Meets Expectations: System Health Analysis and Prognosis for Embedded and Cyber-physical AI
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
https://orcid.org/0000-0002-9132-8532
Christian Tiemann Leonardo Barbini
Abstract
The health management of AI-based systems differs strongly from that of traditional systems, forcing a rethinking and partial reinvention of established techniques: The AI inside provides the capacity to adapt to an operational context – and that leads to a variability in system behaviors that renders conventional health and performance indicators possibly obsolete. Also, even core AI functionality, like perception, can hardly be assessed without complicated reasoning about whether a lack of performance is circumstantial or an actual system health issue. For these reasons, we introduce a system health monitoring methodology that checks health and key performance indicators against expectations while factoring in mitigating circumstances, like environmental effects.
This methodology, which is based on probabilistic reasoning, allows the detection of system health degradation and root-cause analytics and is used by us to ensure the operational fitness of safety-critical systems, i.e., Automated Vehicles. As this domain is subject to temporal changes like seasons that impact a system’s performance more than many developing health issues, we combine health monitors with domain monitors and drift detection. Overall, this provides probabilistic health management that looks at expectations, sets of observations, their distributions and their dynamics to determine whether an embedded AI is still fit for its purpose, whether the cyber-physical system embodying it continues to meet the AI’s operational requirements, and whether observations indicate a health or fitness trend that will result in a lack of safety. A key aspect of this novel approach to reasoning about system health is that it addresses unique properties of AI-based systems: It works with the hit-or-miss behavior of AI that occasionally fails even on seemingly comparable inputs, and it can investigate adaptive processes by looking at the health of information flows that define the decision-making of AI-based systems.
How to Cite
##plugins.themes.bootstrap3.article.details##
Cyber-physical AI, Embedded AI, System Health, Health Monitoring, Probabilistic Health Analytics, Drift Detection
Japan Automobile Manufacturers Association. (2022). Automated driving safety evaluation framework. Retrieved from https://www.jama.or.jp/english/reports/framework.html
Borth, M., & Barbini, L. (2019). Probabilistic health and mission readiness assessment at system-level. Proceedings of the Annual Conference of the PHM Society, 11(1). doi: https://doi.org/10.36001/phmconf.2019.v11i1.777
Borth, M., De Oliveira Filho, J., & van der Ploeg, C. (2024). Fitness assessment of AI-based systems. In Prognostics and System Health Management Conference (PHM) (pp. 235–240). doi: https://doi.org/10.1109/PHM61473.2024.00050
Borth, M., & van Gerwen, E. (2019). Tracking dynamics in concurrent digital twins. In D. Bonjour, D. Krob, F. Palladino, & F. Stephan (Eds.), Complex Systems Design & Management. Springer International Publishing. doi: https://doi.org/10.1007/978-3-030-04209-7_6
Borth, M., & von Hasseln, H. (2002). Systematic generation of Bayesian networks from systems specifications. In M. Musen, B. Neumann, & R. Studer (Eds.), Intelligent Information Processing (Vol. 93). IFIP Advances in Information and Communication Technology. Springer. doi: https://doi.org/10.1007/978-0-387-35602-0_14
Cabon, Y., Murray, N., & Humenberger, M. (2020). Virtual KITTI 2. arXiv. doi: https://doi.org/10.48550/arXiv.2001.10773
Dosovitskiy, A., Ros, G., Codevilla, F., Lopez, A., & Koltun, V. (2017). CARLA: An open urban driving simulator. In Proceedings of the 1st Annual Conference on Robot Learning (pp. 1–16). Retrieved from https://proceedings.mlr.press/v78/dosovitskiy17a.html
Eykholt, K., Evtimov, I., Fernandes, E., et al. (2018). Robust physical-world attacks on deep learning visual classification. In 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 1625–1634). doi: https://doi.org/10.1109/CVPR.2018.00175
Gaidon, A., Wang, Q., Cabon, Y., & Vig, E. (2016). Virtual worlds as proxy for multi-object tracking analysis. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 4340–4349). doi: https://doi.org/10.1109/CVPR.2016.470
van Gerwen, E., Barbini, L., Borth, M., & Passmann, R. (2024). Efficient differential diagnosis using cost-aware active testing. International Journal of Prognostics and Health Management, 15(3). doi: https://doi.org/10.36001/ijphm.2024.v15i3.3849
Hostens, E., Eryilmaz, K., Vangilbergen, M., & Ooijevaar, T. (2024). Bayesian networks for remaining useful life prediction. PHM Society European Conference, 8(1), 1. doi: https://doi.org/10.36001/phme.2024.v8i1.4019
Marcus, G. F., & Davis, E. (2019). Rebooting AI: Building artificial intelligence we can trust (1st ed.). Pantheon Books.
Almazrouei, S. M., Dweiri, F., Aydin, R., & Alnaqbi, A. (2023). A review on the advancements and challenges of artificial intelligence-based models for predictive maintenance of water injection pumps in the oil and gas industry. SN Applied Sciences, 5(12), 391. doi: https://doi.org/10.1007/s42452-023-05618-y
Paardekooper, J.-P., & Borth, M. (2024). Toward a methodology for the verification and validation of AI-based systems. SAE International Journal of Connected and Automated Vehicles, 8(1). doi: https://doi.org/10.4271/12-08-01-0006
Pearl, J. (1988). Probabilistic reasoning in intelligent systems: Networks of plausible inference. Morgan Kaufmann.
Pearl, J. (2009). Causality: Models, reasoning, and inference (2nd ed.). Cambridge University Press. doi: https://doi.org/10.1017/CBO9780511803161
Pfeffer, A. (2016). Practical probabilistic programming. Simon and Schuster.
Pileggi, P., Lazovik, E., Broekhuijsen, J., Borth, M., & Verriet, J. (2020). Lifecycle governance for effective digital twins: A joint systems engineering and IT perspective. In IEEE International Systems Conference (SysCon). doi: 10.1109/SysCon47679.2020.9275662
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You only look once: Unified, real-time object detection. arXiv. doi: https://doi.org/10.48550/arXiv.1506.02640
Ricks, B. W., & Mengshoel, O. J. (2009). Methods for probabilistic fault diagnosis: An electrical power system case study. Annual Conference of the PHM Society, 1(1). Retrieved from https://papers.phmsociety.org/index.php/phmconf/article/view/1594
Weisberg, D. S., & Gopnik, A. (2013). Pretense, counterfactuals, and Bayesian causal models: Why what is not real really matters. Cognitive Science, 37(7), 1368–1381. doi: https://doi.org/10.1111/cogs.12069
This work is licensed under a Creative Commons Attribution 3.0 Unported License.
The Prognostic and Health Management Society advocates open-access to scientific data and uses a Creative Commons license for publishing and distributing any papers. A Creative Commons license does not relinquish the author’s copyright; rather it allows them to share some of their rights with any member of the public under certain conditions whilst enjoying full legal protection. By submitting an article to the International Conference of the Prognostics and Health Management Society, the authors agree to be bound by the associated terms and conditions including the following:
As the author, you retain the copyright to your Work. By submitting your Work, you are granting anybody the right to copy, distribute and transmit your Work and to adapt your Work with proper attribution under the terms of the Creative Commons Attribution 3.0 United States license. You assign rights to the Prognostics and Health Management Society to publish and disseminate your Work through electronic and print media if it is accepted for publication. A license note citing the Creative Commons Attribution 3.0 United States License as shown below needs to be placed in the footnote on the first page of the article.
First Author et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 United States License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.