ENAC Seminar Series by Prof. O. Fink
Event details
| Date | 30.03.2021 |
| Hour | 09:00 › 09:45 |
| Speaker | Prof. Olga Fink |
| Location |
Zoom
Online
|
| Category | Conferences - Seminars |
09:00 – 09:45 – Prof. Olga Fink
Assistant Professor at ETHZ, Zürich
Domain adaptation for intelligent maintenance systems
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.
The talk will provide insights into potential solutions that enable to transfer models and operational experience between different units and between different operating conditions also in unsupervised setups where data on faulty conditions is not available. Moreover, a synthetic-to-real framework for domain adaptation will be presented, where only knowledge of the healthy class is needed. The healthy class is augmented with synthetic faults to generate the rare fault examples based on expert understanding of how faults affect the measured signals. A domain adaptation (DA) is proposed to adapt the model from synthetic faults (source) to the unlabeled real data (target) overcoming the different imbalance levels in source and target datasets.
Short bio:
Olga Fink has been assistant professor of intelligent maintenance systems at ETH Zürich since October 2018, being awarded the prestigious professorship grant of the Swiss National Science Foundation (SNSF).
Olga is also a research affiliate at Massachusetts Institute of Technology and Expert of the Innosuisse in the field of ICT. Olga’s research focuses on Intelligent Maintenance Systems, Data‐Driven Condition‐Based and Predictive Maintenance, Hybrid Approaches Fusing Physical Performance Models and Deep Learning Algorithms, Deep Learning and Decision Support Algorithms for Fault Detection and Diagnostics of Complex Infrastructure and Industrial Assets. Before joining ETH faculty, she was heading the research group “Smart Maintenance” at the Zurich University of Applied Sciences (ZHAW) between 2014 and 2018. 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.
Assistant Professor at ETHZ, Zürich
Domain adaptation for intelligent maintenance systems
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.
The talk will provide insights into potential solutions that enable to transfer models and operational experience between different units and between different operating conditions also in unsupervised setups where data on faulty conditions is not available. Moreover, a synthetic-to-real framework for domain adaptation will be presented, where only knowledge of the healthy class is needed. The healthy class is augmented with synthetic faults to generate the rare fault examples based on expert understanding of how faults affect the measured signals. A domain adaptation (DA) is proposed to adapt the model from synthetic faults (source) to the unlabeled real data (target) overcoming the different imbalance levels in source and target datasets.
Short bio:
Olga Fink has been assistant professor of intelligent maintenance systems at ETH Zürich since October 2018, being awarded the prestigious professorship grant of the Swiss National Science Foundation (SNSF).
Olga is also a research affiliate at Massachusetts Institute of Technology and Expert of the Innosuisse in the field of ICT. Olga’s research focuses on Intelligent Maintenance Systems, Data‐Driven Condition‐Based and Predictive Maintenance, Hybrid Approaches Fusing Physical Performance Models and Deep Learning Algorithms, Deep Learning and Decision Support Algorithms for Fault Detection and Diagnostics of Complex Infrastructure and Industrial Assets. Before joining ETH faculty, she was heading the research group “Smart Maintenance” at the Zurich University of Applied Sciences (ZHAW) between 2014 and 2018. 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.
Practical information
- General public
- Invitation required
- This event is internal
Organizer
- ENAC
Contact
- Christine Crosetti