Pub Date : 2018-09-01DOI: 10.1109/ETFA.2018.8502599
João C. P. Reis, G. Gonçalves
Transfer Learning aims at transferring knowledge from an already learned task to a different, but related task, in order to accelerate the learning process of the latter. This concept can be applied to manufacturing systems where process models that map process parameters into process quality are used to optimize the calibration phase of new unseen products at the shop-floor. However, these process models often require a great amount of experiments, which normally is costly and impractical for most manufacturing systems. The present work explores a Laser Seam Welding scenario with 3 different product variants where the problem is training one of the process models with a reduced amount of labeled data. Artificial Neural Networks (ANNs) were used to model these processes and Inductive Transfer Learning is then used to tackle the proposed problem. Ultimately, this approach was compared to traditional machine learning where no transfer occurs and a model is trained only using the small amount of labeled data. The results revealed that for all the Laser Seam Welding processes the trained models performed better when using Inductive Transfer.
{"title":"Laser Seam Welding optimization using Inductive Transfer Learning with Artificial Neural Networks","authors":"João C. P. Reis, G. Gonçalves","doi":"10.1109/ETFA.2018.8502599","DOIUrl":"https://doi.org/10.1109/ETFA.2018.8502599","url":null,"abstract":"Transfer Learning aims at transferring knowledge from an already learned task to a different, but related task, in order to accelerate the learning process of the latter. This concept can be applied to manufacturing systems where process models that map process parameters into process quality are used to optimize the calibration phase of new unseen products at the shop-floor. However, these process models often require a great amount of experiments, which normally is costly and impractical for most manufacturing systems. The present work explores a Laser Seam Welding scenario with 3 different product variants where the problem is training one of the process models with a reduced amount of labeled data. Artificial Neural Networks (ANNs) were used to model these processes and Inductive Transfer Learning is then used to tackle the proposed problem. Ultimately, this approach was compared to traditional machine learning where no transfer occurs and a model is trained only using the small amount of labeled data. The results revealed that for all the Laser Seam Welding processes the trained models performed better when using Inductive Transfer.","PeriodicalId":6566,"journal":{"name":"2018 IEEE 23rd International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"16 1","pages":"646-653"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90952198","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-09-01DOI: 10.1109/ETFA.2018.8502654
Jose Cabral, M. Wenger, Alois Zoitl
Different causes have contributed to the shift of paradigm in the automation field from centralized to modular and distributable. Software and hardware of Programmable Logic Controllers (PLCs) have evolved to be synchronized with the demands nowadays and new standards are trying to follow this trend. One of them is the IEC 61499 standard, which is intended for modelling distributed industrial solutions with a vendor-independent format. This shifting is also bringing new challenges and this paper focuses on the virtual commissioning of plants, which can become a harder task when the system is distributed and involves different interconnected modules. A major problem when doing a virtual commissioning is the coupling between the different physical systems and controlling tools since many vendors still offer closed integrated solutions. Functional Mockup Interface (FMI) is a standard for a cosimulation interface which intends to fill the gaps between different modelling tools, by packaging the models into Functional Mockup Unit (FMU) and allowing a co-simulation master algorithm to have access to the inside model through the proposed interface. This paper presents a mapping between IEC 61499 models and the FMI standard and an implementation of a tool that can export IEC 61499 models into FMUs, which would allow the co-simulation of physical plants and the PLCs software that controls it. An experiment is shown where a simple Proportional-Integral-Derivative (PID) controller of a tank system is exported as an FMU and co-simulated together with a tank system modelled using OpenModelica.
不同的原因导致了自动化领域的范式从集中式到模块化和分布式的转变。可编程逻辑控制器(plc)的软件和硬件已经发展到与当今的需求同步，新的标准正在努力遵循这一趋势。其中之一是IEC 61499标准，该标准旨在使用独立于供应商的格式对分布式工业解决方案进行建模。这种转变也带来了新的挑战，本文关注的是电厂的虚拟调试，当系统分布且涉及不同互连模块时，这将成为一项更加艰巨的任务。进行虚拟调试时的一个主要问题是不同物理系统和控制工具之间的耦合，因为许多供应商仍然提供封闭的集成解决方案。功能模拟接口(Functional Mockup Interface, FMI)是一种联合仿真接口标准，旨在填补不同建模工具之间的空白，将模型打包到功能模拟单元(Functional Mockup Unit, FMU)中，并允许联合仿真主算法通过提议的接口访问内部模型。本文介绍了IEC 61499模型和FMI标准之间的映射，以及可以将IEC 61499模型导出到fmu的工具的实现，这将允许物理工厂和控制它的plc软件的联合模拟。实验表明，一个简单的比例-积分-导数(PID)控制器油箱系统导出为FMU，并与使用OpenModelica建模的油箱系统共同仿真。
{"title":"Enable Co-Simulation for Industrial Automation by an FMU Exporter for IEC 61499 Models","authors":"Jose Cabral, M. Wenger, Alois Zoitl","doi":"10.1109/ETFA.2018.8502654","DOIUrl":"https://doi.org/10.1109/ETFA.2018.8502654","url":null,"abstract":"Different causes have contributed to the shift of paradigm in the automation field from centralized to modular and distributable. Software and hardware of Programmable Logic Controllers (PLCs) have evolved to be synchronized with the demands nowadays and new standards are trying to follow this trend. One of them is the IEC 61499 standard, which is intended for modelling distributed industrial solutions with a vendor-independent format. This shifting is also bringing new challenges and this paper focuses on the virtual commissioning of plants, which can become a harder task when the system is distributed and involves different interconnected modules. A major problem when doing a virtual commissioning is the coupling between the different physical systems and controlling tools since many vendors still offer closed integrated solutions. Functional Mockup Interface (FMI) is a standard for a cosimulation interface which intends to fill the gaps between different modelling tools, by packaging the models into Functional Mockup Unit (FMU) and allowing a co-simulation master algorithm to have access to the inside model through the proposed interface. This paper presents a mapping between IEC 61499 models and the FMI standard and an implementation of a tool that can export IEC 61499 models into FMUs, which would allow the co-simulation of physical plants and the PLCs software that controls it. An experiment is shown where a simple Proportional-Integral-Derivative (PID) controller of a tank system is exported as an FMU and co-simulated together with a tank system modelled using OpenModelica.","PeriodicalId":6566,"journal":{"name":"2018 IEEE 23rd International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"47 1","pages":"449-455"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90472229","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-09-01DOI: 10.1109/ETFA.2018.8502517
D. Belter, K. Piaskowski, Rafal Staszak
In this paper, we propose a new mapping method based on Normal Distribution Transform Occupancy Maps (NDT-OM) for environment exploration. Our goal is to propose a new architecture which can be used by an industrial mobile robot in a priori unknown environment. The mobile robot introduced in a new environment has to explore the workspace, localize itself and build a map. Current state of the art methods require storing all data collected during this stage and finally build a dense model of the environment. We propose a method which allows building local dense maps of the environment which are organized in a graph-like structure. The change in the registered trajectory of the robot, which may occur after loop closure detection, can be easily utilized by our architecture. Finally, we build a global map which can be later used for collision checking and motion planning.
{"title":"Keyframe-based Local Normal Distribution Transform Occupancy Maps for Environment Mapping","authors":"D. Belter, K. Piaskowski, Rafal Staszak","doi":"10.1109/ETFA.2018.8502517","DOIUrl":"https://doi.org/10.1109/ETFA.2018.8502517","url":null,"abstract":"In this paper, we propose a new mapping method based on Normal Distribution Transform Occupancy Maps (NDT-OM) for environment exploration. Our goal is to propose a new architecture which can be used by an industrial mobile robot in a priori unknown environment. The mobile robot introduced in a new environment has to explore the workspace, localize itself and build a map. Current state of the art methods require storing all data collected during this stage and finally build a dense model of the environment. We propose a method which allows building local dense maps of the environment which are organized in a graph-like structure. The change in the registered trajectory of the robot, which may occur after loop closure detection, can be easily utilized by our architecture. Finally, we build a global map which can be later used for collision checking and motion planning.","PeriodicalId":6566,"journal":{"name":"2018 IEEE 23rd International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"23 1","pages":"706-712"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78162410","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-09-01DOI: 10.1109/etfa.2018.8502511
{"title":"Real-Time and Networked Embedded Systems","authors":"","doi":"10.1109/etfa.2018.8502511","DOIUrl":"https://doi.org/10.1109/etfa.2018.8502511","url":null,"abstract":"","PeriodicalId":6566,"journal":{"name":"2018 IEEE 23rd International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"6 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73167937","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-09-01DOI: 10.1109/etfa.2018.8502590
{"title":"WIP Information Technology in Automation","authors":"","doi":"10.1109/etfa.2018.8502590","DOIUrl":"https://doi.org/10.1109/etfa.2018.8502590","url":null,"abstract":"","PeriodicalId":6566,"journal":{"name":"2018 IEEE 23rd International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"125 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74633391","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-09-01DOI: 10.1109/etfa.2018.8502658
{"title":"Machine Learning for Data-driven Predictive Maintenance in the Industry 4.0 Framework","authors":"","doi":"10.1109/etfa.2018.8502658","DOIUrl":"https://doi.org/10.1109/etfa.2018.8502658","url":null,"abstract":"","PeriodicalId":6566,"journal":{"name":"2018 IEEE 23rd International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"46 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74130734","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-09-01DOI: 10.1109/ETFA.2018.8502577
Wenjing Yang, L. Brenner, A. Giua
The propagation of innovations in social networks has been widely studied recently. Previous research mostly focuses on either maximizing the influence by identifying a set of initial adopters, or minimizing the influence by link blocking under a certain diffusion model. In our case, we address an influence maximization problem considering the link activation under the Independent Cascade model. For this problem, we propose an approximate solution based on the computation of a cost-degree coefficient for selecting links to be activated. Simulations performed on a real network show that our algorithm performs well.
{"title":"Influence Maximization by Link Activation in Social Networks","authors":"Wenjing Yang, L. Brenner, A. Giua","doi":"10.1109/ETFA.2018.8502577","DOIUrl":"https://doi.org/10.1109/ETFA.2018.8502577","url":null,"abstract":"The propagation of innovations in social networks has been widely studied recently. Previous research mostly focuses on either maximizing the influence by identifying a set of initial adopters, or minimizing the influence by link blocking under a certain diffusion model. In our case, we address an influence maximization problem considering the link activation under the Independent Cascade model. For this problem, we propose an approximate solution based on the computation of a cost-degree coefficient for selecting links to be activated. Simulations performed on a real network show that our algorithm performs well.","PeriodicalId":6566,"journal":{"name":"2018 IEEE 23rd International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"2 1","pages":"1248-1251"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79104767","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-09-01DOI: 10.1109/ETFA.2018.8502649
Michael Gundall, Jörg Schneider, H. Schotten, M. Aleksy, D. Schulz, Norman Franchi, Nick Schwarzenberg, C. Markwart, R. Halfmann, P. Rost, D. Wübben, Arne Neumann, Monique Düngen, T. Neugebauer, Rolf Blunk, Mehmet Kus, Jan Grießbach
The increasing demand for highly customized products, as well as flexible production lines, can be seen as trigger for the “fourth industrial revolution”, referred to as “Industrie 4.0”. Current systems usually rely on wire-line technologies to connect sensors and actuators. To enable a higher flexibility such as moving robots or drones, these connections need to be replaced by wireless technologies in the future. Furthermore, this facilitates the renewal of brownfield deployments to address Industrie 4.0 requirements. This paper proposes representative use cases, which have been examined in the German Tactile Internet 4.0 (TACNET 4.0) research project. In order to analyze these use cases, this paper identifies the main challenges and requirements of communication networks in Industrie 4.0 and discusses the applicability of 5th generation wireless communication systems (5G).
{"title":"5G as Enabler for Industrie 4.0 Use Cases: Challenges and Concepts","authors":"Michael Gundall, Jörg Schneider, H. Schotten, M. Aleksy, D. Schulz, Norman Franchi, Nick Schwarzenberg, C. Markwart, R. Halfmann, P. Rost, D. Wübben, Arne Neumann, Monique Düngen, T. Neugebauer, Rolf Blunk, Mehmet Kus, Jan Grießbach","doi":"10.1109/ETFA.2018.8502649","DOIUrl":"https://doi.org/10.1109/ETFA.2018.8502649","url":null,"abstract":"The increasing demand for highly customized products, as well as flexible production lines, can be seen as trigger for the “fourth industrial revolution”, referred to as “Industrie 4.0”. Current systems usually rely on wire-line technologies to connect sensors and actuators. To enable a higher flexibility such as moving robots or drones, these connections need to be replaced by wireless technologies in the future. Furthermore, this facilitates the renewal of brownfield deployments to address Industrie 4.0 requirements. This paper proposes representative use cases, which have been examined in the German Tactile Internet 4.0 (TACNET 4.0) research project. In order to analyze these use cases, this paper identifies the main challenges and requirements of communication networks in Industrie 4.0 and discusses the applicability of 5th generation wireless communication systems (5G).","PeriodicalId":6566,"journal":{"name":"2018 IEEE 23rd International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"1 1","pages":"1401-1408"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85313172","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-09-01DOI: 10.1109/ETFA.2018.8502623
Milan Vathoopan, H. Walzel, Waldemar Eisenmenger, Alois Zoitl, Benjamin Brandenbourger
The industrial automation systems are slowly changing from a centralized architecture to a modularized, system of systems architecture nowadays. Subsequently, there are efforts to replace the classical sequential plant engineering by systems engineering, where the distributed automation entities in a plant represent a system. Considering this revamp, we propose AutomationML based mechatronic models as an enabler for automation systems engineering. Aggregating requirements from a motivating example, a prototypical implementation of a mechatronic model in AutomationML and its potentials concerning automation systems engineering are presented. A use case and its evaluation is detailed where these mechatronic models are visualized for model-based automation engineering or re-engineering. Initial results and future directions are presented.
{"title":"AutomationML Mechatronic Models as Enabler of Automation Systems Engineering: Use-case and Evaluation","authors":"Milan Vathoopan, H. Walzel, Waldemar Eisenmenger, Alois Zoitl, Benjamin Brandenbourger","doi":"10.1109/ETFA.2018.8502623","DOIUrl":"https://doi.org/10.1109/ETFA.2018.8502623","url":null,"abstract":"The industrial automation systems are slowly changing from a centralized architecture to a modularized, system of systems architecture nowadays. Subsequently, there are efforts to replace the classical sequential plant engineering by systems engineering, where the distributed automation entities in a plant represent a system. Considering this revamp, we propose AutomationML based mechatronic models as an enabler for automation systems engineering. Aggregating requirements from a motivating example, a prototypical implementation of a mechatronic model in AutomationML and its potentials concerning automation systems engineering are presented. A use case and its evaluation is detailed where these mechatronic models are visualized for model-based automation engineering or re-engineering. Initial results and future directions are presented.","PeriodicalId":6566,"journal":{"name":"2018 IEEE 23rd International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"15 1","pages":"51-58"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81852794","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-09-01DOI: 10.1109/ETFA.2018.8502448
J. Sini, M. Violante, R. Dessì
This paper presents a methodology to aid the development of multi-agent cyber-physical systems. The software architecture is structured in a multi-layer fashion, distributed on different devices (agents), making its design very challenging. A methodology is thus needed to meet the performance goal of such a system. The proposed methodology relies on Model-Based Software Design techniques, and on the Model/Software/Hardware-In-The-Loop (MIL, SIL, HIL) simulations. In particular, the HIL verification technique, which is widely adopted in the automotive and avionic industry also in the early development phases as a Computer-Aided Design tool, is the core tool of the real-time performances assessment verification. To speed-up the development process, and to obtain a toolchain coherent with the proposed approach, the adoption of a Model-Based Software Design methodology represents an optimal solution. Within those assumptions, we propose a benchmark of the methodology, applied on a customized multiagent system. The aim is to prove that the proposed method is able to achieve and verify a set of real-time requirements on the system behavior.
{"title":"Computer-Aided Design of Multi-Agent Cyber-Physical Systems","authors":"J. Sini, M. Violante, R. Dessì","doi":"10.1109/ETFA.2018.8502448","DOIUrl":"https://doi.org/10.1109/ETFA.2018.8502448","url":null,"abstract":"This paper presents a methodology to aid the development of multi-agent cyber-physical systems. The software architecture is structured in a multi-layer fashion, distributed on different devices (agents), making its design very challenging. A methodology is thus needed to meet the performance goal of such a system. The proposed methodology relies on Model-Based Software Design techniques, and on the Model/Software/Hardware-In-The-Loop (MIL, SIL, HIL) simulations. In particular, the HIL verification technique, which is widely adopted in the automotive and avionic industry also in the early development phases as a Computer-Aided Design tool, is the core tool of the real-time performances assessment verification. To speed-up the development process, and to obtain a toolchain coherent with the proposed approach, the adoption of a Model-Based Software Design methodology represents an optimal solution. Within those assumptions, we propose a benchmark of the methodology, applied on a customized multiagent system. The aim is to prove that the proposed method is able to achieve and verify a set of real-time requirements on the system behavior.","PeriodicalId":6566,"journal":{"name":"2018 IEEE 23rd International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"58 1","pages":"677-684"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80689084","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：