FDI approach to the DAMADICS benchmark problem based on qualitative reasoning coupled with fuzzy neural networks

摘要

A computer-assisted fault detection and isolation (FDI) based on a fuzzy qualitative simulation algorithm used for fault detection purposes, coupled with a hierarchical structure of fuzzy neural networks used to perform the fault isolation task, is presented. The DAMADICS benchmark actuator system has been used as test bed of the current FDI system. Single abrupt and incipient faults, as well as multiple simultaneous faults have been considered to test the overall system robustness. The results obtained prove the efficiency of the proposed FDI system.