A Diagnostic Reasoning Model Based on the Criticality of Assumptions1

It has been realized that the computational complexity of model-based diagnosis makes the mechanism impractical for real-world diagnosis tasks. One way to overcome this disadvantage is to focus the diagnosis on a reduced diagnostic space. we have proposed an improved critical diagnosis reasoning method 6] based on the method IMPLODE 5] proposed by Raiman, de Kleer and Saraswat. The improved method focuses the diagnosis on nding out the kernel diagnoses instead of the whole diagnoses. In this paper, we present a diagnostic reasoning model called DRMCA to implement the improved critical reasoning. The architecture, knowledge representation and algorithms of DRMCA are described in the paper. A non-backtracking algorithm is used to nd out the diagnoses instead of the backtracking algorithm in IMPLODE. The eeciency of DRMCA is improved because of the reduced diagnosis space and the non-backtracking algorithm. The comparisons between DRMCA and IMPLODE are also given to show the improvements of DRMCA.