The 8th International Conference on System Reliability and Safety
Sicily, Italy - November 20-22, 2024

 

Olga Fink, EPFL, Switzerland

Olga Fink has been assistant professor of intelligent maintenance and operations systems at EPFL since March 2022.  Olga is also a research affiliate at Massachusetts Institute of Technology. Olga’s research focuses on Hybrid Algorithms Fusing Physics-Based Models and Deep Learning Algorithms, Hybrid Operational Digital Twins, Transfer Learning, Self-Supervised Learning, Deep Reinforcement Learning and Multi-Agent Systems for Intelligent Maintenance and Operations of Infrastructure and Complex Assets. Before joining EPFL faculty, Olga was assistant professor of intelligent maintenance systems at ETH Zurich from 2018 to 2022, being awarded the prestigious professorship grant of the Swiss National Science Foundation (SNSF). Between 2014 and 2018 she was heading the research group “Smart Maintenance” at the Zurich University of Applied Sciences (ZHAW). Olga received her Ph.D. degree from ETH Zurich with the thesis on “Failure and Degradation Prediction by Artificial Neural Networks: Applications to Railway Systems”, and Diploma degree in industrial engineering from Hamburg University of Technology. She has gained valuable industrial experience as reliability engineer with Stadler Bussnang AG and as reliability and maintenance expert with Pöyry Switzerland Ltd. In 2018, Olga was selected as one of the “Top 100 Women in Business, Switzerland” and in 2019, she was selected as young scientist of the World Economic Forum. In 2020 and 2021, she was  honored as young scientist of the World Laureate Forum.

Speech Title: Integrating Prior Knowledge and AI: Leveraging Inductive Bias in Machine Learning for Effective PHM Solutions
Abstract: In the field of prognostics and health management, the integration of machine learning has enabled the development of advanced predictive models that ensure the reliable and safe operation of complex assets. However, challenges such as sparse, noisy, and incomplete data necessitate the integration of prior knowledge and inductive bias to improve model generalization, interpretability, and robustness.
Inductive bias, defined as the set of assumptions embedded in machine learning models, plays a crucial role in guiding these models to generalize effectively from limited training data to real-world scenarios. In PHM applications, where physical laws and domain-specific knowledge are fundamental, the use of inductive bias can significantly enhance a model’s ability to predict system behavior under diverse operating conditions. By embedding physical principles into learning algorithms, inductive bias reduces the reliance on large datasets, ensures that model predictions are physically consistent, and enhances both the generalizability and interpretability of the models.
This talk will explore various forms of inductive bias tailored for PHM systems, with a particular focus on heterogenous-temporal graph neural networks, as well as physics-informed and algorithm-informed graph neural networks. These approaches will be applied to virtual sensing, modelling multi-body dynamical systems and anomaly detection.

 

Ming Zuo, University of Alberta, Canada

Dr. Mingjian Zuo is Special Professor of the University of Electronic Science & Technology of China, Professor Emeritus of the University of Alberta, Canada, and Founder and Chief Scientist of Mingserve Technology Co. Ltd., China. He received the Bachelor of Science degree in Agricultural Engineering in 1982 from Shandong Institute of Technology, China, and the Master of Science degree in 1986 and the Ph.D. degree in 1989 both in Industrial Engineering from Iowa State University, Ames, Iowa, USA. His research interests include system reliability analysis, maintenance modeling and optimization, signal processing, fault diagnosis, machine learning, and prognosis & health management. He is Fellow of the Canadian Academy of Engineering (CAE), Fellow of the Prognostics and Health Management Society (PHMS), Fellow of the Asia-Pacific Artificial Intelligence Association (FAAIA), Fellow of the Institute of Industrial and Systems Engineers (IISE), and Founding Fellow of the International Society of Engineering Asset Management (ISEAM). He served as Department Editor of IISE Transactions, Associate Editor of IEEE Transactions on Reliability, Associate Editor of Journal of Risk and Reliability, Associate Editor of International Journal of Quality, Reliability and Safety Engineering, Regional Editor of International Journal of Strategic Engineering Asset Management, and Editorial Board Member of Reliability Engineering and System Safety, Journal of Traffic and Transportation Engineering, and International Journal of Performability Engineering.

Speech Title: Machine Learning for Practical Prognosis and Health Management

Abstract: Machine learning has great potential for reliability assurance of engineering assets through prognosis and health management (PHM). It has been attracting attention from both academic and industrial sectors. Recent developments of machine learning, especially the evolving branches of deep learning, transfer learning, and reinforcement learning, bring new opportunities for effective PHM. This talk will first introduce general principles of prognosis and health management and machine learning. We will then present our recent research work on developing machine learning techniques for PHM. Finally, development of PHM tools for industrial settings including traditional and intelligent approaches will be covered.

Katrina Groth, University of Maryland, USA

Katrina M. Groth is an Associate Professor of Mechanical Engineering and the Director of the Reliability Engineering program at the University of Maryland. Groth specializes in safety, risk, and reliability analysis of energy systems. She has an active portfolio of research, including developing quantitative risk assessment (QRA) methods, prognostics and health management (PHM) techniques, and reliability data collection frameworks and algorithms. Her work has influenced safety practices and codes and standards for hydrogen fueling stations, hydrogen storage and electrolyzers, fuel cells, gas pipelines, and nuclear power plants and more. Groth has published over 125 peer-reviewed papers and technical reports, 1 textbook, and has developed multiple software packages. She has received numerous awards, including an NSF CAREER award in 2021 and a DOE Hydrogen Program R&D Award, and the David Okrent Award for Nuclear Safety. She holds a Ph.D. in Reliability Engineering from the University of Maryland.

Speech Title: Insights for hydrogen safety from Quantitative risk assessment (QRA): implications for fueling stations, forklifts, pipelines, and electrolyzers

Safety and reliability issues can impede development and adoption of new technologies, and hydrogen systems are no exception. The widely anticipated adoption of hydrogen technologies requires that the risks associated with those technologies be rigorously investigated and mitigated early in the lifecycle. Quantitative risk assessment (QRA) enables proactively addressing potential failures before they happen – and learning from failures and near misses when they happen. Assessing and addressing risk will enable minimizing failures, downtime, maintenance costs, property damage, injuries, loss of public trust, and costly litigation. This talk presents design-stage QRAs completed for four hydrogen technologies: fueling stations, forklifts, pipelines, and electrolyzers. The emphasis is on 1) sharing early insights that will enable safety and reliability of new deployments, 2) discussing the role of  and 2) sharing high-priority research gaps to motivate the hydrogen safety and reliability engineering research community to address known gaps before they become barriers to hydrogen deployments.