H. Vietz, T. Rauch, A. Löcklin, N. Jazdi, und M. Weyrich, „A Methodology to Identify Cognition Gaps in Visual Recognition Applications Based on Convolutional Neural Network“, in 2021 IEEE 17th International Conference on Automation Science and Engineering (CASE), Lyon, France, 23-27 August 2021, 2021, S. 2045–2050.
Zusammenfassung
Developing consistently well performing visual recognition applications based on convolutional neural networks, e.g. for autonomous driving, is very challenging. One of the obstacles during the development is the opaqueness of their cognitive behaviour. A considerable amount of literature has been published which describes irrational behaviour of trained CNNs showcasing gaps in their cognition. In this paper, a methodology is presented that creates worst-case images using image augmentation techniques. If the CNN's cognitive performance on such images is weak while the augmentation techniques are supposedly harmless, a potential gap in the cognition has been found. The presented worst-case image generator is using adversarial search approaches to efficiently identify the most challenging (worst) image. This is evaluated with the well-known AlexNet CNN using images depicting a typical driving scenario.BibTeX
M. Müller, N. Jazdi, A. Löcklin, L. Hettich, und M. Weyrich, „Adaptive Models for Safe Maintenance Planning of Cyber-physical Systems“, in 15 th CIRP Conference on Intelligent Computation and Manufacturing Engineering, Gulf of Naples, Italy, July 2021, 2021.
Zusammenfassung
The progress of digitalization and Internet of Things enables more and more complex, networked and powerful Cyber-physical Systems (CPS) operating in uncertain environments. This complexity and uncertainty, however, makes it unfeasible to model every aspect in advance. This causes the models to leave their scope and reach their capability limits. Specifically, in safe maintenance planning for highly-automated trucks, this fact causes waste of valuable resource, since maintenance models are often more rule-of-thumb (e.g. operation hours) than precise. In order to counteract this issue, we propose extending the digital twin concept by artificial intelligence such that the models become dynamic and adaptive. Having described the general approach and its architecture, we showcase and evaluate the approach in a highly-automated truck scenario.BibTeX
A. Löcklin, T. Jung, N. Jazdi, T. Ruppert, und M. Weyrich, „Architecture of a Human-Digital Twin as Common Interface for Operator 4.0 Applications“, Procedia CIRP, Vol. 104, pp. 458-463, September 2021, 2021.
Zusammenfassung
At collaborative workspaces, humans and robots share the shop floor and work closely together. Operator 4.0 is a wide research topic and its solutions aim at the creation of Human-centered Cyber-Physical Systems that improve operators’ capabilities. Such applications require a bi directional flow of information and need data, models and simulations of machines as well as humans. To realize a common interface for information, the concept of Digital Twin is promising. This paper therefore discusses the adaption of conventional Digital Twin architectures and presents a derived Human-centered Digital Twin (H-DT) architecture designed for operators in production and intralogistics.BibTeX
A. Löcklin, H. Vietz, D. White, T. Ruppert, N. Jazdi, und M. Weyrich, „Data administration shell for data-science-driven development“, Procedia CIRP, vol. 100, pp. 115-120, Mai 2021, 2021.
Zusammenfassung
Data-science-driven development projects are increasingly gaining the attention of small and medium sized enterprises. Since SME are often lacking the necessary competencies in data science, cooperation with other companies or universities is required. The efficient handling of data is one of the main challenges in joint cross-enterprise development projects. Actual cost driver is the development of data by labeling and classifying the data by domain experts, which is very time-consuming and labor-intensive with large amounts of data. Furthermore, clearance processes also have a high potential to cause delays before data can be shared with project partners. Moreover, before the actual work can begin, it is often necessary to clean up and repair incomplete or noisy data. The concept of Data Administration Shell presented in this paper addresses the challenge of structured information sharing and information management in joint cross-enterprise engineering. The Data Administration Shell links data sets to information regarding data origin and already performed analyses including their results and program scripts. Adding relations and documentation facilitates the reuse of data sets for subsequent projects. For this purpose, the Data Administration Shell adapts the concepts serving the information sharing in the research field of manufacturing and Digital Twin. The evaluation of the Data Administration Shell was based on time-series measurement data from a production process optimization scenario. Here, the Data Administration Shell manages the data sets of time series data and facilitates the joint cross-enterprise engineering of data-driven solutions.BibTeX
A. Löcklin, K. Przybysz-Herz, T. Ruppert, R. Libert, L. Jakab, N. Jazdi, und M. Weyrich, „Tailored digitization with real-time locating systems: Ultra-wideband RTLS for production and logistics“, atp magazin vol. 63, no. 3, pp. 76-83, März, 2021, 2021.
Zusammenfassung
We are seeing a boom in the use of real-time position data to automate and optimize tasks in the field of production and logistics. Here we consider the reasons for this, show what has already proven to be industrially viable and give an overview of six current research efforts. We show which use cases have been automated by RTLS and where RTLS could play a role to further optimize production processes or material flows in the future.BibTeX
A. Löcklin, C. Kotsch, K. Krüning, M. Rentschler, C. Ebert, M. Müller, und M. Weyrich, „Testen 4.0 in der Automatisierungstechnik: Agiles modellbasiertes Testen vernetzter Systeme und Komponenten“, Automation 2021, VDI Verlag GmbH Düsseldorf, pp. 335-352, 29. und 30 June 2021, 2021.
Zusammenfassung
Die Flexibilisierung von Produktionsanlagen ist notwendig, um in einem volatilen Marktumfeld erfolgreich sein zu können. Durch die Bereitstellung und Pflege geeigneter Schnittstellen und Betriebsmodi, sowie dem Umbau von Anlagen, kann auf geänderte Anforderungen an die Produktion reagiert werden. Für die Realisierung derartiger hochflexibler und rekonfigurierbarer Anlagen ist ein erhöhter Engineering- und Testaufwand notwendig. Jede zusätzliche Funktion samt aller damit verbundener Abhängigkeiten müssen vor Inbetriebnahme mehrfach von Herstellern, Integratoren und Betreibern überprüft werden. Damit der resultierende erhöhte Testaufwand auch zukünftig handhabbar bleibt, werden in dieser Veröffentlichung folgende Ansätze vorgestellt, um ein effizientes und wirkungsvolles Testen im Bereich der flexiblen Produktion zu ermöglichen: Zum einen lässt sich durch eine auf Richtlinien basierende Modularisierung von Anlagen und Komponenten der Testaufwand reduzieren. Auch sorgen Agile Teams für eine verbesserte Kommunikation zwischen Entwicklungs- und Testabteilungen. Überdies ermöglicht die Anwendung von Digitalen Zwillingen einen effektiveren Informationsaustausch zwischen den Stakeholdern und Modellbasiertes Testen ermöglicht Vorteile bei der Testautomatisierung. Alle Ansätze sind jeweils eigenständig wirksam, aber zusammengenommen ergeben sich zusätzliche Synergieeffekte.BibTeX
B. Maschler, T. Müller, A. Löcklin, und M. Weyrich, „Transfer Learning as an Enhancement for Reconfiguration Management of Cyber-Physical Production Systems“, in 15th CIRP Conference on Intelligent Computation and Manufacturing Engineering, July 2021, Gulf of Naples, Italy, 2021.
Zusammenfassung
Reconfiguration demand is increasing due to frequent requirement changes for manufacturing systems. Recent approaches aim at investigating feasible configuration alternatives from which they select the optimal one. This relies on processes whose behavior is not reliant on e.g. the production sequence. However, when machine learning is used, components’ behavior depends on the process’ specifics, requiring additional concepts to successfully conduct reconfiguration management. Therefore, we propose the enhancement of the comprehensive reconfiguration management with transfer learning. This provides the ability to assess the machine learning dependent behavior of the different CPPS configurations with reduced effort and further assists the recommissioning of the chosen one. A real cyber-physical production system from the discrete manufacturing domain is utilized to demonstrate the aforementioned proposal.BibTeX