A Bayesian Approach to Learning in Fault Isolation
Anna Pernestål, Hannes Wettig, Tomi Silander, Matias Nyberg and Petri Myllymäki
In: The 19th International Workshop on Principles of Diagnosis (DX-08), September 22-24, 2008, Blue Mountains, NSW, Australia.
Fault isolation is the task of localizing faults in a process, given observations from it. To do this, a model describing the realtion between faults and observations is needed. In this paper we focus on learning such models both from training data and from prior knowledge. There are several challenges in learning for fault isolation. The number of data, as well as the available computing resources, are often limited. Furthermore, there may be previously unobserved fault patterns. To meet these challenges we take on a Bayesian approach. We compare five different approaches to learning for fault isolation, and evaluate their performance on a real application; the diagnosis of an automotive engine.