require continuous run-time (self-) optimization of processes with respect to various parameters, e.g. efficiency, availability, energy consumption etc. A promising approach for achieving (self-) optimization in manufacturing systems is the usage of the context sensitivity approach. Thereby the Cyber-Physical Systems play an important role as sources of information to achieve context sensitivity. In this paper it is demonstrated how context sensitivity can be used to realize a holistic solution for (self-) optimization of discrete flexible manufacturing systems, by making use of Cyber-Physical System integrated in manufacturing systems/processes. A generic approach for context sensitivity, based on self-learning algorithms, is proposed aiming at a various manufacturing systems. The new solution is propos encompassing run-time context extractor and optimizer. Based on the self-learning module both context extraction and optimizer are continuously...
IFIP Advances in Information and Communication Technology, 2015
In this paper a context classifier for service robots is presented. Independently of the applicat... more In this paper a context classifier for service robots is presented. Independently of the application, service robots need to have the notion of their context in order to behave appropriately. A context classification architecture that can be integrated in service robots reliability calculation is proposed. Sensorial information is used as input. This information is then fused (using Fuzzy Sets) in order to create a knowledge base that is used as an input to the classifier. The classification technique used is Bayes Networks, as the object of classification is partially observable, stochastic and has a sequential activity. Although the results presented refer to indoor/outdoor classification, the architecture is scalable in order to be used in much wider and detailed context classification. A community of service robots, contributing with their own contextual experience to dynamically improve the classification architecture, can use cloud-based technologies.
The word "flexibility" is often abused and not univocally understood within the manufacturing sci... more The word "flexibility" is often abused and not univocally understood within the manufacturing science domain and in particular in the context of industrial automation. Since the raise of industrial robots in the 1960', different researchers and practitioners have been using such a common word with different meanings. This has generated a very articulated concept, spanning from capability of a system to increase the production volumes to ability to handle product mix variation. Several authors have tried to count the current meanings of such a word in manufacturing and someone arrived to more than 50 [1]!. In spite of this fuzziness in both the definition and scope, the concept of flexibility remain one of the cornerstones in the curriculum of industrial and production engineers, and it appears in many courses along the bachelor and master studies. The apparent paradox that higher education institutions have to teach things that are not even well-defined and agreed in the scientific world is, in fact, quite a usual practice. In order to clarify what is, or should be, learnt this work analyzes first the established literature to extract a "working" characterization of the flexibility concept. The resulting understanding is then used to represent the experts' perception of the topic which in turn is used as ideal level of understanding that a student should achieve her/himself when studying such a concept. The second phase of the work aims at disclosing and classifying the multifaceted perceptions of flexibility that two different classes of industrial engineering students have after two courses in which the focal concept of manufacturing flexibility has been presented using two different approaches. The research is based on a phenomenographic analysis of a series of well-designed interviews to the students [2]. The collected data have consequently been structured in a finite set of clusters according of: (1) the level of understanding of the key concept (as expressed in the Bloom's taxonomy [3]) and (2) the nature of the shown knowledge (as presented in the SOLO taxonomy [4]). The classification is then the basis for defining an epistemological sound approach to develop suitable teaching and learning activities to ensure optimal acquisition of the concept of flexibility.
The advent of the Industry 4.0 initiative has made it so that manufacturing environments are beco... more The advent of the Industry 4.0 initiative has made it so that manufacturing environments are becoming more and more dynamic, connected but also inherently more complex, with additional inter-dependencies, uncertainties and large volumes of data being generated. Recent advances in Industrial Artificial Intelligence have showcased the potential of this technology to assist manufacturers in tackling the challenges associated with this digital transformation of Cyber-Physical Systems, through its data-driven predictive analytics and capacity to assist decision-making in highly complex, non-linear and often multistage environments. However, the industrial adoption of such solutions is still relatively low beyond the experimental pilot stage, as real environments provide unique and difficult challenges for which organizations are still unprepared. The aim of this paper is thus twofold. First, a systematic review of current Industrial Artificial Intelligence literature is presented, focusing on its application in real manufacturing environments to identify the main enabling technologies and core design principles. Then, a set of key challenges and opportunities to be addressed by future research efforts are formulated along with a conceptual framework to bridge the gap between research in this field and the manufacturing industry, with the goal of promoting industrial adoption through a successful transition towards a digitized and data-driven companywide culture. This paper is among the first to provide a clear definition and holistic view of Industrial Artificial Intelligence in the Industry 4.0 landscape, identifying and analysing its fundamental building blocks and ongoing trends. Its findings are expected to assist and empower researchers and manufacturers alike to better understand the requirements and steps necessary for a successful transition into Industry 4.0 supported by AI, as well as the challenges that may arise during this process.
Nowadays smart cities are becoming more and more a hot topic in the technological world. Some dif... more Nowadays smart cities are becoming more and more a hot topic in the technological world. Some different approaches emerged and many city departments approved investigation and implementation of the smart city technology in their cities. The implementation of these processes is becoming a landmark for the modern cities. This paper proposes a generic semantic model to easily plug and manage heterogeneous smart devices and areas of cities, in order to integrate all the diverse components that constitute a fully integrated and functional smart city environment. This semantic model can be used in the most diverse city scenarios; to demonstrate it, a specific scenario is presented in this paper, describing the usage of the proposed semantic model to detect new components and share information among the smart components.
Today, data scientists in the manufacturing domain are confronted with various communication stan... more Today, data scientists in the manufacturing domain are confronted with various communication standards, protocols and technologies to save and transfer various kinds of data. These circumstances makes it hard to understand, find, access and extract data needed for use case depended applications. One solution could be a data pipelining approach enforced by a semantic model which describes smart manufacturing assets itself and the access to their data along their life-cycle. Many research contributions in smart manufacturing already came out with with reference architectures like the RAMI 4.0 or standards for meta data description or asset classification. Our research builds upon these outcomes and introduces a semantic model based DIN Spec 91345 (RAMI 4.0) compliant data pipelining approach with the smart manufacturing domain as exemplary use case. This paper has a focus on the developed semantic model used to enable an easy data exploration, finding, access and extraction of data, compatible with various used communication standards, protocols and technologies used to save and transfer data. INDEX TERMS Data pipeline, industry 4.0, RAMI 4.0, smart manufacturing, semantic model.
2007 IEEE International Symposium on Assembly and Manufacturing, 2007
The aim of this paper is to introduce the basic principles. and concepts of evolvable assembly sy... more The aim of this paper is to introduce the basic principles. and concepts of evolvable assembly systems, EAS, represents a novel way of designing and implementing assembly systems in industry, and was first presented in 2002. The essence of EAS resides in the ability of system components to not only adapt to the changing conditions of operation, but also to
Abstract. Self-organising evolvable assembly systems (SO-EAS) are in-tended to tackle the challen... more Abstract. Self-organising evolvable assembly systems (SO-EAS) are in-tended to tackle the challenges of agile manufacturing: high responsive-ness, the ability to cope with ever-changing requirements, many variants and small lot sizes. SO-EAS are composed of modules with ...
The complexity associated to Humanitarian Demining becomes very high due to its broad set of acti... more The complexity associated to Humanitarian Demining becomes very high due to its broad set of activities, which beyond the already complex of landmine removal, includes other socioeconomic supporting activities. Hence, more complex computer based supporting systems are required. The main goal of this article is to describe potential applications of multi-agent systems to the Humanitarian Demining domain, covering areas such as: knowledge-based systems, collaborative networks, agent-based modelling and multi-agent robotic systems. This is the result of the work being carried out by the Portuguese company IntRoSys, whose main research objective is the development of tools and methods to support humanitarian demining.
2015 10th International Symposium on Mechatronics and its Applications (ISMA), 2015
The manufacturing industry has been steadily evolving over the years, with new market trends enco... more The manufacturing industry has been steadily evolving over the years, with new market trends encouraging manufacturers to find new ways to meet the consumers' demands and quickly adapt to new business opportunities. Manufacturing systems are therefore required to be more and more agile and flexible in an environment dominated by unpredictable changes and disturbances. As a direct consequence several new solutions have been proposed, revolving around agility, flexibility, reconfigurability and modularity, enabling concepts such as Plug & Produce (P&P). Following this trend, the present article proposes a possible implementation for a multiagent-based knowledge extraction architecture to support P&P in flexible, distributed manufacturing monitoring systems. The validation process is also described, entailing the application of said system in a real industrial environment, more specifically monitoring two robotic cells performing the welding of a car's side member.
Current major roadmapping efforts have all clearly underlined that true industrial sustainability... more Current major roadmapping efforts have all clearly underlined that true industrial sustainability will require far higher levels of systems’ autonomy and adaptability. Inaccordance with these recom ...
A robust maintenance of ecosystems demands for highly accurate and frequent monitoring of their s... more A robust maintenance of ecosystems demands for highly accurate and frequent monitoring of their status. The extension and remoteness of some environments renders their human-based monitoring extremely difficult. Riverine environments are a notorious example, as their sampling requires to bear into account both streams and riverbanks. The relevance of monitoring riverine environments is magnified by the intricate interactions that occur between river waters and coastal waters. This article provides a critical survey of existing solutions using robots for environmental monitoring of water bodies. Based on the survey, this article argues that autonomous robotic marsupial systems are especially adequate for the tasks at hand. Lessons learned, as well as future avenues on the application of marsupial robotic teams to environmental monitoring, are laid out in this article.
Modularity and embedded intelligence enable seamless shop floor reconfiguration enhancing reactiv... more Modularity and embedded intelligence enable seamless shop floor reconfiguration enhancing reactiveness and responsiveness to changing requirements. However the amount of information underlying modern enterprises is considerable. Recent approaches attempt to map and relate the main concepts in domain ontologies. Often that information is excessive and does not provide the adequate operational shop floor support. In this paper a compact OWL ontology computable by intelligent agents living in embedded devices and focusing on the essential (re)configuration and connectivity aspects (social, mechanical, electrical and other interfaces) is proposed under the framework of the biologically inspired Evolvable Assembly Systems.
Presented in 2002, and applied within the EUPASS[1] and A3 [1]projects, Evolvable Assembly System... more Presented in 2002, and applied within the EUPASS[1] and A3 [1]projects, Evolvable Assembly Systems (EAS) proposes a novel way of applying assembly systems in industry. The essence of EAS resides in ...
Information Control Problems in Manufacturing 2006, 2006
The work presented in this paper intends to clarify how multiagents can be an adequate paradigm t... more The work presented in this paper intends to clarify how multiagents can be an adequate paradigm to solve the challenges imposed by Evolvable Assembly Systems (EAS). The article will therefore show that a multiagent architecture based on coalitions of assembly modules (CoBASA) can be successfully used to implement the control architecture for EAS.
The advent of Industry 4.0 has shown the tremendous transformative potential of combining artific... more The advent of Industry 4.0 has shown the tremendous transformative potential of combining artificial intelligence, cyber-physical systems and Internet of Things concepts in industrial settings. Despite this, data availability is still a major roadblock for the successful adoption of data-driven solutions, particularly concerning deep learning approaches in manufacturing. Specifically in the quality control domain, annotated defect data can often be costly, time-consuming and inefficient to obtain, potentially compromising the viability of deep learning approaches due to data scarcity. In this context, we propose a novel method for generating annotated synthetic training data for automated quality inspections of structural adhesive applications, validated in an industrial cell for automotive parts. Our approach greatly reduces the cost of training deep learning models for this task, while simultaneously improving their performance in a scarce manufacturing data context with imbalanced training sets by 3.1%
Markets and consequently manufacturing companies are facing an unprecedented challenge. The const... more Markets and consequently manufacturing companies are facing an unprecedented challenge. The constant markets demand of more and more customized and personalized products combined with the recent evolution of information technologies, brought to the manufacturing world the integration of new solutions previously unimaginable in a production environment. Hence, in the last years manufacturing systems were changing and nowadays each component present in the shop floor generates a huge amount of data that is usually not used. In this paper the authors present a framework capable to deal with all this data generated from a production cell in the automotive industry and reduce the energy consumption. Firstly, it is described how the information is extracted and how the data clustering is done, then the data mining process and management are presented, together with the obtained results.
2019 IEEE 17th International Conference on Industrial Informatics (INDIN), 2019
In the last years the utilization of Multiagent Systems to implement distributed control systems ... more In the last years the utilization of Multiagent Systems to implement distributed control systems in industrial environments was presented as suitable and as a cost-effective solution to deal with the new requirements regarding flexibility and dynamism on the shop-floor. However, the proposed implementation of these distributed Cyber-Physical Production Systems faced some challenges regarding hardware and network requirements. Hence, the proposed work presents one utilization of a Multiagent-based distributed control system running on the fog level and running upon the edge level. This research presents a test and assessment of running intelligent agents outside the edge level but at the same time avoid the deployment of the industrial agents on the cloud level due to time and performance constraints. The proposed test presents a Multiagent architecture responsible for controlling the shop-floor, but the overall architecture was designed to accommodate the agents on the fog level, running upon the edge level composed by industrial controllers running Device Profile Web Services.
IECON 2017 - 43rd Annual Conference of the IEEE Industrial Electronics Society, 2017
Smart grids rely on the integration of distributed energy resources towards an intelligent and di... more Smart grids rely on the integration of distributed energy resources towards an intelligent and distributed manner to organize the electrical power grid enabled by a bidirectional flow of information to improve reliability and robustness, fault detection and system operation, and plug-and-playability of energy devices. The integration of information and communication technologies (ICT), one of the key enablers of smart grids, will ease the deployment of intelligent and distributed systems implementing the automation functions. In this context, there is a need to assess how these systems, developed using these emergent technologies, e.g., multi-agent systems, data analytics and machine learning, will behave and affect the working conditions of the power grid. This paper aims to explore the development of a transparent and loose-coupled interface between the behavioral control system and the physical or simulated power system environment, in a coupled simulation perspective, aiming to assess and improve the development of such systems during the design phase.
Highly flexible manufacturing systems require continuous run-time (self-) optimization of process... more Highly flexible manufacturing systems require continuous run-time (self-) optimization of processes with respect to various parameters, e.g. efficiency, availability, energy consumption etc. A promising approach for achieving (self-) optimization in manufacturing systems is the usage of the context sensitivity approach. Thereby the Cyber-Physical Systems play an important role as sources of information to achieve context sensitivity. In this paper it is demonstrated how context sensitivity can be used to realize a holistic solution for (self-) optimization of discrete flexible manufacturing systems, by making use of Cyber-Physical System integrated in manufacturing systems/processes. A generic approach for context sensitivity, based on self-learning algorithms, is proposed aiming at a various manufacturing systems. The new solution is propos encompassing run-time context extractor and optimizer. Based on the self-learning module both context extraction and optimizer are continuously...
IFIP Advances in Information and Communication Technology, 2015
In this paper a context classifier for service robots is presented. Independently of the applicat... more In this paper a context classifier for service robots is presented. Independently of the application, service robots need to have the notion of their context in order to behave appropriately. A context classification architecture that can be integrated in service robots reliability calculation is proposed. Sensorial information is used as input. This information is then fused (using Fuzzy Sets) in order to create a knowledge base that is used as an input to the classifier. The classification technique used is Bayes Networks, as the object of classification is partially observable, stochastic and has a sequential activity. Although the results presented refer to indoor/outdoor classification, the architecture is scalable in order to be used in much wider and detailed context classification. A community of service robots, contributing with their own contextual experience to dynamically improve the classification architecture, can use cloud-based technologies.
The word "flexibility" is often abused and not univocally understood within the manufacturing sci... more The word "flexibility" is often abused and not univocally understood within the manufacturing science domain and in particular in the context of industrial automation. Since the raise of industrial robots in the 1960', different researchers and practitioners have been using such a common word with different meanings. This has generated a very articulated concept, spanning from capability of a system to increase the production volumes to ability to handle product mix variation. Several authors have tried to count the current meanings of such a word in manufacturing and someone arrived to more than 50 [1]!. In spite of this fuzziness in both the definition and scope, the concept of flexibility remain one of the cornerstones in the curriculum of industrial and production engineers, and it appears in many courses along the bachelor and master studies. The apparent paradox that higher education institutions have to teach things that are not even well-defined and agreed in the scientific world is, in fact, quite a usual practice. In order to clarify what is, or should be, learnt this work analyzes first the established literature to extract a "working" characterization of the flexibility concept. The resulting understanding is then used to represent the experts' perception of the topic which in turn is used as ideal level of understanding that a student should achieve her/himself when studying such a concept. The second phase of the work aims at disclosing and classifying the multifaceted perceptions of flexibility that two different classes of industrial engineering students have after two courses in which the focal concept of manufacturing flexibility has been presented using two different approaches. The research is based on a phenomenographic analysis of a series of well-designed interviews to the students [2]. The collected data have consequently been structured in a finite set of clusters according of: (1) the level of understanding of the key concept (as expressed in the Bloom's taxonomy [3]) and (2) the nature of the shown knowledge (as presented in the SOLO taxonomy [4]). The classification is then the basis for defining an epistemological sound approach to develop suitable teaching and learning activities to ensure optimal acquisition of the concept of flexibility.
The advent of the Industry 4.0 initiative has made it so that manufacturing environments are beco... more The advent of the Industry 4.0 initiative has made it so that manufacturing environments are becoming more and more dynamic, connected but also inherently more complex, with additional inter-dependencies, uncertainties and large volumes of data being generated. Recent advances in Industrial Artificial Intelligence have showcased the potential of this technology to assist manufacturers in tackling the challenges associated with this digital transformation of Cyber-Physical Systems, through its data-driven predictive analytics and capacity to assist decision-making in highly complex, non-linear and often multistage environments. However, the industrial adoption of such solutions is still relatively low beyond the experimental pilot stage, as real environments provide unique and difficult challenges for which organizations are still unprepared. The aim of this paper is thus twofold. First, a systematic review of current Industrial Artificial Intelligence literature is presented, focusing on its application in real manufacturing environments to identify the main enabling technologies and core design principles. Then, a set of key challenges and opportunities to be addressed by future research efforts are formulated along with a conceptual framework to bridge the gap between research in this field and the manufacturing industry, with the goal of promoting industrial adoption through a successful transition towards a digitized and data-driven companywide culture. This paper is among the first to provide a clear definition and holistic view of Industrial Artificial Intelligence in the Industry 4.0 landscape, identifying and analysing its fundamental building blocks and ongoing trends. Its findings are expected to assist and empower researchers and manufacturers alike to better understand the requirements and steps necessary for a successful transition into Industry 4.0 supported by AI, as well as the challenges that may arise during this process.
Nowadays smart cities are becoming more and more a hot topic in the technological world. Some dif... more Nowadays smart cities are becoming more and more a hot topic in the technological world. Some different approaches emerged and many city departments approved investigation and implementation of the smart city technology in their cities. The implementation of these processes is becoming a landmark for the modern cities. This paper proposes a generic semantic model to easily plug and manage heterogeneous smart devices and areas of cities, in order to integrate all the diverse components that constitute a fully integrated and functional smart city environment. This semantic model can be used in the most diverse city scenarios; to demonstrate it, a specific scenario is presented in this paper, describing the usage of the proposed semantic model to detect new components and share information among the smart components.
Today, data scientists in the manufacturing domain are confronted with various communication stan... more Today, data scientists in the manufacturing domain are confronted with various communication standards, protocols and technologies to save and transfer various kinds of data. These circumstances makes it hard to understand, find, access and extract data needed for use case depended applications. One solution could be a data pipelining approach enforced by a semantic model which describes smart manufacturing assets itself and the access to their data along their life-cycle. Many research contributions in smart manufacturing already came out with with reference architectures like the RAMI 4.0 or standards for meta data description or asset classification. Our research builds upon these outcomes and introduces a semantic model based DIN Spec 91345 (RAMI 4.0) compliant data pipelining approach with the smart manufacturing domain as exemplary use case. This paper has a focus on the developed semantic model used to enable an easy data exploration, finding, access and extraction of data, compatible with various used communication standards, protocols and technologies used to save and transfer data. INDEX TERMS Data pipeline, industry 4.0, RAMI 4.0, smart manufacturing, semantic model.
2007 IEEE International Symposium on Assembly and Manufacturing, 2007
The aim of this paper is to introduce the basic principles. and concepts of evolvable assembly sy... more The aim of this paper is to introduce the basic principles. and concepts of evolvable assembly systems, EAS, represents a novel way of designing and implementing assembly systems in industry, and was first presented in 2002. The essence of EAS resides in the ability of system components to not only adapt to the changing conditions of operation, but also to
Abstract. Self-organising evolvable assembly systems (SO-EAS) are in-tended to tackle the challen... more Abstract. Self-organising evolvable assembly systems (SO-EAS) are in-tended to tackle the challenges of agile manufacturing: high responsive-ness, the ability to cope with ever-changing requirements, many variants and small lot sizes. SO-EAS are composed of modules with ...
The complexity associated to Humanitarian Demining becomes very high due to its broad set of acti... more The complexity associated to Humanitarian Demining becomes very high due to its broad set of activities, which beyond the already complex of landmine removal, includes other socioeconomic supporting activities. Hence, more complex computer based supporting systems are required. The main goal of this article is to describe potential applications of multi-agent systems to the Humanitarian Demining domain, covering areas such as: knowledge-based systems, collaborative networks, agent-based modelling and multi-agent robotic systems. This is the result of the work being carried out by the Portuguese company IntRoSys, whose main research objective is the development of tools and methods to support humanitarian demining.
2015 10th International Symposium on Mechatronics and its Applications (ISMA), 2015
The manufacturing industry has been steadily evolving over the years, with new market trends enco... more The manufacturing industry has been steadily evolving over the years, with new market trends encouraging manufacturers to find new ways to meet the consumers' demands and quickly adapt to new business opportunities. Manufacturing systems are therefore required to be more and more agile and flexible in an environment dominated by unpredictable changes and disturbances. As a direct consequence several new solutions have been proposed, revolving around agility, flexibility, reconfigurability and modularity, enabling concepts such as Plug & Produce (P&P). Following this trend, the present article proposes a possible implementation for a multiagent-based knowledge extraction architecture to support P&P in flexible, distributed manufacturing monitoring systems. The validation process is also described, entailing the application of said system in a real industrial environment, more specifically monitoring two robotic cells performing the welding of a car's side member.
Current major roadmapping efforts have all clearly underlined that true industrial sustainability... more Current major roadmapping efforts have all clearly underlined that true industrial sustainability will require far higher levels of systems’ autonomy and adaptability. Inaccordance with these recom ...
A robust maintenance of ecosystems demands for highly accurate and frequent monitoring of their s... more A robust maintenance of ecosystems demands for highly accurate and frequent monitoring of their status. The extension and remoteness of some environments renders their human-based monitoring extremely difficult. Riverine environments are a notorious example, as their sampling requires to bear into account both streams and riverbanks. The relevance of monitoring riverine environments is magnified by the intricate interactions that occur between river waters and coastal waters. This article provides a critical survey of existing solutions using robots for environmental monitoring of water bodies. Based on the survey, this article argues that autonomous robotic marsupial systems are especially adequate for the tasks at hand. Lessons learned, as well as future avenues on the application of marsupial robotic teams to environmental monitoring, are laid out in this article.
Modularity and embedded intelligence enable seamless shop floor reconfiguration enhancing reactiv... more Modularity and embedded intelligence enable seamless shop floor reconfiguration enhancing reactiveness and responsiveness to changing requirements. However the amount of information underlying modern enterprises is considerable. Recent approaches attempt to map and relate the main concepts in domain ontologies. Often that information is excessive and does not provide the adequate operational shop floor support. In this paper a compact OWL ontology computable by intelligent agents living in embedded devices and focusing on the essential (re)configuration and connectivity aspects (social, mechanical, electrical and other interfaces) is proposed under the framework of the biologically inspired Evolvable Assembly Systems.
Presented in 2002, and applied within the EUPASS[1] and A3 [1]projects, Evolvable Assembly System... more Presented in 2002, and applied within the EUPASS[1] and A3 [1]projects, Evolvable Assembly Systems (EAS) proposes a novel way of applying assembly systems in industry. The essence of EAS resides in ...
Information Control Problems in Manufacturing 2006, 2006
The work presented in this paper intends to clarify how multiagents can be an adequate paradigm t... more The work presented in this paper intends to clarify how multiagents can be an adequate paradigm to solve the challenges imposed by Evolvable Assembly Systems (EAS). The article will therefore show that a multiagent architecture based on coalitions of assembly modules (CoBASA) can be successfully used to implement the control architecture for EAS.
The advent of Industry 4.0 has shown the tremendous transformative potential of combining artific... more The advent of Industry 4.0 has shown the tremendous transformative potential of combining artificial intelligence, cyber-physical systems and Internet of Things concepts in industrial settings. Despite this, data availability is still a major roadblock for the successful adoption of data-driven solutions, particularly concerning deep learning approaches in manufacturing. Specifically in the quality control domain, annotated defect data can often be costly, time-consuming and inefficient to obtain, potentially compromising the viability of deep learning approaches due to data scarcity. In this context, we propose a novel method for generating annotated synthetic training data for automated quality inspections of structural adhesive applications, validated in an industrial cell for automotive parts. Our approach greatly reduces the cost of training deep learning models for this task, while simultaneously improving their performance in a scarce manufacturing data context with imbalanced training sets by 3.1%
Markets and consequently manufacturing companies are facing an unprecedented challenge. The const... more Markets and consequently manufacturing companies are facing an unprecedented challenge. The constant markets demand of more and more customized and personalized products combined with the recent evolution of information technologies, brought to the manufacturing world the integration of new solutions previously unimaginable in a production environment. Hence, in the last years manufacturing systems were changing and nowadays each component present in the shop floor generates a huge amount of data that is usually not used. In this paper the authors present a framework capable to deal with all this data generated from a production cell in the automotive industry and reduce the energy consumption. Firstly, it is described how the information is extracted and how the data clustering is done, then the data mining process and management are presented, together with the obtained results.
Uploads
Papers by Jose Barata