BEGIN:VCALENDAR VERSION:2.0 PRODID:-//Memento EPFL// BEGIN:VEVENT SUMMARY:CIS - "Get to know your neighbors" Seminar series - Prof. Olga Fin k DTSTART:20220822T151500 DTEND:20220822T161500 DTSTAMP:20260916T073845Z UID:464257174e8d4ad1b6123ba46567321f7b546e81ef5a1b76ef7290f9 CATEGORIES:Conferences - Seminars DESCRIPTION:Prof. Olga Fink\nTitle: Domain adaptation and hybrid algorithm s fusing physics-based and deep learning algorithms for fault diagnostics and prognostics\n\nAbstract: The amount of measured and collected conditio n monitoring data for complex infrastructure and industrial assets has bee n recently increasing significantly due to falling costs\, improved techno logy\, 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 le arn the fault patterns of all the possible fault types affecting a system. Consequently\, faulty conditions cannot be used to learn patterns from. E ven collecting a representative dataset with all possible operating condit ions can be a challenging task since the systems experience a high variabi lity of operating conditions. Therefore\, training samples captured over l imited time periods may not be representative for the entire operating pro file. The collection of a representative dataset may delay the implementat ion of data-​driven fault detection and isolation systems. Furthermore\, domain experts require an interpretability of the obtained results.\nThe talk will cover two approaches to tackle these challenges. On the one hand \, it will provide insights into potential solutions that enable to transf er models and operational experience between different units of a fleet an d 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 a nd deep neural networks\, thereby\, not only improving the performance but also improving the interpretability of the developed models.\n\nBio: Olga Fink has been assistant professor of intelligent maintenance and operatio ns systems at EPFL since March 2022. Before joining EPFL faculty\, Olga wa s assistant professor of intelligent maintenance systems at ETH Zurich fro m 2018 to 2022\, being awarded the prestigious professorship grant of the Swiss National Science Foundation (SNSF). Between 2014 and 2018 she was he ading the research group “Smart Maintenance” at the Zurich University of Applied Sciences (ZHAW) where she was senior lecturer. Olga received h er Ph.D. from ETH Zurich on the topic of “Failure and Degradation Predic tion by Artificial Neural Networks: Applications to Railway Systems” and a diploma in industrial engineering from the Hamburg University of Tech nology. She has gained valuable industry experience as a reliability engi neer for railway rolling stock and as a reliability and maintenance exper t for railway systems. Olga’s research focuses on Data‐Driven Condit ion‐Based and Predictive Maintenance\, Physics-Informed Machine Learnin g for Operational Digital Twins\, Deep Learning and Decision Support Algor ithms for Fault Detection\, Diagnostics and Prognostics of Complex Indust rial Assets.\n\n\nThe Center for Intelligent Systems at EPFL (CIS) is a co llaboration among IC\, ENAC\, SB\; SV and STI that brings together researc hers working on different aspects of Intelligent Systems.\nIn order to pro mote exchanges among researchers and encourage the creation of new\, colla borative projects\, CIS is organizing a "Get to know your neighbors" serie s. Each seminar will consist of one short overview presentation geared to the general public at EPFL.   \n \nThe CIS seminar will take place In hybrid mode: Room INF 328 and by Zoom https://epfl.zoom.us/j/68022007910 \ n\nPlease connect to your zoom account using your "@epfl.ch" address\, as this live event is only open to the EPFL community\nMonday\, August 22th\, 2022 from 3:15 to 4:15 pm\nNB: Video recordings of the seminars will be m ade available on our website and published on our social media pages LOCATION:INF 328 https://plan.epfl.ch/?room==INF%20328 https://epfl.zoom.u s/j/68022007910 STATUS:CONFIRMED END:VEVENT END:VCALENDAR