CIS – “Get to know your neighbors” Seminar Series
“Domain adaptation and hybrid algorithms fusing physics-based and deep learning algorithms for fault diagnostics and prognostics”
Prof. Olga Fink, Tenure Track Assistant Professor, Intelligent Maintenance and Operations Systems
Monday, August 22, 2022 3:15 – 4:15pm | Hybrid
or on-site INF 328
The amount of measured and collected condition monitoring data for complex infrastructure and industrial assets has been recently increasing significantly due to falling costs, improved technology, and increased reliability of sensors and data transmission. However, faults in safety critical systems are rare. The diversity of the fault types and operating conditions makes it often impossible to extract and learn the fault patterns of all the possible fault types affecting a system. Consequently, faulty conditions cannot be used to learn patterns from. Even collecting a representative dataset with all possible operating conditions can be a challenging task since the systems experience a high variability of operating conditions. Therefore, training samples captured over limited time periods may not be representative for the entire operating profile. The collection of a representative dataset may delay the implementation of data-driven fault detection and isolation systems. Furthermore, domain experts require an interpretability of the obtained results.
The talk will cover two approaches to tackle these challenges. On the one hand, it will provide insights into potential solutions that enable to transfer models and operational experience between different units of a fleet and between different operating conditions also in unsupervised setups where data on faulty conditions is not available. On the other hand, the talk will introduce a hybrid framework that fuses physical performance models and deep neural networks, thereby, not only improving the performance but also improving the interpretability of the developed models.
Olga Fink has been assistant professor of intelligent maintenance and operations systems at EPFL since March 2022. 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) where she was senior lecturer. Olga received her Ph.D. from ETH Zurich on the topic of “Failure and Degradation Prediction by Artificial Neural Networks: Applications to Railway Systems” and a diploma in industrial engineering from the Hamburg University of Technology. She has gained valuable industry experience as a reliability engineer for railway rolling stock and as a reliability and maintenance expert for railway systems. Olga’s research focuses on Data‐Driven Condition‐Based and Predictive Maintenance, Physics-Informed Machine Learning for Operational Digital Twins, Deep Learning and Decision Support Algorithms for Fault Detection, Diagnostics and Prognostics of Complex Industrial Assets.