Inaugural Lecture - Prof. Olga Fink
Date: 10 May 2023
Time: 17:30 - 18:45
Introductions by the Dean, lectures by Prof. Olga Fink and Prof. Stefana Parascho. Followed by an Apero.
Place: CO2
Zoom link
Title:
From physics to machine learning and back: Applications to intelligent maintenance and operation of complex systems
Abstract
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. Particularly run to failure trajectories are rare. 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, diagnostics and prognostics systems. Moreover, some of the current limitations include limited scalability, generalization ability and interpretability of the developed models.
The talk will give insights into the currently ongoing research at the Intelligent Maintenance and Operations Systems Laboratory at EPFL, focusing on two key areas. Firstly, the presentation will center around the fusion of physics-based and deep learning algorithms, particularly in the context of fault diagnostics and prognostics. Secondly, the presentation will delve into the topic of domain adaptation and generalization and their impact on improving fault diagnostics and prognostics.
About the speaker
Olga Fink has been assistant professor at EPFL since March 2022, heading the “Intelligent Maintenance and Operations Systems” laboratory. Olga is also a research affiliate at Massachusetts Institute of Technology. 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 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.
Time: 17:30 - 18:45
Introductions by the Dean, lectures by Prof. Olga Fink and Prof. Stefana Parascho. Followed by an Apero.
Place: CO2
Zoom link
Title:
From physics to machine learning and back: Applications to intelligent maintenance and operation of complex systems
Abstract
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. Particularly run to failure trajectories are rare. 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, diagnostics and prognostics systems. Moreover, some of the current limitations include limited scalability, generalization ability and interpretability of the developed models.
The talk will give insights into the currently ongoing research at the Intelligent Maintenance and Operations Systems Laboratory at EPFL, focusing on two key areas. Firstly, the presentation will center around the fusion of physics-based and deep learning algorithms, particularly in the context of fault diagnostics and prognostics. Secondly, the presentation will delve into the topic of domain adaptation and generalization and their impact on improving fault diagnostics and prognostics.
About the speaker
Olga Fink has been assistant professor at EPFL since March 2022, heading the “Intelligent Maintenance and Operations Systems” laboratory. Olga is also a research affiliate at Massachusetts Institute of Technology. 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 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.
Links
Practical information
- Informed public
- Registration required
Organizer
- SAR - Gesualdo Casciana