Uncertainty and Approximation in Multi-model Diagnosis. Information Sciences.

Diagnosis of industrial plants is a complex task, usually performed by systems provided with the plant itself. However, these diagnostic systems are not reliable when the working conditions are different from those expected at design time. In this paper, we present OMISSYS (Opportunistic Model-based diagnosIS SYStem), a system that can diagnose faults in plants whose components are imperfectly described, and where data are affected by uncertainty and imprecision. OMISSYS exploits the available knowledge and data to obtain a suboptimal diagnosis for the detected fault. We represent imperfection using uncertain-fuzzy numbers, a formalism that can represent both uncertainty and imprecision. OMISSYS was tested on realistic examples and it efficiently produced satisfactory diagnoses.