Pub Date : 2021-09-07DOI: 10.1109/ETFA45728.2021.9613178
Z. Bakhshi, G. Rodríguez-Navas, H. Hansson
In our previous work we proposed a fault-tolerant persistent storage for container-based fog architecture. We leveraged the use of containerization to provide storage as a containerized application working along with other containers. As a fault-tolerance mechanism we introduced a replicated data structure and to solve consistency issue between the replicas distributed in the cluster of nodes, we used the RAFT consensus protocol. In this paper, we verify our proposed solution using the UPPAAL model checker. We explain how our solution is modeled in UPPAAL and present a formal verification of key properties related to persistent storage and data consistency between nodes.
{"title":"Using UPPAAL to Verify Recovery in a Fault-tolerant Mechanism Providing Persistent State at the Edge","authors":"Z. Bakhshi, G. Rodríguez-Navas, H. Hansson","doi":"10.1109/ETFA45728.2021.9613178","DOIUrl":"https://doi.org/10.1109/ETFA45728.2021.9613178","url":null,"abstract":"In our previous work we proposed a fault-tolerant persistent storage for container-based fog architecture. We leveraged the use of containerization to provide storage as a containerized application working along with other containers. As a fault-tolerance mechanism we introduced a replicated data structure and to solve consistency issue between the replicas distributed in the cluster of nodes, we used the RAFT consensus protocol. In this paper, we verify our proposed solution using the UPPAAL model checker. We explain how our solution is modeled in UPPAAL and present a formal verification of key properties related to persistent storage and data consistency between nodes.","PeriodicalId":312498,"journal":{"name":"2021 26th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA )","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127438054","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 : 2021-09-07DOI: 10.1109/ETFA45728.2021.9613622
Georg Buchgeher, R. Ramler, Heinz Stummer, H. Kaufmann
Microservices are widely used by large internet companies as they support scalable systems with high resilience and fault-tolerance, flexible and agile development, and continuous delivery enabling fast time to market. Hence, there is an increasing interest in adopting microservices in the field of industrial automation. This raises the question, if and to what degree this architectural style can also be applied for the development of industrial control systems (ICS). In this paper, we have systematically analyzed the applicability of microservices for ICS development. Together with domain experts from industry, we have developed a migration path from a monolithic ICS towards cloud-ready systems based on microservices. By studying the central principles for microservice development and operation, we found that microservices can be applied in the context of ICS and the use of microservices leads to increased flexibility with regard to frequent software releases and the development of new deployment variants. However, communication between real-time services is still an open research challenge that poses a potential technical risk in the migration towards adopting full microservice-based system architectures.
{"title":"Adopting Microservices for Industrial Control Systems: A Five Step Migration Path","authors":"Georg Buchgeher, R. Ramler, Heinz Stummer, H. Kaufmann","doi":"10.1109/ETFA45728.2021.9613622","DOIUrl":"https://doi.org/10.1109/ETFA45728.2021.9613622","url":null,"abstract":"Microservices are widely used by large internet companies as they support scalable systems with high resilience and fault-tolerance, flexible and agile development, and continuous delivery enabling fast time to market. Hence, there is an increasing interest in adopting microservices in the field of industrial automation. This raises the question, if and to what degree this architectural style can also be applied for the development of industrial control systems (ICS). In this paper, we have systematically analyzed the applicability of microservices for ICS development. Together with domain experts from industry, we have developed a migration path from a monolithic ICS towards cloud-ready systems based on microservices. By studying the central principles for microservice development and operation, we found that microservices can be applied in the context of ICS and the use of microservices leads to increased flexibility with regard to frequent software releases and the development of new deployment variants. However, communication between real-time services is still an open research challenge that poses a potential technical risk in the migration towards adopting full microservice-based system architectures.","PeriodicalId":312498,"journal":{"name":"2021 26th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA )","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122477819","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 : 2021-09-07DOI: 10.1109/ETFA45728.2021.9613179
Nico Braunisch, Sven Schlesinger, R. Lehmann
In this paper, we present our approach towards a modular and adaptable IoT gateway for operational data and functions in the use case of retrofitting brownfield installation for industrie 4.0. The aim is to enable the existing operational technology installation to provide accessible function endpoints that can be triggered by modern IT services. To fulfill the high demands of flexibility in the IT and the requirements towards time-critical response in the OT a highly decoupled architecture employing a streaming platform is proposed. In perspective to mediating between synchronous interaction in functional aspects and asynchronous behavior in OT-IT communication a function call gateway resolves this issue with the support of a highperformance RPC framework. For the concept to be useful for a wide range of retrofitted OT, design principles and modeling standards of Industrie 4.0 are used.
{"title":"Function call gateway for operational aspects in Industrie 4.0","authors":"Nico Braunisch, Sven Schlesinger, R. Lehmann","doi":"10.1109/ETFA45728.2021.9613179","DOIUrl":"https://doi.org/10.1109/ETFA45728.2021.9613179","url":null,"abstract":"In this paper, we present our approach towards a modular and adaptable IoT gateway for operational data and functions in the use case of retrofitting brownfield installation for industrie 4.0. The aim is to enable the existing operational technology installation to provide accessible function endpoints that can be triggered by modern IT services. To fulfill the high demands of flexibility in the IT and the requirements towards time-critical response in the OT a highly decoupled architecture employing a streaming platform is proposed. In perspective to mediating between synchronous interaction in functional aspects and asynchronous behavior in OT-IT communication a function call gateway resolves this issue with the support of a highperformance RPC framework. For the concept to be useful for a wide range of retrofitted OT, design principles and modeling standards of Industrie 4.0 are used.","PeriodicalId":312498,"journal":{"name":"2021 26th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA )","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126084963","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 : 2021-09-07DOI: 10.1109/ETFA45728.2021.9613378
A. Casavola, G. Franzé, Francesco Tedesco
In this paper, an adaptive sensor selection architecture is developed to deal with distributed state estimation problems for multi-agent networked systems consisting of three different classes of nodes (plants, sensors and agents). Specifically, the problem of adequately fusing the sensors data coming from the plants and delivered to the agents, is addressed by evaluating their trustworthiness. This is achieved by exploiting a well-established approach in the power electronics: the Perturb&Observe algorithm that in the present framework allows one to select the more adequate group of sensors so as to compute at each time instant the best state estimate according to a given performance index. Some simulations are finally reported to testify the effectiveness of the proposed methodology.
{"title":"Sensors Selection via a Distributed Reputation Mechanism: An Information Fusion Approach","authors":"A. Casavola, G. Franzé, Francesco Tedesco","doi":"10.1109/ETFA45728.2021.9613378","DOIUrl":"https://doi.org/10.1109/ETFA45728.2021.9613378","url":null,"abstract":"In this paper, an adaptive sensor selection architecture is developed to deal with distributed state estimation problems for multi-agent networked systems consisting of three different classes of nodes (plants, sensors and agents). Specifically, the problem of adequately fusing the sensors data coming from the plants and delivered to the agents, is addressed by evaluating their trustworthiness. This is achieved by exploiting a well-established approach in the power electronics: the Perturb&Observe algorithm that in the present framework allows one to select the more adequate group of sensors so as to compute at each time instant the best state estimate according to a given performance index. Some simulations are finally reported to testify the effectiveness of the proposed methodology.","PeriodicalId":312498,"journal":{"name":"2021 26th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA )","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121079676","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 : 2021-09-07DOI: 10.1109/ETFA45728.2021.9613698
Andreas Berlet, Julius Rückert, H. Koziolek, R. Drath, Mike Barth
Process engineers design industrial process plants using piping and instrumentation diagrams (P&IDs). Today, data analysts who diagnose plant disturbances based on historical signal trends usually analyze these complex diagrams manually on paper, which is time-consuming and error-prone. In the last 15 years, researchers have thus proposed several approaches and tools to turn these diagrams into machine-readable models that can be processed by software tools. Yet, these tools lack sophisticated query interfaces and intuitive visualizations. We propose the method TOPNAV to navigate plant topology models and aid data analytics. The method supports systematic searching for elements and paths in topology models and feeding the results into analytical tools to facilitate statistical analyses. In a user study, an up to 90% time reduction was observed compared to manual P&ID analysis, while reducing errors significantly.
{"title":"TOPNAV: Efficiently Navigating through Industrial Process Plant Topologies","authors":"Andreas Berlet, Julius Rückert, H. Koziolek, R. Drath, Mike Barth","doi":"10.1109/ETFA45728.2021.9613698","DOIUrl":"https://doi.org/10.1109/ETFA45728.2021.9613698","url":null,"abstract":"Process engineers design industrial process plants using piping and instrumentation diagrams (P&IDs). Today, data analysts who diagnose plant disturbances based on historical signal trends usually analyze these complex diagrams manually on paper, which is time-consuming and error-prone. In the last 15 years, researchers have thus proposed several approaches and tools to turn these diagrams into machine-readable models that can be processed by software tools. Yet, these tools lack sophisticated query interfaces and intuitive visualizations. We propose the method TOPNAV to navigate plant topology models and aid data analytics. The method supports systematic searching for elements and paths in topology models and feeding the results into analytical tools to facilitate statistical analyses. In a user study, an up to 90% time reduction was observed compared to manual P&ID analysis, while reducing errors significantly.","PeriodicalId":312498,"journal":{"name":"2021 26th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA )","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126856720","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 : 2021-09-07DOI: 10.1109/ETFA45728.2021.9613265
Deniz Neufeld, Ute Schmid
This work focuses on computationally efficient difference metrics of time series and compares two different unsupervised methods for anomaly classification. It takes place in the domain of hardware systems testing for reliability, where several structurally identical devices are tested at the same time with a load expected in their lifetime use. The devices perform different maneuvers in predefined testing cycles. It is possible that rare, unexpected system defects appear. They often show up in the measured data signals of the system, for example as a decrease in the output pressure of a pump. Due to the intended aging of the parts under load, the measured data also exhibits a concept drift, i.e. a shift in the data distribution. It is of interest to detect anomalous behavior as early as possible to reduce cost, save time and enable accurate root-cause-analysis. We formulate this problem as an anomaly detection task on periodic multivariate time series data. Experiments are evaluated using an open access hydraulic test bench data set by Helwig et al. [1]. The method's performance under concept drift is tested by simulating an aging system using the same data set. We find that Mean Squared Error towards the median in combination with the Modified z-Score is the most robust method for this use case. The solution can be applied from the beginning of a hardware testing cycle. The computations are intuitive to understand, and the classification results can be visualized for better interpretability and plausibility analysis.
{"title":"Anomaly Detection for Hydraulic Systems under Test","authors":"Deniz Neufeld, Ute Schmid","doi":"10.1109/ETFA45728.2021.9613265","DOIUrl":"https://doi.org/10.1109/ETFA45728.2021.9613265","url":null,"abstract":"This work focuses on computationally efficient difference metrics of time series and compares two different unsupervised methods for anomaly classification. It takes place in the domain of hardware systems testing for reliability, where several structurally identical devices are tested at the same time with a load expected in their lifetime use. The devices perform different maneuvers in predefined testing cycles. It is possible that rare, unexpected system defects appear. They often show up in the measured data signals of the system, for example as a decrease in the output pressure of a pump. Due to the intended aging of the parts under load, the measured data also exhibits a concept drift, i.e. a shift in the data distribution. It is of interest to detect anomalous behavior as early as possible to reduce cost, save time and enable accurate root-cause-analysis. We formulate this problem as an anomaly detection task on periodic multivariate time series data. Experiments are evaluated using an open access hydraulic test bench data set by Helwig et al. [1]. The method's performance under concept drift is tested by simulating an aging system using the same data set. We find that Mean Squared Error towards the median in combination with the Modified z-Score is the most robust method for this use case. The solution can be applied from the beginning of a hardware testing cycle. The computations are intuitive to understand, and the classification results can be visualized for better interpretability and plausibility analysis.","PeriodicalId":312498,"journal":{"name":"2021 26th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA )","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129289156","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 : 2021-09-07DOI: 10.1109/ETFA45728.2021.9613205
Jakob Giner, Raphael Lamprecht, Viola Gallina, Catherine Laflamme, Lennard Sielaff, W. Sihn
As the automation of production lines in modern manufacturing environments becomes ubiquitous, their flexibility and resilience become increasingly important. Consequently, the scheduling of maintenance activities is growing more complex and at the same time ever more crucial for ensuring adequate system availability. In this paper a digital model of a production environment is presented, using building blocks and restrictions that can be found in most modern production environments. Maintenance and repair activities in the model are scheduled by a reinforcement learning agent for different proof-of-concept scenarios, which can be optimised using measures such as maximizing production capacity and minimizing maintenance costs. The results of this paper provide the basis for further work to improve the working conditions of human maintenance planners by providing a reliable decision support system which facilitates the task of scheduling planned and unplanned maintenance activities.
{"title":"Demonstrating Reinforcement Learning for Maintenance Scheduling in a Production Environment","authors":"Jakob Giner, Raphael Lamprecht, Viola Gallina, Catherine Laflamme, Lennard Sielaff, W. Sihn","doi":"10.1109/ETFA45728.2021.9613205","DOIUrl":"https://doi.org/10.1109/ETFA45728.2021.9613205","url":null,"abstract":"As the automation of production lines in modern manufacturing environments becomes ubiquitous, their flexibility and resilience become increasingly important. Consequently, the scheduling of maintenance activities is growing more complex and at the same time ever more crucial for ensuring adequate system availability. In this paper a digital model of a production environment is presented, using building blocks and restrictions that can be found in most modern production environments. Maintenance and repair activities in the model are scheduled by a reinforcement learning agent for different proof-of-concept scenarios, which can be optimised using measures such as maximizing production capacity and minimizing maintenance costs. The results of this paper provide the basis for further work to improve the working conditions of human maintenance planners by providing a reliable decision support system which facilitates the task of scheduling planned and unplanned maintenance activities.","PeriodicalId":312498,"journal":{"name":"2021 26th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA )","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113932844","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 : 2021-09-07DOI: 10.1109/ETFA45728.2021.9613492
K. KrishneGowda, E. Peter, Matthias Scheide, L. Wimmer, R. Kays, E. Grass, R. Kraemer
We propose a closed-loop industrial radio system with a star topology for factory automation using Parallel Sequence Spread Spectrum (PSSS) technology. This system implements all significant concepts for synchronization, duplex-communication, channel estimation/equalization based on an innovative transceiver concept. The industrial environment tends to have non-line of sight channels that lead to RMS delay spreads of less than 100 ns. Here, we propose a channel equalization scheme to compensate for these delay spreads. Another challenging aspect is the implementation of a code division duplexing (CDD) scheme. We propose a closed-loop system architecture that can achieve the targets set by Industry 4.0 bodies such as IWSAN. This paper gives an overview of the closed-loop systems concept.
{"title":"Parallel Sequence Spread Spectrum based Ultra-Reliable Low Latency Communication for Factory Automation","authors":"K. KrishneGowda, E. Peter, Matthias Scheide, L. Wimmer, R. Kays, E. Grass, R. Kraemer","doi":"10.1109/ETFA45728.2021.9613492","DOIUrl":"https://doi.org/10.1109/ETFA45728.2021.9613492","url":null,"abstract":"We propose a closed-loop industrial radio system with a star topology for factory automation using Parallel Sequence Spread Spectrum (PSSS) technology. This system implements all significant concepts for synchronization, duplex-communication, channel estimation/equalization based on an innovative transceiver concept. The industrial environment tends to have non-line of sight channels that lead to RMS delay spreads of less than 100 ns. Here, we propose a channel equalization scheme to compensate for these delay spreads. Another challenging aspect is the implementation of a code division duplexing (CDD) scheme. We propose a closed-loop system architecture that can achieve the targets set by Industry 4.0 bodies such as IWSAN. This paper gives an overview of the closed-loop systems concept.","PeriodicalId":312498,"journal":{"name":"2021 26th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA )","volume":"634 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122950291","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 : 2021-09-07DOI: 10.1109/ETFA45728.2021.9613439
Zarina Chokparova, L. Urbas
Information plays a significant role in modern process industries due to the demand for flexibility and mobility in production. Therefore, it is important to preserve the privacy and security of the information exchanged and shared between partners in value chains, for instance asset chains or supply chains. Since many companies have their own technological solutions and methods for operation and control, this information is regarded as their intellectual property. For the protection of recipes, material flows, or operational and control variables during the manufacturing of products, various methods are available. These techniques include anonymization and encryption solutions. To deal with mathematical models and the computation of formulas, homomorphic encryption schemes can be applied to the data which have to be shared within a value chain. Based on the experience of previous implementations of homomorphic crypto system in different domains, the opportunities for adaptation of encryption methods in process industries are considered. This paper proposes the application of homomorphic encryption in a value chain and defines a specific protocol that enables the Paillier cryptosystem on a time series. A use case is designed for confidential information exchange between a secret owner and a value provider in a value chain. The architecture of confidentiality-preserving information sharing satisfies the zero-knowledge proof requirement and shows low similarity between original and recovered messages.
{"title":"Utilization of Homomorphic Cryptosystems for Information Exchange in Value Chains","authors":"Zarina Chokparova, L. Urbas","doi":"10.1109/ETFA45728.2021.9613439","DOIUrl":"https://doi.org/10.1109/ETFA45728.2021.9613439","url":null,"abstract":"Information plays a significant role in modern process industries due to the demand for flexibility and mobility in production. Therefore, it is important to preserve the privacy and security of the information exchanged and shared between partners in value chains, for instance asset chains or supply chains. Since many companies have their own technological solutions and methods for operation and control, this information is regarded as their intellectual property. For the protection of recipes, material flows, or operational and control variables during the manufacturing of products, various methods are available. These techniques include anonymization and encryption solutions. To deal with mathematical models and the computation of formulas, homomorphic encryption schemes can be applied to the data which have to be shared within a value chain. Based on the experience of previous implementations of homomorphic crypto system in different domains, the opportunities for adaptation of encryption methods in process industries are considered. This paper proposes the application of homomorphic encryption in a value chain and defines a specific protocol that enables the Paillier cryptosystem on a time series. A use case is designed for confidential information exchange between a secret owner and a value provider in a value chain. The architecture of confidentiality-preserving information sharing satisfies the zero-knowledge proof requirement and shows low similarity between original and recovered messages.","PeriodicalId":312498,"journal":{"name":"2021 26th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA )","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128418612","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 : 2021-09-07DOI: 10.1109/ETFA45728.2021.9613282
Tobias Gerlach, D. Eggink
Joining element and assembly design remain largely a manual process. This increases risks of more costly and longer development trajectories. Current automation solutions do not consider historical data and traditional machine learning approaches have limitations. Meanwhile, generative adversary networks became benchmark methodologies to perform generation tasks in computer vision. Products in manufacturing industry may contain thousands of spot welds, thus design automation enables engineers to focus on their core competencies. This work presents a methodology to predict spot weld locations using generative adversarial networks. A 2D-based approach implements a variant of StarGAN_v2 to predict locations. It uses domain-based prediction concepts that integrate clustering of geometrical and product manufacturing information, as well as reference guided style generation. Results indicate that generative adversarial networks can predict spot weld positions based on 2D image data.
{"title":"Generative Adversarial Networks for spot weld design","authors":"Tobias Gerlach, D. Eggink","doi":"10.1109/ETFA45728.2021.9613282","DOIUrl":"https://doi.org/10.1109/ETFA45728.2021.9613282","url":null,"abstract":"Joining element and assembly design remain largely a manual process. This increases risks of more costly and longer development trajectories. Current automation solutions do not consider historical data and traditional machine learning approaches have limitations. Meanwhile, generative adversary networks became benchmark methodologies to perform generation tasks in computer vision. Products in manufacturing industry may contain thousands of spot welds, thus design automation enables engineers to focus on their core competencies. This work presents a methodology to predict spot weld locations using generative adversarial networks. A 2D-based approach implements a variant of StarGAN_v2 to predict locations. It uses domain-based prediction concepts that integrate clustering of geometrical and product manufacturing information, as well as reference guided style generation. Results indicate that generative adversarial networks can predict spot weld positions based on 2D image data.","PeriodicalId":312498,"journal":{"name":"2021 26th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA )","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115866999","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：