Intelligent Fault Diagnosis of Aeroengine based on Algorithm Fusion

Abstract

Fault diagnosis of aero engine is an important research to ensure the safety of engine operation, it is mainly classified by numerical deviation of engine performance parameters. Algorithm fusion technology is an excellent model method that can complement various algorithms, in this paper, the improved immune algorithm and grey theory are used for fault diagnosis, aiming at the grey relational algorithm, we propose a dynamic fault domain determination method; in immune algorithm, we propose a new mutation strategy; finally, we adopt the improved D-S evidence theory for algorithm fusion. The proposed algorithm is applied to engine fault diagnosis and fault domain determination, compared with the traditional grey association algorithm, the improved grey association algorithm can improve the test accuracy by 28.3%, the improved immune algorithm is 8.9% more accurate than the traditional immune algorithm, the accuracy of the aero-engine fault diagnosis test set using the improved d-s evidence theory reached 92.8%.