Patricia M. Dold, Fabian Bleier, Meiko Boley, Ralf Mikut
Abstract In production, quality monitoring is essential to detect defective elements. State-of-the-art approaches are single-sensor systems (SSS) and multi-sensor systems (MSS). Yet, these approaches might not be suitable: Nowadays, one component may comprise several hundred meters of the weld seam, necessitating high-speed welding to produce enough components. To detect as many defects as possible in time, fast yet precise monitoring is required. However, information captured by SSS might not be sufficient and MSS suffer from long inference times. Therefore, we present a confidence-based cascaded system (CS). The key idea of the CS is that not all data are analyzed to obtain the quality weld, but only selected ones. As evidenced by our results, all CS outperform SSS in terms of accuracy and inference time. Further, compared to MSS, the CS has hardware advantages.
{"title":"Two-stage quality monitoring of a laser welding process using machine learning","authors":"Patricia M. Dold, Fabian Bleier, Meiko Boley, Ralf Mikut","doi":"10.1515/auto-2023-0044","DOIUrl":"https://doi.org/10.1515/auto-2023-0044","url":null,"abstract":"Abstract In production, quality monitoring is essential to detect defective elements. State-of-the-art approaches are single-sensor systems (SSS) and multi-sensor systems (MSS). Yet, these approaches might not be suitable: Nowadays, one component may comprise several hundred meters of the weld seam, necessitating high-speed welding to produce enough components. To detect as many defects as possible in time, fast yet precise monitoring is required. However, information captured by SSS might not be sufficient and MSS suffer from long inference times. Therefore, we present a confidence-based cascaded system (CS). The key idea of the CS is that not all data are analyzed to obtain the quality weld, but only selected ones. As evidenced by our results, all CS outperform SSS in terms of accuracy and inference time. Further, compared to MSS, the CS has hardware advantages.","PeriodicalId":55437,"journal":{"name":"At-Automatisierungstechnik","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135810737","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Zusammenfassung LLC-Resonanzwandler spielen eine wichtige Rolle bei der Energieversorgung batteriebetriebener Elektrokleinfahrzeuge. Die Modellierung des nichtlinearen, dynamischen Verhaltens dieser Schaltungstopologie ist seit einiger Zeit Gegenstand von Forschungs- und Entwicklungsarbeiten. Häufig werden hierzu möglichst einfache lineare Kleinsignalmodelle abgeleitet, welche allerdings nur einen Reglerentwurf in einem Arbeitspunkt zulassen. Die vorliegende Arbeit greift eine neue Methode zur Modellierung von LLC-Resonanzwandlern auf und erweitert diese im Rahmen eines Takagi-Sugeno Fuzzy-Modells, um das nichtlineare Verhalten über einen großen Arbeitsbereich abzudecken. Die vorgestellte Methode wird mit einem datengetriebenen Takagi-Sugeno-Modell verglichen.
{"title":"Approximative Modellierung eines LLC-Resonanzwandlers mit Takagi-Sugeno-Modellen","authors":"Alessio Cavaterra, Steven Lambeck, Ulf Schwalbe","doi":"10.1515/auto-2023-0015","DOIUrl":"https://doi.org/10.1515/auto-2023-0015","url":null,"abstract":"Zusammenfassung LLC-Resonanzwandler spielen eine wichtige Rolle bei der Energieversorgung batteriebetriebener Elektrokleinfahrzeuge. Die Modellierung des nichtlinearen, dynamischen Verhaltens dieser Schaltungstopologie ist seit einiger Zeit Gegenstand von Forschungs- und Entwicklungsarbeiten. Häufig werden hierzu möglichst einfache lineare Kleinsignalmodelle abgeleitet, welche allerdings nur einen Reglerentwurf in einem Arbeitspunkt zulassen. Die vorliegende Arbeit greift eine neue Methode zur Modellierung von LLC-Resonanzwandlern auf und erweitert diese im Rahmen eines Takagi-Sugeno Fuzzy-Modells, um das nichtlineare Verhalten über einen großen Arbeitsbereich abzudecken. Die vorgestellte Methode wird mit einem datengetriebenen Takagi-Sugeno-Modell verglichen.","PeriodicalId":55437,"journal":{"name":"At-Automatisierungstechnik","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135810496","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Selected contributions from the Workshop “Computational Intelligence”","authors":"Ralf Mikut, Andreas Kroll, Horst Schulte","doi":"10.1515/auto-2023-0159","DOIUrl":"https://doi.org/10.1515/auto-2023-0159","url":null,"abstract":"","PeriodicalId":55437,"journal":{"name":"At-Automatisierungstechnik","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135810487","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract The online classification of grid disturbances in power transmission systems has been investigated since many years and shows promising results on measured and simulated PMU signals. Nonetheless, a practical deployment of machine learning techniques is still challenging due to robustness problems, which may lead to severe misclassifications in the model application. This paper formulates an advanced evaluation procedure for disturbance classification methods by introducing additional measurement noise, unknown operational points, and unknown disturbance events in the test dataset. Based on preliminary work, Siamese Sigmoid Networks are used as classification approach and are compared against several benchmark models for a simulated power transmission system at 400 kV. Different test scenarios are proposed to evaluate the disturbance classification models assuming a limited and full observability of the grid with PMUs.
{"title":"Influence of nuisance variables on the PMU-based disturbance classification in power transmission systems","authors":"André Kummerow, Peter Bretschneider","doi":"10.1515/auto-2023-0023","DOIUrl":"https://doi.org/10.1515/auto-2023-0023","url":null,"abstract":"Abstract The online classification of grid disturbances in power transmission systems has been investigated since many years and shows promising results on measured and simulated PMU signals. Nonetheless, a practical deployment of machine learning techniques is still challenging due to robustness problems, which may lead to severe misclassifications in the model application. This paper formulates an advanced evaluation procedure for disturbance classification methods by introducing additional measurement noise, unknown operational points, and unknown disturbance events in the test dataset. Based on preliminary work, Siamese Sigmoid Networks are used as classification approach and are compared against several benchmark models for a simulated power transmission system at 400 kV. Different test scenarios are proposed to evaluate the disturbance classification models assuming a limited and full observability of the grid with PMUs.","PeriodicalId":55437,"journal":{"name":"At-Automatisierungstechnik","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135810733","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract A power tracking controller for frequency support by photovoltaic power plants without battery storage is presented. Due to the decreasing inertia, regenerative systems such as wind turbines and photovoltaic power plants must provide an instantaneous reserve for fast frequency support in power systems. To provide grid support by PV power plants, a control scheme, and a design procedure are introduced to ensure power reserve by leaving the optimal operating point. A model-based generalized design procedure in the Takagi-Sugeno fuzzy framework for PV system with switched-mode DC-DC converter is presented to achieve the specified control objectives. Simulation studies show the applicability of the control scheme.
{"title":"Fast power tracking control of PV power plants for frequency support","authors":"Horst Schulte, Stephan Kusche","doi":"10.1515/auto-2023-0029","DOIUrl":"https://doi.org/10.1515/auto-2023-0029","url":null,"abstract":"Abstract A power tracking controller for frequency support by photovoltaic power plants without battery storage is presented. Due to the decreasing inertia, regenerative systems such as wind turbines and photovoltaic power plants must provide an instantaneous reserve for fast frequency support in power systems. To provide grid support by PV power plants, a control scheme, and a design procedure are introduced to ensure power reserve by leaving the optimal operating point. A model-based generalized design procedure in the Takagi-Sugeno fuzzy framework for PV system with switched-mode DC-DC converter is presented to achieve the specified control objectives. Simulation studies show the applicability of the control scheme.","PeriodicalId":55437,"journal":{"name":"At-Automatisierungstechnik","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135810486","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract The quality of data used for data-driven modeling affects the model performance significantly. Thus, design of experiments (DoE) is an important part during model development. The design space is constrained in many applications. In this work, the constrained case is investigated. An Latin hypercube based approach is applied and analyzed for strongly constrained design spaces. Contrary to commonly used optimization techniques, an incremental procedure is proposed. In every step, new data are added to the design. Each new point is selected by a distance-based criterion. The performance of the created designs is evaluated by the quality of the trained models. For different constraints, artificial data sets are created with a function generator. The performance of local model networks and Gaussian process regression models trained with those designs is evaluated and compared to models trained on data sets based on Sobol’ sequences.
{"title":"Latin hypercubes for constrained design of experiments for data-driven models","authors":"Fabian Schneider, Ralph J. Hellmig, Oliver Nelles","doi":"10.1515/auto-2023-0017","DOIUrl":"https://doi.org/10.1515/auto-2023-0017","url":null,"abstract":"Abstract The quality of data used for data-driven modeling affects the model performance significantly. Thus, design of experiments (DoE) is an important part during model development. The design space is constrained in many applications. In this work, the constrained case is investigated. An Latin hypercube based approach is applied and analyzed for strongly constrained design spaces. Contrary to commonly used optimization techniques, an incremental procedure is proposed. In every step, new data are added to the design. Each new point is selected by a distance-based criterion. The performance of the created designs is evaluated by the quality of the trained models. For different constraints, artificial data sets are created with a function generator. The performance of local model networks and Gaussian process regression models trained with those designs is evaluated and compared to models trained on data sets based on Sobol’ sequences.","PeriodicalId":55437,"journal":{"name":"At-Automatisierungstechnik","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135810938","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
S. Fluchs, Emre Taştan, Tobias Trumpf, Alexander Horch, R. Drath, A. Fay
Zusammenfassung „Security by Design“ ist der Begriff für die Verlagerung von Cybersecurity-Überlegungen von den Endnutzern eines Systems auf dessen Planer und Realisierer im Engineering. Um die Last auf den Schultern der Endnutzer zu verringern, müssen Security-Entscheidungen nicht nur während der Entwicklung getroffen werden, sondern auch in einer Weise, die für Dritte nachvollziehbar ist. Planer von industriellen Automatisierungssystemen (ICS) verfügen jedoch in der Regel weder über Security-Expertise noch über Zeit für das Security-Engineering. Die in dieser Arbeit vorgestellte Methode „Security by Design Decisions“ soll sie in die Lage versetzen, Security-Entscheidungen trotzdem selbstständig zu identifizieren, zu treffen und zu begründen. Kernelemente der Methode sind funktionsbasierte Diagramme sowie vordefinierte Bibliotheken mit typischen Funktionen und deren Security-Parametern. Die als Software-Demonstrator implementierte Methode wurde mit HIMA, einem deutschen Spezialisten für sicherheitsgerichtete Automatisierungslösungen, validiert. Die Ergebnisse zeigen, dass Planer mit ihrer Hilfe Security-Entscheidungen identifizieren, treffen und nachvollziehbar dokumentieren können, die sie sonst nicht (bewusst) getroffen hätten – schnell und mit wenig Security-Expertise. Die Methode ist auch gut geeignet, um weniger erfahrenen Personen Wissen über Security-Entscheidungen zugänglich zu machen. Zusammengefasst können mit der Methode „Security by Design Decisions“ mehr Personen in kürzerer Zeit zur „Security by Design“ eines ICS beitragen.
{"title":"Nachvollziehbare Security by Design-Entscheidungen für Automatisierungssysteme mittels funktionsbasierter Diagramme und Security-Bibliotheken","authors":"S. Fluchs, Emre Taştan, Tobias Trumpf, Alexander Horch, R. Drath, A. Fay","doi":"10.1515/auto-2023-0084","DOIUrl":"https://doi.org/10.1515/auto-2023-0084","url":null,"abstract":"Zusammenfassung „Security by Design“ ist der Begriff für die Verlagerung von Cybersecurity-Überlegungen von den Endnutzern eines Systems auf dessen Planer und Realisierer im Engineering. Um die Last auf den Schultern der Endnutzer zu verringern, müssen Security-Entscheidungen nicht nur während der Entwicklung getroffen werden, sondern auch in einer Weise, die für Dritte nachvollziehbar ist. Planer von industriellen Automatisierungssystemen (ICS) verfügen jedoch in der Regel weder über Security-Expertise noch über Zeit für das Security-Engineering. Die in dieser Arbeit vorgestellte Methode „Security by Design Decisions“ soll sie in die Lage versetzen, Security-Entscheidungen trotzdem selbstständig zu identifizieren, zu treffen und zu begründen. Kernelemente der Methode sind funktionsbasierte Diagramme sowie vordefinierte Bibliotheken mit typischen Funktionen und deren Security-Parametern. Die als Software-Demonstrator implementierte Methode wurde mit HIMA, einem deutschen Spezialisten für sicherheitsgerichtete Automatisierungslösungen, validiert. Die Ergebnisse zeigen, dass Planer mit ihrer Hilfe Security-Entscheidungen identifizieren, treffen und nachvollziehbar dokumentieren können, die sie sonst nicht (bewusst) getroffen hätten – schnell und mit wenig Security-Expertise. Die Methode ist auch gut geeignet, um weniger erfahrenen Personen Wissen über Security-Entscheidungen zugänglich zu machen. Zusammengefasst können mit der Methode „Security by Design Decisions“ mehr Personen in kürzerer Zeit zur „Security by Design“ eines ICS beitragen.","PeriodicalId":55437,"journal":{"name":"At-Automatisierungstechnik","volume":"71 1","pages":"759 - 778"},"PeriodicalIF":1.0,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42301808","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","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：