Skip to content
Licensed Unlicensed Requires Authentication Published by De Gruyter (O) October 9, 2024

Vorgehen für die Entwicklung einer Architektur für menschzentrierte KI in der Fertigung

Procedure for the development of an architecture for human-centered AI in manufacturing
  • Manuel Belke

    Manuel Belke studied Mechanical Engineering (B. Sc.) and Automation Engineering (M. Sc.) at RWTH Aachen University. After graduating, he joined the Department for Automation and Control Engineering of the Chair for Machine Tools at the Laboratory for Machine Tools and Production Engineering WZL in 2020 as a research associate. His research interests include human-centered automation technologies and vision based robot control strategies.

    EMAIL logo
    , Hossein Omid Beiki

    Hossein Omid Beiki studied Mechanical Engineering (B. Sc. and M. Sc.) at RWTH Aachen University. After graduating, he joined the Department for Automation and Control Engineering of the Chair for Machine Tools at the Laboratory for Machine Tools and Production Engineering WZL in 2022 as a research associate. His research interests include autonomous visual quality inspection with robotics and AI.

    , Janis Ochel , Franziska Plum

    Franziska Plum studied Mechanical Engineering (B. Sc.) and Automation Engineering (M. Sc.) at RWTH Aachen University. After graduating, she joined the Department for Machine Data Analytics and NC-Technology Department of the Chair for Machine Tools at the Laboratory for Machine Tools and Production Engineering (WZL) in 2022 as a research associate. Her research interests include neural networks and thermo-elastic machine tool behavior.

    , Oliver Petrovic

    Oliver Petrovic, M. Sc. is head of the Department for Automation and Control of the Chair for Machine Tools at the Laboratory for Machine Tools and Production Engineering WZL of RWTH Aachen University. After completing his master's degree in Mechanical Engineering at RWTH Aachen University, he worked at WZL as a research associate from 2018 to 2022. His research focuses on AI-based instustrial robotics and human-robot interaction.

    and Christian Brecher

    Prof. Dr.-Ing. Christian Brecher is a full professor at RWTH Aachen University and has been head of the Chair for Machine Tools at the Laboratory for Machine Tools and Production Engineering WZL since 2004. He also is a member of the board of directors of the Fraunhofer Institute for Production Technology (IPT) in Aachen.

Zusammenfassung

Um eine hohe Qualität in Produktionsprozessen zu realisieren, ist die Expertise von Prozessexperten von entscheidender Bedeutung. Die Aufnahme und Formalisierung des Wissens erfordern die Entwicklung einer menschzentrierten künstlichen Intelligenz (KI) und insbesondere einer Architektur, die die Integration des Menschen während des gesamten Entwicklungsprozesses erlaubt. Es wird die Entwicklung einer Architektur für eine menschzentrierte KI beschrieben, die die Anforderungen verschiedener Fertigungsverfahren berücksichtigt und gleichzeitig die Anforderungen der in dem Entwicklungsprozess beteiligten Personen berücksichtigt.

Abstract

In order to achieve high quality in production processes, the expertise of process experts is of crucial importance. The acquisition and formalization of knowledge requires the development of a human-centric artificial intelligence (AI) and, in particular, an architecture that allows the integration of humans throughout the development process. The development of an architecture for a human-centered AI that considers the requirements of different manufacturing processes is described based on the requirements gathered from involved persons during the development process.


Korrespondenzautor: Manuel Belke, Laboratory for Machine Tools and Production Engineering (WZL) of RWTH Aachen University, Steinbachstraße 25, 52074 Aachen, Germany, E-mail: 

Über die Autoren

Manuel Belke

Manuel Belke studied Mechanical Engineering (B. Sc.) and Automation Engineering (M. Sc.) at RWTH Aachen University. After graduating, he joined the Department for Automation and Control Engineering of the Chair for Machine Tools at the Laboratory for Machine Tools and Production Engineering WZL in 2020 as a research associate. His research interests include human-centered automation technologies and vision based robot control strategies.

Hossein Omid Beiki

Hossein Omid Beiki studied Mechanical Engineering (B. Sc. and M. Sc.) at RWTH Aachen University. After graduating, he joined the Department for Automation and Control Engineering of the Chair for Machine Tools at the Laboratory for Machine Tools and Production Engineering WZL in 2022 as a research associate. His research interests include autonomous visual quality inspection with robotics and AI.

Franziska Plum

Franziska Plum studied Mechanical Engineering (B. Sc.) and Automation Engineering (M. Sc.) at RWTH Aachen University. After graduating, she joined the Department for Machine Data Analytics and NC-Technology Department of the Chair for Machine Tools at the Laboratory for Machine Tools and Production Engineering (WZL) in 2022 as a research associate. Her research interests include neural networks and thermo-elastic machine tool behavior.

Oliver Petrovic

Oliver Petrovic, M. Sc. is head of the Department for Automation and Control of the Chair for Machine Tools at the Laboratory for Machine Tools and Production Engineering WZL of RWTH Aachen University. After completing his master's degree in Mechanical Engineering at RWTH Aachen University, he worked at WZL as a research associate from 2018 to 2022. His research focuses on AI-based instustrial robotics and human-robot interaction.

Christian Brecher

Prof. Dr.-Ing. Christian Brecher is a full professor at RWTH Aachen University and has been head of the Chair for Machine Tools at the Laboratory for Machine Tools and Production Engineering WZL since 2004. He also is a member of the board of directors of the Fraunhofer Institute for Production Technology (IPT) in Aachen.

  1. Research ethics: Not applicable.

  2. Author contributions: All authors have accepted responsibility for the entire content of this manuscript and approved its submission.

  3. Use of Large Language Models, AI and Machine Learning Tools: None declared.

  4. Conflict of interest: The authors state no conflict of interest.

  5. Research funding: Dieser Beitrag wird im Rahmen des Forschungs- und Entwicklungsprojekts „Generalisierung Menschzentrierter KI-Applikationen für die Produktionsoptimierung (GeMeKI)“ durch das Bundesministerium für Bildung und Forschung (BMBF) im Programm „Zukunft der Wertschöpfung – Forschung zu Produktion, Dienstleistung und Arbeit“ (Förderkennzeichen 02P20A121) gefördert und vom Projektträger Karlsruhe (PTKA) betreut.

  6. Data availability: The datasets generated and/or analyzed during the current study are available from the corresponding author on reasonable request.

Literaturverzeichnis

[1] C. Brecher, O. Petrovic, Y. Dassen, P. Blanke, M. Trinh, and S. Wurm, “Nachhaltige produktion-as-a-service,” in Empower Green Production Tagungsband, Aachen, 2023.Search in Google Scholar

[2] G. Brune, “Mehr Qualität, geringere Kosten, höhere Effizienz. KI in der Produktion von Nahrungsmitteln,” in Künstliche Intelligenz heute: Anwendungen aus wirtschaft, medizin und wissenschaft, G. Brune, Ed., Wiesbaden, [S.l.]: Springer Vieweg, 2023, pp. 29–40.10.1007/978-3-658-38994-9_4Search in Google Scholar

[3] R. H. Schmitt, D. Buschmann, K. Briele, P. Schlegel, and M. Ellerich, “Nachhaltige Produktion durch Predictive Quality und Sustainability Analytics entlang der Lieferkette,” in Monetarisierung von technischen Daten: Innovationen aus Industrie und Forschung, D. Trauth, T. Bergs, and W. Prinz, Eds., Heidelberg, [S.l.]: Morgan Kaufmann, 2021, pp. 521–536.10.1007/978-3-662-62915-4_26Search in Google Scholar

[4] O. Petrovic, et al.., “Hybride Intelligenz – Mensch und KI im Zusammenspiel/Development and introduction of production processes with AI assistance system – Hybrid intelligence: Human and AI in cooperation,” wt, vol. 112, no. 05, pp. 330–335, 2022, https://doi.org/10.37544/1436-4980-2022-05-60.Search in Google Scholar

[5] B. Pokorni, M. Braun, and C. Knecht, “Menschzentrierte KI-Anwendungen in der Produktion,” in World Usability Day, W. Bauer, O. Riedel, T. Renner, and M. Peissner, Eds., Fraunhofer IAO, 2021. Available at: https://publica.fraunhofer.de/handle/publica/300817.Search in Google Scholar

[6] M. Schindler, “Demokratisierung Künstlicher Intelligenz bei der BMW Group: Selbstservice für KI-basierte Computer Vision,” in Künstliche Intelligenz erfolgreich umsetzen, U. Lichtenthaler, Ed., Wiesbaden, Springer Fachmedien Wiesbaden, 2021, pp. 149–170.10.1007/978-3-658-34670-6_9Search in Google Scholar

[7] Cognilytica, “AI data engineering lifecycle checklist: Following steps for AI project success,” 2020. [Online] https://www.cloudera.com/content/dam/www/marketing/resources/whitepapers/ai-data-lifecycle-checklist-cloudera-whitepaper.pdf?daqp=true%20 [Accessed: Sep. 27, 2023].Search in Google Scholar

[8] C. Brecher, M. Belke, M. Trinh, L. Gründel, and O. Petrovic, “Industrielle Datenprozesse für KI-Technologien: Handlungsempfehlungen am Beispiel von Robotik-Applikationen,” in Industrie 4.0 Management, Berlin, GITO Verlag, 2021, pp. 37–41.Search in Google Scholar

[9] A. Blum, et al.., “Ganzheitlicher Ablaufplan für wissensgetriebene Projekte des maschinellen Lernens in der Produktion,” tm - Technisches Messen, vol. 89, no. 5, pp. 363–383, 2022, https://doi.org/10.1515/teme-2022-0027.Search in Google Scholar

[10] D. Ping, The Machine Learning Solutions Architect Handbook: Create Machine Learning Platforms to Run Solutions in an Enterprise Setting, Birmingham, Packt Publishing, 2022.Search in Google Scholar

[11] J. Yan, Y. Meng, L. Lu, and L. Li, “Industrial big data in an industry 4.0 environment: Challenges, schemes, and applications for predictive maintenance,” IEEE Access, vol. 5, pp. 23484–23491, 2017, https://doi.org/10.1109/ACCESS.2017.2765544.Search in Google Scholar

[12] H. S. Obaid, S. A. Dheyab, and S. S. Sabry, “The impact of data pre-processing techniques and dimensionality reduction on the accuracy of machine learning,” in 2019 9th Annual Information Technology, Electromechanical Engineering and Microelectronics Conference (IEMECON), Jaipur, India, 2019, pp. 279–283.10.1109/IEMECONX.2019.8877011Search in Google Scholar

[13] V. Shopov and V. Markova, “Impact of data preprocessing on machine learning performance,” in Proceedings of the International Conference on Information Technologies (InfoTech-2013), 2013. [Online]. Available at: https://www.researchgate.net/profile/ventseslav-shopov/publication/273131653_impact_of_data_preprocessing_on_machine_learning_performance/links/54f885f40cf2ccffe9df52e3/impact-of-data-preprocessing-on-machine-learning-performance.pdf.Search in Google Scholar

[14] K. K. Pal and K. S. Sudeep, “Preprocessing for image classification by convolutional neural networks,” in 2016 IEEE International Conference on Recent Trends in Electronics, Information & Communication Technology (RTEICT), Bangalore, India, 2016, pp. 1778–1781.10.1109/RTEICT.2016.7808140Search in Google Scholar

[15] S. Ayvaz and K. Alpay, “Predictive maintenance system for production lines in manufacturing: A machine learning approach using IoT data in real-time,” Expert Syst. Appl., vol. 173, p. 114598, 2021, https://doi.org/10.1016/j.eswa.2021.114598.Search in Google Scholar

[16] J. Dalzochio, et al.., “Machine learning and reasoning for predictive maintenance in Industry 4.0: Current status and challenges,” Comput. Ind., vol. 123, p. 103298, 2020, https://doi.org/10.1016/j.compind.2020.103298.Search in Google Scholar

[17] C. Yang, S. Lan, L. Wang, W. Shen, and G. G. Q. Huang, “Big data driven edge-cloud collaboration architecture for Cloud manufacturing: A software defined perspective,” IEEE Access, vol. 8, pp. 45938–45950, 2020, https://doi.org/10.1109/ACCESS.2020.2977846.Search in Google Scholar

[18] J. Ing, et al.., “Edge-cloud collaboration architecture for AI transformation of SME manufacturing enterprises,” in 2020 IEEE/ITU International Conference on Artificial Intelligence for Good (AI4G), Geneva, Switzerland, 2020, pp. 170–175.10.1109/AI4G50087.2020.9311075Search in Google Scholar

[19] V. Colla, C. Pietrosanti, E. Malfa, and K. Peters, “Environment 4.0: How digitalization and machine learning can improve the environmental footprint of the steel production processes,” Matériaux & Techniques, vol. 108, nos. 5–6, p. 507, 2020, https://doi.org/10.1051/mattech/2021007.Search in Google Scholar

[20] S. Fahle, C. Prinz, and B. Kuhlenkötter, “Systematic review on machine learning (ML) methods for manufacturing processes – identifying artificial intelligence (AI) methods for field application,” Procedia CIRP, vol. 93, pp. 413–418, 2020, https://doi.org/10.1016/j.procir.2020.04.109.Search in Google Scholar

[21] G. González Rodríguez, J. M. Gonzalez-Cava, and J. A. Méndez Pérez, “An intelligent decision support system for production planning based on machine learning,” J. Intell. Manuf., vol. 31, no. 5, pp. 1257–1273, 2020, https://doi.org/10.1007/s10845-019-01510-y.Search in Google Scholar

[22] Y. Zhang, A. Michi, J. Wagner, E. Andre, B. Schuller, and F. Weninger, “A generic human-machine annotation framework based on dynamic cooperative learning,” IEEE Trans. Cybern., vol. 50, no. 3, pp. 1230–1239, 2020, https://doi.org/10.1109/TCYB.2019.2901499.Search in Google Scholar PubMed

[23] X. Zhu, A. Singla, S. Zilles, and A. N. Rafferty, “An overview of machine teaching,” arXiv preprint arXiv:1801.05927, 2018.Search in Google Scholar

[24] A. Alsaid and J. D. Lee, “The DataScope: A mixed-initiative architecture for data labeling,” Proceedings of the Human Factors and Ergonomics Society Annual Meeting, vol. 66, no. 1, pp. 1559–1563, 2022.10.1177/1071181322661356Search in Google Scholar

[25] B. Boecking, W. Neiswanger, E. Xing, and A. Dubrawski, “Interactive weak supervision: Learning useful heuristics for data labeling,” 2020. [Online]. Available at: http://arxiv.org/pdf/2012.06046v2.Search in Google Scholar

[26] K. Siau and W. Wang, “Building trust in artificial intelligence, machine learning, and robotics,” Cutter Bus. Technol. J., vol. 31, no. 2, pp. 47–53, 2018.Search in Google Scholar

[27] N. Burkart and M. F. Huber, “A survey on the explainability of supervised machine learning,” Jair, vol. 70, pp. 245–317, 2021, https://doi.org/10.1613/jair.1.12228.Search in Google Scholar

[28] P. Damacharla, A. Y. Javaid, J. J. Gallimore, and V. K. Devabhaktuni, “Common metrics to benchmark human-machine teams (HMT): A review,” IEEE Access, vol. 6, pp. 38637–38655, 2018, https://doi.org/10.1109/ACCESS.2018.2853560.Search in Google Scholar

[29] C. Burns, “Human-centred design,” in Taylor & Francis eBooks, eHealth research, theory, development: A multi-disciplinary approach, L. van Gemert-Pijnen, R. Sanderman, S. M. Kelders, and H. Kip, Eds., London, Taylor and Francis, 2018, pp. 207–227.Search in Google Scholar

[30] J. Bokrantz, M. Subramaniyan, and A. Skoogh, “Realising the promises of artificial intelligence in manufacturing by enhancing CRISP-DM,” Prod. Plann. Control, pp. 1–21, 2023, https://doi.org/10.1080/09537287.2023.2234882.Search in Google Scholar

[31] C. Emmanouilidis and S. Waschull, “Human in the loop of AI systems in manufacturing,” in Becoming a Platform in Europe: On the Governance of the Collaborative Economy, J. Soldatos and D. Kyriazis, Eds., Las Vegas, Now Publishers, 2021.Search in Google Scholar

[32] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 779–788.10.1109/CVPR.2016.91Search in Google Scholar

[33] E. Coronado, T. Kiyokawa, G. A. Garcia Ricardez, I. G. Ramirez-Alpizar, G. Venture, and N. Yamanobe, “Evaluating quality in human-robot interaction: A systematic search and classification of performance and human-centered factors, measures and metrics towards an industry 5.0,” J. Manuf. Syst., vol. 63, pp. 392–410, 2022, https://doi.org/10.1016/j.jmsy.2022.04.007.Search in Google Scholar

[34] W. Xu, M. J. Dainoff, L. Ge, and Z. Gao, “Transitioning to human interaction with AI systems: New challenges and opportunities for HCI professionals to enable human-centered AI,” Int. J. Human–Comput. Interact., vol. 39, no. 3, pp. 494–518, 2023, https://doi.org/10.1080/10447318.2022.2041900.Search in Google Scholar

[35] C. Brecher, H.-M. Eckel, T. Motschke, M. Fey, and A. Epple, “Estimation of the virtual workpiece quality by the use of a spindle-integrated process force measurement,” CIRP Annals, vol. 68, no. 1, pp. 381–384, 2019, https://doi.org/10.1016/j.cirp.2019.04.020.Search in Google Scholar

[36] M. Königs and C. Brecher, “Process-parallel virtual quality evaluation for metal cutting in series production,” Procedia Manuf., vol. 26, pp. 1087–1093, 2018, https://doi.org/10.1016/j.promfg.2018.07.145.Search in Google Scholar

Erhalten: 2023-12-08
Angenommen: 2024-08-29
Online erschienen: 2024-10-09
Erschienen im Druck: 2024-10-28

© 2024 Walter de Gruyter GmbH, Berlin/Boston

Downloaded on 18.2.2025 from https://www.degruyter.com/document/doi/10.1515/auto-2023-0230/html
Scroll to top button