Abstract
Integration of Artificial Intelligence (AI) methods into industrial systems engineering processes is challenging. Despite an increasing body of knowledge on AI techniques and impressive state-of-the-art reports, the application of AI in industrial contexts is only at an early stage. This paper summarizes challenges for AI Systems Engineering. Two examples of AI systems engineering are provided: the TRUMPF Sorting Guide and ABB BatchInsight. Summaries of the projects give insights into the project executions and related challenges. The learnings from these projects also show that increased maturity of AI systems engineering can be expected from increased method competence and adjusted project setups. Here guidelines and best practices for AI systems engineering can support.
Zusammenfassung
Die Integration von Methoden der Künstlichen Intelligenz (KI) in die Prozesse des Systems engineering ist eine Herausforderung. Trotz des zunehmenden Wissens über KI-Techniken und eines beeindruckenden State-of-the-Art steht die Anwendung von KI im industriellen Kontext erst in einem frühen Stadium. Dieser Beitrag fasst die Herausforderungen für KI Systems engineering zusammen. Dabei werden zwei Beispiele für KI Systems engineering vorgestellt: der TRUMPF Sorting Guide und ABB BatchInsight. Zusammenfassungen der Projekte geben Einblicke in die Projektdurchführung und die damit verbundenen Herausforderungen. Die Projekte zeigen auch, dass ein höherer Reifegrad von KI Systems engineering durch erhöhte Methodenkompetenz und dem Thema angemessene Projektstrukturen zu erwarten ist. Hier können Richtlinien und Best Practices für KI Systems Engineering unterstützen.
About the authors
Dipl. Ing. (FH) Ingo Sawilla currently works in the role of Coordinator for Data Governance, Data-/Information Security and Data Protection Manager for TRUMPF Werkzeugmaschinen SE + Co. KG, Ditzingen, Germany.
Dr.-Ing. Christian Weber is a Data Engineer in the AI Team in the Research and Development Department of TRUMPF Werkzeugmaschinen SE + Co. KG, Ditzingen, Germany, and holds a PhD in Computer Science from the University of Stuttgart. He has published numerous papers in the field of data management for machine learning and its support by software platforms.
Dr. Benedikt Schmidt works as Principal Scientist at the ABB Corporate Research Center Germany. His focus is industrial data analytics, covering software infrastructures for industrial data analytics and artificial intelligence, especially machine learning. He studied computer science at the University of Paderborn. After his studies, he worked as a research assistant at SAP’s research center and completed his doctorate at the Technical University of Darmstadt.
Dr. Marco Ulrich heads the “Software Technologies” department at the ABB Corporate Research Center Germany which is focusing on industrial digitalization. Research fields span from IoT and connectivity to software architectures and cloud computing up to artificial intelligence and data analytics. He studied Physics at the Karlsruhe Institute of Technology (KIT) and the University of Uppsala (Sweden) and holds a doctoral degree in Physics from University of Heidelberg and the German Cancer Research Center (DKFZ).
References
1. Ahmed, U., D. Ha, S. Shin, N. Shaukat, U. Zahid and C. Han. 2017. Estimation of disturbance propagation path using principal component analysis (PCA) and multivariate granger causality (MVGC) techniques. Industrial & Engineering Chemistry Research 56(25): 7260–7272.10.1021/acs.iecr.6b02763Search in Google Scholar
2. Anderson, N., W. Diab, T. French, K. Harper, S. Lin, D. Nair and W. Sobel. 2017. The industrial Internet of things volume T3: Analytics framework. Industrial Internet Consortium Report.Search in Google Scholar
3. Arunthavanathan, R., F. Khan, S. Ahmed, S. Imtiaz and R. Rusli 2020. Fault detection and diagnosis in process system using artificial intelligence-based cognitive technique. Computers & Chemical Engineering 134: 106697. https://doi.org/10.1016/j.compchemeng.2019.106697.10.1016/j.compchemeng.2019.106697Search in Google Scholar
4. Deng, L. 2018. Artificial intelligence in the rising wave of deep learning: The historical path and future outlook [perspectives]. IEEE Signal Processing Magazine 35(1): 180–177.10.1109/MSP.2017.2762725Search in Google Scholar
5. Došilović, F. K., M. Brčić and N. Hlupić. 2018. Explainable artificial intelligence: A survey. 2018 41st International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO). IEEE, pp. 0210–0215.10.23919/MIPRO.2018.8400040Search in Google Scholar
6. Hankel, M. and B. Rexroth. 2015. Das referenzarchitekturmodell industrie 4.0 (RAMI 4.0). ZVEI – Zentralverband Elektrotechnik- und Elektronikindustrie e.V., Fachverband Automation, Frankfurt.Search in Google Scholar
7. Hasterok, C., J. Stompe, J. Pfrommer, T. Usländer, J. Ziehn, S. Reiter, M. Weber and T. Riedel. 2021. PAISE – Process model for AI systems engineering. CC-King. Kompetenzzentrum KI-Engineering.Search in Google Scholar
8. Hoffmann, M. W., R. Drath and C. Ganz. 2021. Proposal for requirements on industrial AI solutions. In: Machine learning for cyber physical systems. Springer Vieweg, Berlin, Heidelberg, pp. 63–72.10.1007/978-3-662-62746-4_7Search in Google Scholar
9. Kagermann, H. and W. Henning. 2021. Zehn Jahre Industrie 4.0. Frankfurter Allgemeine Zeitung, 29.03.2021. Available from: https://www.dfki.de/web/news/zehn-jahre-industrie-4-0/.Search in Google Scholar
10. Kleinemeier, M. 2014. Von der Automatisierungspyramide zu Unternehmenssteuerungsnetzwerken. In: Industrie 4.0 in Produktion, Automatisierung und Logistik. Springer, pp. 571–579.10.1007/978-3-658-04682-8_29Search in Google Scholar
11. Kosanovich, K., M. Piovoso, K. Dahl, J. MacGregor and P. Nomikos 1994. Multi-way PCA applied to an industrial batch process. In: Proceedings of 1994 American Control Conference-Acc’94, Vol. 2. IEEE, pp. 1294–1298.10.1109/ACC.1994.752268Search in Google Scholar
12. Leitner, S.-H. and W. Mahnke. 2006. OPC UA – service-oriented architecture for industrial applications. Softwaretechnik-Trends 26.Search in Google Scholar
13. Mäkinen, S., H. Skogström, E. Laaksonen and T. Mikkonen. 2021. Who needs MLOps: What data scientists seek to accomplish and how can MLOps help? ArXiv preprint arXiv:2103.08942.10.1109/WAIN52551.2021.00024Search in Google Scholar
14. McDermott, T. A., M. R. Blackburn and P. A. Beling. 2021. Artificial intelligence and future of systems engineering. In: Systems engineering and artificial intelligence. Springer, pp. 47–59.10.1007/978-3-030-77283-3_3Search in Google Scholar
15. Plattform Industrie 4.0. 2021. Technology Scenario “Artificial Intelligence in Industrie 4.0.” Federal Ministry for Economic Affairs and Energy (BMWi).Search in Google Scholar
16. Sculley, D., G. Holt, D. Golovin, E. Davydov, T. Phillips, D. Ebner, V. Chaudhary, M. Young, J.-F. Crespo and D. Dennison. 2015. Hidden technical debt in machine learning systems. Advances in Neural Information Processing Systems 28: 2503–2511.Search in Google Scholar
17. Sundararajan, M., A. Taly and Q. Yan. 2017. Axiomatic attribution for deep networks. In: International Conference on Machine Learning. JMLR.org, pp. 3319–3328.Search in Google Scholar
18. Torrey, L. and J. Shavlik. 2010. Transfer learning. In: Handbook of research on machine learning applications and trends: Algorithms, methods, and techniques. IGI global, pp. 242–264.10.4018/978-1-60566-766-9.ch011Search in Google Scholar
19. Vanschoren, J. 2018. Meta-Learning: A Survey. ArXiv preprint arXiv:1810.03548.Search in Google Scholar
© 2022 Walter de Gruyter GmbH, Berlin/Boston