Managing uncertainty in product and process design for the circular factory
-
Michael Heizmann
,
Jürgen Beyerer
Abstract
In the circular factory, uncertain attributes of object instances and process steps are found at diverse occasions. Even if uncertainty can also be found to some extent in linear production, the high variation of product attributes of used objects causes the process steps in the circular factory to generate a much higher variability of the properties of the objects handled in circular processes. In consequence, a methodology is needed to model, handle and manage uncertainties at all relevant situations within the circular factory. In contrast to linear production, the uncertainty of attributes cannot be extended to an object class (with the same production history), but must be assigned to each object instance (with its own history) individually. In this contribution, the basic concepts for managing uncertainty in the circular factory are introduced. As a common basis, probabilities are used to express uncertainty, thus being compatible with the traditional and proven concepts of measurement science and stochastics. To describe the individual information state of object instances, it is complemented with a joint probability distribution describing all relevant object attributes. Some examples for processes within the circular factory demonstrate how uncertainty is considered to manage the uncertainty related challenges of used objects.
Zusammenfassung
In der Kreislauffabrik finden sich unsichere Eigenschaften von Objektinstanzen und Prozessschritten an verschiedenen Stellen. Auch wenn Unsicherheiten bis zu einem gewissen Grad auch in der linearen Produktion anzutreffen sind, führt die große Variation der Eigenschaften der gebrauchten Objekte während der Prozessschritte in der Kreislauffabrik zu einer viel größeren Variabilität der Eigenschaften der in Kreisprozessen betrachteten Objekte. Infolgedessen wird eine Methodik benötigt, um Unsicherheiten in allen relevanten Situationen innerhalb der Kreislauffabrik zu modellieren, zu handhaben und zu beherrschen. Im Gegensatz zur linearen Produktion kann die Unsicherheit von Eigenschaften nicht auf eine Objektklasse (mit gleicher Produktionshistorie) ausgedehnt werden, sondern muss jeder Objektinstanz (mit eigener Historie) individuell zugewiesen werden. In diesem Beitrag werden die grundlegenden Konzepte für die Beherrschung von Unsicherheiten in der Kreislauffabrik vorgestellt. Als gemeinsame Basis werden Wahrscheinlichkeiten verwendet, um Unsicherheit auszudrücken, was mit den traditionellen und bewährten Konzepten der Messtechnik und Stochastik kompatibel ist. Zur Beschreibung des individuellen Informationsstands bezüglich Objektinstanzen wird jede Instanz durch eine Verbund-Wahrscheinlichkeitsverteilung ergänzt, die alle relevanten Objekteigenschaften beschreibt. Einige Beispiele für Prozesse innerhalb der Kreislauffabrik zeigen, wie Unsicherheiten berücksichtigt werden, um die mit gebrauchten Objekten verbundenen Herausforderungen zu bewältigen.
About the authors
Michael Heizmann is Professor of Mechatronic Measurement Systems at the Institute of Industrial Information Technology at the Karlsruhe Institute of Technology. His research interests include measurement science, machine vision, signal and image processing, image and information fusion and their applications.
Prof. Dr.-Ing. Jürgen Beyerer has been a full professor for informatics at the Institute for Anthropomatics and Robotics at the Karlsruhe Institute of Technology KIT since March 2004 and director of the Fraunhofer Institute of Optronics, System Technologies and Image Exploitation IOSB in Ettlingen, Karlsruhe, Ilmenau, Görlitz, Lemgo, Oberkochen and Rostock. Research interests include automated visual inspection, signal and image processing, variable image acquisition and processing, active vision, metrology, information theory, fusion of data and information from heterogeneous sources, system theory, autonomous systems and automation. (Photocredits: Chiara Bellamoli).
Dr.-Ing. Stefan Dietrich is group leader of the group “Manufacturing and Component Behaviour” at the Institute for Applied Materials – Materials Engineering at the Karlsruhe Institute of Technology. His research areas include materials for additive manufacturing, heat treatment technologies, surface engineering and non-destructive evaluation and data fusion with their applications.
Luisa Hoffmann is a PhD student at the Institute for Industrial Information Technology at the Karlsruhe Institute of Technology, specializing in information fusion under the supervision of Professor Michael Heizmann.
Jan-Philipp Kaiser, M.Sc. is a research associate in the quality assurance group at the Institute of Production Science (wbk) at the Karlsruhe Institute of Technology (KIT). His research focuses on autonomous inspection systems using robot-guided measurement technology and artificial intelligence methods.
Prof. Dr.-Ing. Gisela Lanza is member of the management board at the Institute of Production Science (wbk) of the Karlsruhe Institute of Technology (KIT). She heads the Production Systems division dealing with the topics of global production strategies, production system planning, and quality assurance in research and industrial practice.
Alina Roitberg is a Tenure-Track Juniorprofessor at the University of Stuttgart, leading the Intelligent Sensing and Perception Group at the Institute for AI, University of Stuttgart. Her research interests include computer vision, human activity recognition, domain adaptation, open set recognition, as well as resource- and data-efficient learning.
Rainer Stiefelhagen is Professor for Computer Systems for Visually Impaired Students at the Institute of Anthropomatics and Robotics at the Karlsruhe Institute of Technology. His research interests include image and video understanding, multimodal interfaces, applications in medical image analysis, assistive technology for seeing impaired users, driver assistance, robotics and surveillance.
Nicole Stricker is Professor of Operations Management at Aalen University. Her research is focussing on the production planning and control of complex production systems including the consideration of uncertainties.
Helena Wexel, M.Sc. is a research associate in the group of Manufacturing and Material Technology at wbk Institute of Production Science at Karlsruhe Institute of Technology (KIT). Main research area: Additive manufacturing using directed energy deposition.
Prof. Dr.-Ing. Frederik Zanger is director of the research group Manufacturing and Material Technology at wbk Institute of Production Science at Karlsruhe Institute of Technology (KIT) and responsible for the area digitalization of process development for additive manufacturing.
-
Research ethics: Not applicable.
-
Author contributions: The authors have accepted responsibility for the entire content of this manuscript and approved its submission.
-
Competing interests: The authors state no conflict of interest.
-
Research funding: The project AgiProbot is funded by the Carl Zeiss Foundation and the work described therein served to prepare the SFB 1574 Circular Factory for the Perpetual Product (project ID: 471687386), which has since been approved by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) with a start date of April 1, 2024.
-
Data availability: Not applicable.
References
[1] ISO/IEC Guide 98-3:2008-09, Uncertainty of Measurement – Part 3: Guide to the Expression of Uncertainty in Measurement, Geneva, Switzerland, ISO/IEC, 2008.Search in Google Scholar
[2] M. Sewell, “Why probability?” 2023. Available at: http://www.stats.org.uk/why-probability/.Search in Google Scholar
[3] D. V. Lindley, “Scoring rules and the inevitability of probability,” Int. Stat. Rev., vol. 50, no. 1, pp. 1–26, 1982. https://doi.org/10.2307/1402448.Search in Google Scholar
[4] L. V. Lindley, “The probability approach to the treatment of uncertainty in artificial intelligence and expert systems,” Stat. Sci., vol. 2, no. 1, pp. 17–24, 1987. https://doi.org/10.1214/ss/1177013427.Search in Google Scholar
[5] T. Tolio, et al.., “Design, management and control of demanufacturing and remanufacturing systems,” CIRP Ann., vol. 66, no. 2, pp. 585–609, 2017. https://doi.org/10.1016/j.cirp.2017.05.001.Search in Google Scholar
[6] S. Mete, Z. A. Çil, E. Özceylan, K. Ağpak, and O. Battaïa, “An optimisation support for the design of hybrid production lines including assembly and disassembly tasks,” Int. J. Prod. Res., vol. 56, no. 24, pp. 7375–7389, 2018. https://doi.org/10.1080/00207543.2018.1428774.Search in Google Scholar
[7] E. Özceylan, C. B. Kalayci, A. Güngör, and S. M. Gupta, “Disassembly line balancing problem: a review of the state of the art and future directions,” Int. J. Prod. Res., vol. 57, nos. 15–16, pp. 4805–4827, 2019. https://doi.org/10.1080/00207543.2018.1428775.Search in Google Scholar
[8] F. T. Altekin and C. Akkan, “Task-failure-driven rebalancing of disassembly lines,” Int. J. Prod. Res., vol. 50, no. 18, pp. 4955–4976, 2012. https://doi.org/10.1080/00207543.2011.616915.Search in Google Scholar
[9] J. Pfrommer, D. Stogl, K. Aleksandrov, S. Escaida Navarro, B. Hein, and J. Beyerer, “Plug & produce by modelling skills and service-oriented orchestration of reconfigurable manufacturing systems,” at – Automatisierungstechnik, vol. 63, no. 10, pp. 790–800, 2015. https://doi.org/10.1515/auto-2014-1157.Search in Google Scholar
[10] M. C. May, S. Schmidt, A. Kuhnle, N. Stricker, and G. Lanza, “Product generation module: automated production planning for optimized workload and increased efficiency in matrix production systems,” Procedia CIRP, vol. 96, pp. 45–50, 2021. https://doi.org/10.1016/j.procir.2021.01.050.Search in Google Scholar
[11] S. Schindler, Strategische Planung von Technologieketten für die Produktion, Dissertation, Munich, 2014.Search in Google Scholar
[12] N. Stricker, A. Pfeiffer, E. Moser, B. Kádár, G. Lanza, and L. Monostori, “Supporting multi-level and robust production planning and execution,” CIRP Ann., vol. 64, no. 1, pp. 415–418, 2015. https://doi.org/10.1016/j.cirp.2015.04.115.Search in Google Scholar
[13] B. V. Dasarathy, “Information Fusion – what, where, why, when, and how?” Fusion, vol. 2, no. 2, pp. 75–76, 2001. https://doi.org/10.1016/s1566-2535(01)00032-x.Search in Google Scholar
[14] G. Koliander, Y. El-Laham, P. M. Djurić, and F. Hlawatsch, “Fusion of probability density functions,” Proc. IEEE, vol. 110, no. 4, pp. 404–453, 2022. https://doi.org/10.1109/jproc.2022.3154399.Search in Google Scholar
[15] N. Wu, The Maximum Entropy Method, Berlin, Springer, 1997.10.1007/978-3-642-60629-8Search in Google Scholar
[16] M. Huber, Nonlinear Gaussian Filtering Theory, Algorithms, and Applications, Karlsruhe, KIT Scientific Publishing, 2015.Search in Google Scholar
[17] W3C Provenance Working Group, “The PROV data model,” 2013. Available at: http://www.w3.org/TR/2013/prov-overview.Search in Google Scholar
[18] O. C. Schrempf, O. Feiermann, and U. D. Hanebeck, “Optimal mixture approximation of the product of mixtures,” in 2005 7th International Conference on Information Fusion, Philadelphia, PA, USA, 2005, pp. 85–92.10.1109/ICIF.2005.1591840Search in Google Scholar
[19] J. Pearl, “Bayesian networks: a model of self-activated memory for evidential reasoning,” in Proceedings of the 7th Conference of the Cognitive Science Society, 1985, pp. 329–334.Search in Google Scholar
[20] M. Errington and S. J. Childe, “A business process model of inspection in remanufacturing,” J. Remanufacturing, vol. 3, no. 7, pp. 1–22, 2013. https://doi.org/10.1186/2210-4690-3-7.Search in Google Scholar
[21] G. Cai and S. Mahadevan, “Uncertainty quantification of manufacturing process effects on macroscale material properties,” Int. J. Multiscale Comput. Eng., vol. 14, no. 3, pp. 191–213, 2016. https://doi.org/10.1615/intjmultcompeng.2016015552.Search in Google Scholar
[22] Z. Hu and S. Mahadevan, “Uncertainty quantification in prediction of material properties during additive manufacturing,” Scr. Mater., vol. 135, pp. 135–140, 2017. https://doi.org/10.1016/j.scriptamat.2016.10.014.Search in Google Scholar
[23] H. Zhang, S. Liu, H. Lu, Y. Zhang, and Y. Hu, “Remanufacturing and remaining useful life assessment,” in Handbook of Manufacturing Engineering and Technology, 2015, pp. 3137–3193.10.1007/978-1-4471-4670-4_112Search in Google Scholar
[24] X. Zhang, W. Cui, W. Li, and F. Liou, “A hybrid process integrating reverse engineering, pre-repair processing, additive manufacturing, and material testing for component remanufacturing,” Materials, vol. 12, no. 12, p. 1961, 2019. https://doi.org/10.3390/ma12121961.Search in Google Scholar PubMed PubMed Central
[25] J.-P. Wu, R. Kang, and X.-Y. Li, “Uncertain accelerated degradation modeling and analysis considering epistemic uncertainties in time and unit dimension,” Reliab. Eng. Syst. Saf., vol. 201, no. C, 2020, Art. no. 106967. https://doi.org/10.1016/j.ress.2020.106967.Search in Google Scholar
[26] ANSYS, Inc. Ansys GRANTA EduPack Software, Cambridge, UK, ANSYS, Inc., 2023. Available at: www.ansys.com/materials.Search in Google Scholar
[27] Z. Wang, et al.., “Uncertainty quantification and reduction in metal additive manufacturing,” NPJ Comput. Mater., vol. 6, no. 1, p. 175, 2020. https://doi.org/10.1038/s41524-020-00444-x.Search in Google Scholar
[28] S. Mahadevan, P. Nath, and Z. Hu, “Uncertainty quantification for additive manufacturing process improvement: recent advances,” ASCE ASME J. Risk Uncertain. Eng. Syst. B Mech. Eng., vol. 8, no. 1, 2022, Art. no. 010801. https://doi.org/10.1115/1.4053184.Search in Google Scholar
[29] V. Lubkowitz, P. Fischmann, V. Schulze, and F. Zanger, “Influence of initial powder layer thickness and focus deviation on the properties of hybrid manufactured parts by Laser Powder Bed Fusion,” Procedia CIRP, vol. 111, pp. 87–91, 2022. https://doi.org/10.1016/j.procir.2022.08.136.Search in Google Scholar
[30] E. Segebade, M. Gerstenmeyer, S. Dietrich, F. Zanger, and V. Schulze, “Influence of anisotropy of additively manufactured AlSi10Mg parts on chip formation during orthogonal cutting,” Procedia CIRP, vol. 82, pp. 113–118, 2019. https://doi.org/10.1016/j.procir.2019.04.043.Search in Google Scholar
[31] Z. Hu and S. Mahadevan, “Uncertainty quantification and management in additive manufacturing: current status, needs, and opportunities,” Int. J. Adv. Des. Manuf. Technol., vol. 93, pp. 2855–2874, 2017. https://doi.org/10.1007/s00170-017-0703-5.Search in Google Scholar
[32] A. Panda, A. K. Sahoo, R. Kumar, and D. Das, “A concise review of uncertainty analysis in metal machining,” Mater. Today: Proc., vol. 26, no. 2, pp. 1734–1739, 2020. https://doi.org/10.1016/j.matpr.2020.02.365.Search in Google Scholar
[33] Q. Ren, L. Baron, and M. Balazinski, “Application of type-2 fuzzy estimation on uncertainty in machining: an approach on acoustic emission during turning process,” in NAFIPS 2009-2009 Annual Meeting of the North American Fuzzy Information Processing Society, IEEE, 2019, pp. 1–6.10.1109/NAFIPS.2009.5156421Search in Google Scholar
[34] Q. Liu, M. Janardhana, B. Hinton, M. Brandt, and K. Sharp, “Laser cladding as a potential repair technology for damaged aircraft components,” Int. J. Struct. Integr., vol. 2, no. 3, pp. 314–331, 2011. https://doi.org/10.1108/17579861111162914.Search in Google Scholar
[35] S. Kramer, K. Drechsel, M. Jarwitz, V. Schulze, and F. Zanger, “Potential of contactless support structures for improving the part quality of AlSi10Mg PBF-LB parts,” in Fraunhofer Direct Digital Manufacturing Conference, 2023.Search in Google Scholar
[36] D. Gauder, M. Biehler, J. Goelz, V. Schulze, and G. Lanza, “In-process acoustic pore detection in milling using deep learning,” CIRP J. Manuf. Sci. Technol., vol. 37, pp. 125–133, 2022. https://doi.org/10.1016/j.cirpj.2022.01.008.Search in Google Scholar
[37] D. Hendrycks and K. Gimpel, “A baseline for detecting misclassified and out-of-distribution examples in neural networks,” in Proceedings of International Conference on Learning Representations (ICLR), 2016.Search in Google Scholar
[38] A. Nguyen, J. Yosinski, and J. Clune, “Deep neural networks are easily fooled: high confidence predictions for unrecognizable images,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 427–436.10.1109/CVPR.2015.7298640Search in Google Scholar
[39] C. Guo, G. Pleiss, Y. Sun, and K. Q. Weinberger, “On calibration of modern neural networks,” in Proceedings of the 34th International Conference on Machine Learning, vol. 70, 2017, pp. 1321–1330.10.1109/WACV.2018.00149Search in Google Scholar
[40] A. Roitberg, et al.., “Is my driver observation model overconfident? Input-guided calibration networks for reliable and interpretable confidence estimates,” IEEE Trans. Intell. Transp. Syst., vol. 23, no. 12, pp. 25271–25286, 2022. https://doi.org/10.1109/tits.2022.3196410.Search in Google Scholar
[41] A. Kendall and Y. Gal, “What uncertainties do we need in Bayesian deep learning for computer vision?” in Advances in Neural Information Processing Systems, 2017, pp. 5580–5590.Search in Google Scholar
[42] Y. Gal and Z. Ghahramani, “Dropout as a Bayesian approximation: representing model uncertainty in deep learning,” in International Conference on Machine Learning, 2016, pp. 1050–1059.Search in Google Scholar
[43] B. Lakshminarayanan, A. Pritzel, and C. Blundell, “Simple and scalable predictive uncertainty estimation using deep ensembles,” in Advances in Neural Information Processing Systems, 2017, pp. 6402–6413.Search in Google Scholar
© 2024 Walter de Gruyter GmbH, Berlin/Boston
Articles in the same Issue
- Frontmatter
- Editorial
- Perpetual innovative products from circular factories for sustainable production
- Survey
- The vision of the circular factory for the perpetual innovative product
- Long living human-machine systems in construction and production enabled by digital twins
- Methods
- Enabling the vision of a perpetual innovative product – predicting function fulfillment of new product generations in a circular factory
- Managing uncertainty in product and process design for the circular factory
- Learning human actions from complex manipulation tasks and their transfer to robots in the circular factory
- Self-learning and autonomously adapting manufacturing equipment for the circular factory
- The role of an ontology-based knowledge backbone in a circular factory
- Analysis and evaluation of adaptive remanufacturing strategies for mechanical products
Articles in the same Issue
- Frontmatter
- Editorial
- Perpetual innovative products from circular factories for sustainable production
- Survey
- The vision of the circular factory for the perpetual innovative product
- Long living human-machine systems in construction and production enabled by digital twins
- Methods
- Enabling the vision of a perpetual innovative product – predicting function fulfillment of new product generations in a circular factory
- Managing uncertainty in product and process design for the circular factory
- Learning human actions from complex manipulation tasks and their transfer to robots in the circular factory
- Self-learning and autonomously adapting manufacturing equipment for the circular factory
- The role of an ontology-based knowledge backbone in a circular factory
- Analysis and evaluation of adaptive remanufacturing strategies for mechanical products
