A data mining approach to incremental adaptive functional diagnosis

This paper presents a novel approach to functional fault diagnosis adopting data mining to exploit knowledge extracted from the system model. Such knowledge puts into relation test outcomes with components failures, to define an incremental strategy for identifying the candidate faulty component. The diagnosis procedure is built upon a set of sorted, possibly approximate, rules that specify given a (set of) failing test, which is the faulty candidate. The procedure iterative selects the most promising rules and requests the execution of the corresponding tests, until a component is identified as faulty, or no diagnosis can be performed. The proposed approach aims at limiting the number of tests to be executed in order to reduce the time and cost of diagnosis. Results on a set of examples show that the proposed approach allows for a significant reduction of the number of executed tests (the average improvement ranges from 32% to 88%).