Statistical Signal Processing Approaches to Fault Detection
2006 (English)In: Proceedings of the 6th IFAC Symposium on Fault Detection, Supervision and Safety of Technical Processes, 2006, 24-35 p.Conference paper (Refereed)
The parity space approach to fault detection and isolation (FDI) has beendeveloped during the last twenty years, and the focus here is to describe its applicationto stochastic systems. A mixed model with both stochastic inputs and deterministicdisturbances and faults is formulated over a sliding window. Algorithms for detecting andisolating faults on-line and analyzing the probability for correct and incorrect decisionsoff-line are provided. A major part of the paper is devoted to discussing properties ofthis model-based approach and generalizations to cases of incomplete model knowledge,and non-linear non-Gaussian models. For this purpose, a simulation example is usedthroughout the paper for numerical illustrations, and real-life applications for motivations.The ﬁnal section discusses the reverse problem: fault detection approaches to statisticalsignal processing. It is motivated by three applications that a simple CUSUM detectorin feedback loop with an adaptive ﬁlter can mitigate the inherent trade-off betweenestimation accuracy and tracking speed in linear ﬁlters.
Place, publisher, year, edition, pages
2006. 24-35 p.
Fault detection, Diagnosis, Kalman filtering, Adaptive filters, Linear systems, Principal component analysis, Subspace identification
Engineering and Technology Control Engineering
IdentifiersURN: urn:nbn:se:liu:diva-89260DOI: 10.3182/20060829-4-CN-2909.00004ISBN: 978-3-902661-14-2OAI: oai:DiVA.org:liu-89260DiVA: diva2:607569
6th IFAC Symposium on Fault Detection, Supervision and Safety of Technical Processes, Beijing, China, August-September, 2006