Dr. Olga Fink

Dr. Olga Fink

Dr. Olga Fink
ZHAW School of Engineering
Rosenstrasse 3
8400 Winterthur

+41 (0) 58 934 49 52
olga.fink@zhaw.ch

Persönliches Profil

Tätigkeit an der ZHAW als

Senior Lecturer Reliability and Maintenance Engineering

Lehrtätigkeit in der Weiterbildung

Arbeits- und Forschungsschwerpunkte, Spezialkenntnisse

- Condition-based and Predictive Maintenance of Energy and Transportation Systems

- Prognostics and Health Management (PHM)

- Data-driven Algorithms for Fault Detection and Diagnostics

- Reliability, Availability, Maintainability and Safety (RAMS) of Railway Systems

- Reliable Operation of Public Transportation Systems

Aus- und Fortbildung

04/12 PhD in Civil Engineering, ETH Zürich
PhD thesis “Failure and Degradation Prediction by Artificial Neural Networks: Applications to Railway Systems”

Beruflicher Werdegang

Reliability and Maintenance Expert Pöyry Switzerland AG
Research associate at the Institute for Transport Planning and Systems (IVT) ETH Zürich
Reliability Engineer at Stadler Bussnang AG

Mitglied in Netzwerken

Projekte

Mitarbeit an folgenden Projekten

Publikationen

Beiträge, peer-reviewed

; ; ().

Fault detection based on signal reconstruction with Auto-Associative Extreme Learning Machines

.

Engineering Applications of Artificial Intelligence, 57 105-117. Peer reviewed.

; ; ; ; ; ().

Cluster Analysis of Condition Monitoring Data

.

In: Risk Reliability and Safety. Innovating Theory and Practice. London: Taylor & Francis. Peer reviewed.

; ; ().

Deep Health Indicator Extraction: A Method based on Auto-encoders and Extreme Learning Machines

.

Annual conference of the PHM society Peer reviewed.

; ; ().

Maximal information-based nonparametric exploration for condition monitoring data

.

Third European Conference of the Prognostics and Health Management Society Peer reviewed.

; ; ().

Online Sequential Extreme Learning Machines for Fault Detection

.

In: IEEE International Conference on Prognostics and Health Management. Ottawa: IEEE PHM2016. Peer reviewed.

; ; ().

A Classification Framework for Predicting Components' Remaining Useful Life Based on Discrete-Event Diagnostic Data

.

IEEE Transactions on Reliability, 64, 3. 1049 - 1056. Peer reviewed.

; ; ().

Development and Application of Deep Belief Networks for Predicting Railway Operations Disruptions

.

International Journal of Performability Engineering, 11, 2. 121 - 134. Peer reviewed.

; ; ().

Fuzzy Classification With Restricted Boltzman Machines and Echo-State Networks for Predicting Potential Railway Door System Failures

.

IEEE Transactions on Reliability, 64, 3. 861 - 868. Peer reviewed.

; ; ().

Two Machine Learning Approaches for Short-Term Wind Speed Time-Series Prediction

.

IEEE Transactions on Neural Networks and Learning Systems Peer reviewed.

Beiträge, nicht peer-reviewed

; ().

Vorausschauende Instandhaltung der Eisenbahnsysteme mit Hilfe der künstlichen Intelligenz

.

Eisenbahn-Technische Rundschau, 63(9). 184 – 186.

Publikationen vor Tätigkeit an der ZHAW

PEER REVIEWED SCIENTIFIC JOURNALS

Fink, O., E. Zio, U. Weidmann (2015): Novelty detection by multivariate kernel density estimation and growing neural gas algorithm, Mechanical Systems and Signal Processing, 50-51, 427-436

Fink, O., E. Zio, U. Weidmann (2014): Quantifying the reliability of fault classifiers, Information Sciences, 266, 65-74

Fink, O., E. Zio, U. Weidmann (2014): Predicting component reliability and level of degradation with complex-valued neural networks, Reliability Engineering & System Safety, 121, 198–206

Fink, O., A. Nash, U. Weidmann (2013): Predicting potential railway operational disruptions with echo state networks, Transportation Research Record, 2374, 66-72.

Fink, O., E. Zio, U. Weidmann (2013): Predicting time series of railway speed restrictions with time-dependent machine learning techniques, Expert Systems with Applications, 40 (15), 6033–6040

Fink, O., E. Zio (2013) Semi-Markov processes with semi-regenerative states for the availability analysis of chemical process plants with storage units, Proceedings of the Institution of Mechanical Engineers, Part O: Journal of Risk and Reliability, 227 (3), 279-289

REFEREED SCIENTIFIC CONFERENCE PAPERS

Fink, O., E. Zio, U. Weidmann (2013): Extreme learning machines for predicting operation disruption events in railway systems. In Proceedings of the European Safety and Reliability Conference (ESREL), Amsterdam, Netherlands, September 2013

Fink, O., E. Zio, U. Weidmann (2013): Anticipating railway operation disruption events based on the analysis of discrete-event diagnostic data. Chemical Engineering Transactions, 33; Proceedings of the Prognostics and Health Management Conference (PHM), Milan, Italy, September 2013.

Fink, O., U. Weidmann (2013): Deep belief networks for predicting potential railway operations disruptions caused by critical component failures. In Proceedings of the Advances in Risk and Reliability Technology Symposium, Loughborough, UK, Mai 2013.

Fink, O., U. Weidmann (2013): Predicting potential railway operations disruptions caused by critical component failure using echo state neural networks and automatically collected diagnostic data. 92nd Annual Meeting of the Transportation Research Board, Washington, D.C., USA, January 2013.

Fink, O. (2012): Availability analysis of chemical process plants with storage units applying semi-Markov processes with semi-regenerative states. In Proceedings of the European Safety and Reliability Conference (ESREL) Helsinki, Finland, June 2012.

Fink, O., Weidmann, U. (2011) Scope and potential of applying artificial neural networks in reliability prediction with a focus on railway rolling stock. In Proceedings of European Safety and Reliability Conference (ESREL) Troyes, France, September 2011.

Fink, O., Weidmann, U. (2011): Review of artificial neural network applications in reliability prediction with a focus on design phase and railway rolling stock applications, In Proceedings of the 17th ISSAT international Conference Reliability & Quality in Design, Vancouver, Canada, August 2011

Fink, O., U. Weidmann, D. Hofmann, A. Krolo (2011): Potential of applying artificial neural networks in analysis and forecasting of reliability (in German). In Proceedings of the conference for technical reliability, Stuttgart, Germany, Mai 2011



MONOGRAPHS:

O. Fink (2014) Failure and Degradation Prediction by Artificial Neural Networks: Applications to Railway Systems, Monograph series 165, IVT, ETH Zurich, Zurich

Carrasco N., O. Fink and U. Weidmann (2012) Operational stability and reliability of urban bus routes in Zurich, Switzerland, Monograph series 156, IVT, ETH Zurich, Zurich