A combined diagnosis system design using model-based and data-driven methods
2016 (English)In: 2016 3RD CONFERENCE ON CONTROL AND FAULT-TOLERANT SYSTEMS (SYSTOL), IEEE , 2016, 177-182 p.Conference paper (Refereed)
A hybrid diagnosis system design is proposed that combines model-based and data-driven diagnosis methods for fault isolation. A set of residuals are used to detect if there is a fault in the system and a consistency-based fault isolation algorithm is used to compute all diagnosis candidates that can explain the triggered residuals. To improve fault isolation, diagnosis candidates are ranked by evaluating the residuals using a set of one-class support vector machines trained using data from different faults. The proposed diagnosis system design is evaluated using simulations of a model describing the air-flow in an internal combustion engine.
Place, publisher, year, edition, pages
IEEE , 2016. 177-182 p.
Conference on Control and Fault-Tolerant Systems, ISSN 2162-1209
IdentifiersURN: urn:nbn:se:liu:diva-134515DOI: 10.1109/SYSTOL.2016.7739747ISI: 000391868600028ISBN: 978-1-5090-0658-8 OAI: oai:DiVA.org:liu-134515DiVA: diva2:1074340
3rd Conference on Control and Fault-Tolerant Systems (SysTol)
Funding Agencies|Volvo Car Corporation in Gothenburg, Sweden2017-02-152017-02-152017-02-15