TY - CHAP A1 - Radtke, Maximilian-Peter A1 - Bock, Jürgen ED - Do, Phuc ED - Michau, Gabriel ED - Ezhilarasu, Cordelia T1 - Combining Knowledge and Deep Learning for Prognostics and Health Management T2 - Proceedings of the European Conference of the PHM Society 2022 N2 - In the recent past deep learning approaches have achieved remarkable results in the area of Prognostics and Health Management (PHM). These algorithms rely on large amounts of data, which is often not available, and produce outputs, which are hard to interpret. Before the broad success of deep learning machine faults were often classified using domain expert knowledge based on experience and physical models. In comparison, these approaches only require small amounts of data and produce highly interpretable results. On the downside, however, they struggle to predict unexpected patterns hidden in data. This research aims to combine knowledge and deep learning to increase accuracy, robustness and interpretability of current models. UR - https://doi.org/10.36001/phme.2022.v7i1.3302 KW - Deep Learning KW - Knowledge KW - Hybrid AI Y1 - 2022 UR - https://doi.org/10.36001/phme.2022.v7i1.3302 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-27816 SN - 978-1-936263-36-3 SP - 594 EP - 597 PB - PHM Society CY - Rochester ER - TY - JOUR A1 - Hartl, Jakob Joseph Lorenz A1 - Bock, Jürgen T1 - A Maturity Model to Determine the Degree of Utilization of Machine Learning in Production Planning and Control Processes JF - Tehnički glasnik N2 - The presented work introduces a maturity model for evaluating Machine Learning implementations, with a primary focus on Production Planning and Control processes, as well as broader organizational and technical aspects in companies. This model emerges as a response to the research gap identified in the analysis of 14 existing maturity models, which served as foundational bases for the development of this novel approach. By examining success factors and obstacles at different maturity levels, categorized according to defined dimensions and overarching design fields, this model can serve as a catalyst for bridging the research gap between models demanded in practice and the scholary exploration of topics related to Machine Learning in corporate processes. Notably, the structured design of this maturity model ensures accessibility for small and medium sized enterprises (SMEs). UR - https://doi.org/10.31803/tg-20240513233046 Y1 - 2024 UR - https://doi.org/10.31803/tg-20240513233046 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-49102 SN - 1848-5588 SN - 1846-6168 VL - 18 IS - 3 SP - 437 EP - 444 PB - University North CY - Koprivnica ER - TY - JOUR A1 - Demiral, Tarik A1 - Bock, Jürgen A1 - Johansson, Pierre T1 - Challenges in Flexible Manufacturing Technologies for the Final Assembly in the Commercial Vehicle Industry JF - Tehnički glasnik N2 - Increasing customer demands and product diversity as well as emerging technologies and market trends, such as the establishment of new driveline technologies, like e-mobility or hydrogen, present challenges for manufacturing companies in the commercial vehicle industry. Consequently, companies must strengthen their focus to the aspect of flexibility within their manufacturing processes. This paper contributes to the state of the art in flexible manufacturing technologies research, which enables manufacturing companies to deal with these increasing flexibility requirements. Focussing on the area of final assembly the paper takes a holistic perspective and characterizes the readiness of automotive companies to be able to implement flexible manufacturing technologies. The system ecosystem and the process organization of automotive companies are examined with respect to the requirements of flexible manufacturing. Finally, gaps that hinder the implementation of flexible manufacturing technologies are identified and described, and possible solution concepts for the identified gaps are proposed. UR - https://doi.org/10.31803/tg-20230417140747 KW - business capabilities KW - final assembly KW - flexibility KW - gap analysis KW - manufacturing Y1 - 2023 UR - https://doi.org/10.31803/tg-20230417140747 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-37880 SN - 1848-5588 VL - 17 IS - 2 SP - 260 EP - 267 PB - University North CY - Koprivnica ER - TY - CHAP A1 - Winter, Michael A1 - Bock, Jürgen A1 - Hoos, Johannes A1 - Klausmann, Tobias A1 - Schnebel, Boris A1 - Schmitt, Siwara A1 - Simon, Marco A1 - Stolze, Melanie A1 - Vieira da Silva, Luis Miguel A1 - Kleinert, Tobias ED - Jumar, Ulrich ED - Diedrich, Christian T1 - Methods to Describe, Assign and Derive Capabilities from the Capability, Skill and Service (CSS) Model T2 - 18. Fachtagung, EKA 2024, Entwurf komplexer Automatisierungssysteme, Beschreibungsmittel, Methoden, Werkzeuge und Anwendungen N2 - For the use of the CSS model, workflows are needed to describe, assign and derive capabilities. This contribution provides a Capability Determining method that encompasses the three underlying technology-independent methods to guide stakeholders in describing, assigning and deriving capabilities for manufacturing. The first underlying method, Describing Capabilities, describes a workflow for the formal semantic description of capabilities. The workflow for assigning capabilities to a production resource is explained using the second method Assigning Capability. In the last workflow, capabilities are derived from production specification or a process description using the method Deriving Capability. UR - http://dx.doi.org/10.25673/116039 KW - Industry 4.0 KW - Capability description KW - Resource function KW - Product description KW - Automation engineering Y1 - 2024 UR - http://dx.doi.org/10.25673/116039 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-48431 PB - Institut für Automation und Kommunikation CY - Magdeburg ER - TY - CHAP A1 - Bock, Jürgen A1 - Klausmann, Tobias A1 - Kleinert, Tobias A1 - Köcher, Aljosha A1 - Simon, Marco A1 - Winter, Michael ED - Facchinetti, Tullio ED - Cenedese, Angelo ED - Lo Bello, Lucia ED - Vitturi, Stefano ED - Sauter, Thilo ED - Tramarin, Federico T1 - A Formal Approach to Defining Effects of Manufacturing Functions T2 - 2024 IEEE 29th International Conference on Emerging Technologies and Factory Automation (ETFA) UR - https://doi.org/10.1109/etfa61755.2024.10710847 Y1 - 2024 UR - https://doi.org/10.1109/etfa61755.2024.10710847 SN - 979-8-3503-6123-0 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Steffel, Pauline A1 - Bock, Jürgen A1 - Schiendorfer, Alexander ED - Almeida, Luis ED - Indria, Marina ED - de Sousa, Mario ED - Visioli, Antonio ED - Ashjaei, Mohammad ED - Santos, Pedro T1 - Towards a Configurable and Reusable RL Training Infrastructure for AMRs in ROS2 T2 - 2025 IEEE 30th International Conference on Emerging Technologies and Factory Automation (ETFA) UR - https://doi.org/10.1109/ETFA65518.2025.11205702 Y1 - 2025 UR - https://doi.org/10.1109/ETFA65518.2025.11205702 SN - 979-8-3315-5383-8 PB - IEEE CY - Piscataway ER - TY - JOUR A1 - Piendl, Daniel A1 - Radtke, Maximilian-Peter A1 - Jacobsen, Hendrik A1 - Bock, Jürgen A1 - Zaeh, Michael T1 - Predictive Maintenance of Ball Screws: A Comparative Study Using Real-World Industrial Data JF - Procedia CIRP N2 - Ball screws are widely used in machine tool feed drives. With increasing degradation of the ball screws, machining accuracy and economic efficiency decrease. Past investigations have shown that condition monitoring models can predict this degradation. However, these models are typically trained and evaluated using datasets derived from test benches, questioning their applicability to real machine tools. In this article, a comparative evaluation of a selection of these condition monitoring models using an industrial dataset is described. This dataset consists of measurement data from a total of nine ball screws used in three machine tools until failure. It was shown that when using data of multiple ball screws or machines, artificial neural networks or automated machine learning methods achieve a higher accuracy than statistical methods. However, for smaller datasets, statistical methods perform almost as well. The results provide an insight into the industrial applicability of the evaluated condition monitoring models. UR - https://doi.org/10.1016/j.procir.2025.02.135 Y1 - 2025 UR - https://doi.org/10.1016/j.procir.2025.02.135 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-61629 SN - 2212-8271 VL - 2025 IS - 134 SP - 390 EP - 395 PB - Elsevier CY - Amsterdam ER - TY - JOUR A1 - Köcher, Aljosha A1 - Belyaev, Alexander A1 - Hermann, Jesko A1 - Bock, Jürgen A1 - Meixner, Kristof A1 - Volkmann, Magnus A1 - Winter, Michael A1 - Zimmermann, Patrick A1 - Grimm, Stephan A1 - Diedrich, Christian T1 - A reference model for common understanding of capabilities and skills in manufacturing JF - at - Automatisierungstechnik N2 - In manufacturing, many use cases of Industrie 4.0 require vendor-neutral and machine-interpretable information models to describe, implement and execute resource functions. Such models have been researched under the terms capabilities and skills. Standardization of such models is required, but currently not available. This paper presents a reference model developed jointly by members of various organizations in a working group of the Plattform Industrie 4.0. This model covers definitions of most important aspects of capabilities and skills. It can be seen as a basis for further standardization efforts. N2 - Für viele Anwendungsfälle von Industrie 4.0 werden herstellerneutrale und maschinenlesbare Informationsmodelle von Capabilities und Skills benötigt. In der Praxis sind standardisierte Modelle erforderlich, welche zur Zeit jedoch nicht existieren. In diesem Beitrag wird ein Referenzmodell vorgestellt, das von Mitgliedern verschiedener Organisationen in einer Arbeitsgruppe der Plattform Industrie 4.0 erarbeitet wurde. Dieses Modell umfasst Definitionen der wichtigsten Aspekte von Capabilities und Skills und kann somit als wichtige Grundlage für weitere Standardisierungsarbeiten angesehen werden. T2 - Ein Referenzmodell für ein gemeinsames Verständnis von Capabilities und Skills von Anlagen UR - https://doi.org/10.1515/auto-2022-0117 KW - capabilities KW - resource functions KW - services KW - skill KW - standardization KW - Capabilities KW - Maschinenfunktionen KW - Services KW - Skills KW - Standardisierung Y1 - 2023 UR - https://doi.org/10.1515/auto-2022-0117 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-30866 SN - 2196-677X SN - 0178-2312 VL - 71 IS - 2 SP - 94 EP - 104 PB - De Gruyter CY - Berlin ER - TY - CHAP A1 - Radtke, Maximilian-Peter A1 - Huber, Marco F. A1 - Bock, Jürgen ED - Kulkarni, Chetan S. ED - Roychoudhury, Indranil T1 - Increasing Robustness of Data-Driven Fault Diagnostics with Knowledge Graphs T2 - Proceedings of the Annual Conferenceof the PHM Society 2023 N2 - In the realm of prognostics and health management (PHM), it is common to possess not only process data but also domain knowledge, which, if integrated into data-driven algorithms, can aid in solving specific tasks. This paper explores the integration of knowledge graphs (KGs) into deep learning models to develop a more resilient approach capable of handling domain shifts, such as variations in machine operating conditions. We present and assess a KG-enhanced deep learning approach in a representative PHM use case, demonstrating its effectiveness by incorporating domain-invariant knowledge through the KG. Furthermore, we provide guidance for constructing a comprehensive hierarchical KG representation that preserves semantic information while facilitating numerical representation. The experimental results showcase the improved performance and domain shift robustness of the KG-enhanced approach in fault diagnostics. UR - https://doi.org/10.36001/phmconf.2023.v15i1.3552 Y1 - 2023 UR - https://doi.org/10.36001/phmconf.2023.v15i1.3552 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-43307 PB - PHM Society CY - Rochester ER - TY - CHAP A1 - Radtke, Maximilian-Peter A1 - Huber, Marco F. A1 - Bock, Jürgen ED - Facchinetti, Tullio ED - Cenedese, Angelo ED - Lo Bello, Lucia ED - Vitturi, Stefano ED - Sauter, Thilo ED - Tramarin, Federico T1 - Encoding Machine Phase Information into Heterogeneous Graphs for Adaptive Fault Diagnosis T2 - 2024 IEEE 29th International Conference on Emerging Technologies and Factory Automation (ETFA) UR - https://doi.org/10.1109/etfa61755.2024.10711048 Y1 - 2024 UR - https://doi.org/10.1109/etfa61755.2024.10711048 SN - 979-8-3503-6123-0 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Radtke, Maximilian-Peter A1 - Bock, Jürgen ED - Do, Phuc ED - Michau, Gabriel ED - Ezhilarasu, Cordelia T1 - Expert Knowledge Induced Logic Tensor Networks BT - A Bearing Fault Diagnosis Case Study T2 - Proceedings of the 7th European Conference of the Prognostics and Health Management Society 2022 N2 - In the recent past deep learning approaches have achieved some remarkable results in the area of fault diagnostics and anomaly detection. Nevertheless, these algorithms rely on large amounts of data, which is often not available, and produce outputs, which are hard to interpret. These deficiencies make real life applications difficult. Before the broad success of deep learning machine faults were often classified using domain expert knowledge based on experience and physical models. In comparison, these approaches only require small amounts of data and produce highly interpretable results. On the downside, however, they struggle to predict unexpected patterns hidden in data. Merging these two concepts promises to increase accuracy, robustness and interpretability of models. In this paper we present a hybrid approach to combine expert knowledge with deep learning and evaluate it on rolling element bearing fault detection. First, we create a knowledge base for fault classification derived from the expected physical attributes of different faults in the envelope spectrum of vibration signals. This knowledge is used to derive a similarity function for comparing input signals to expected faulty signals. Afterwards, the similarity measure is incorporated into different neural networks using a Logic Tensor Network (LTN). This enables logical reasoning in the loss function, in which we aim to mimic the decision process of an expert analyzing the input data. Further, we extend LTNs by weight schedules for axiom groups. We show that our approach outperforms the baseline models on two bearing fault data sets with different attributes and directly gives a better understanding of whether or not fault signals are influenced by other effects or behave as expected. UR - https://doi.org/10.36001/phme.2022.v7i1.3329 KW - Logic Tensor Networks KW - Hybrid AI KW - Expert Knowledge KW - Fault Diagnosis KW - Deep Learning KW - Bearing Y1 - 2022 UR - https://doi.org/10.36001/phme.2022.v7i1.3329 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-27803 SN - 978-1-936263-36-3 IS - 1 SP - 421 EP - 431 PB - PHM Society CY - State College ER -