Synthesized Fault Diagnosis Method Based on Fuzzy Logic and D-S Evidence Theory

Based on fuzzy logic theory, the information fusion technique at decision-making level is introduced for fault diagnosis system. A comprehensive fault diagnosis method based on fuzzy logic and D-S evidence theory is presented by making use of multi-sensor information fusion technique. In this method, the basic reliability distribution of evidence theory is obtained by using fuzzy membership function, which can significantly improve the accuracy of the fault diagnosis through taking full advantages of redundant and complementary fault information from all sensors. Finally the method is applied for fault diagnosis of ship diesel engine. Diagnostic results indicate that the technique is effective, greatly improving the efficiency of fault diagnosis.