Bayesian Fault Diagnosis for Automitive Engines by Combining Data and Process Knowledge
2009 (English)In: IEEE Transactions on Systems, Man and Cybernetics, ISSN 0018-9472Article in journal (Other academic) Submitted
We consider fault diagnosis of complex systems, motivated by the problem of fault diagnosis of an automotive diesel engine. Previous fault diagnosis algorithms are typically based either on process knowledge, for example a Fault Signature Matrix (FSM), or on training data. Both these methods have their advantages and drawbacks.
The main contribution in the present work is that we show how to integrate process knowledge and training data to improve fault diagnosis for automotive processes. We carefully investigate the characteristics of our motivating application, and we derive a new method for fault diagnosis based Bayesian inference.
To illustrate the new fault diagnosis method we have applied it to the diagnosis of the gas flow of an automotive engine using data from real driving situations. It is shown that diagnosis performance is improved compared to previous methods using solely data or process knowledge. Finally we study the relation between the new method and previous state of the art methods for fault diagnosis.
Place, publisher, year, edition, pages
IEEE , 2009.
Engineering and Technology
IdentifiersURN: urn:nbn:se:liu:diva-51922OAI: oai:DiVA.org:liu-51922DiVA: diva2:278125