Bayesian model-based diagnosis

Model-based diagnosis concerns using a model of the structure and behaviour of a system or device in order to establish why the system or device is ma lfunctioning. Traditionally, little attention has been given to the problem of dealing with uncertainty in model-based diagnosis. Given the fact that determining a diagnosis for a problem almost always involves uncertainty, t his situation is not entirely satisfactory. This paper builds upon and exte nds previous work in model-based diagnosis by supplementing the well-known model-based framework with mathematically sound ways for dealing with uncer tainty. The resulting method integrates logical reasoning with probabilisti c reasoning, and reasoning about the structure and behaviour of a system wi th reasoning by taking stochastic independence assumptions into account. (C ) 2001 Elsevier Science Inc. All rights reserved.