Aero-Engine Gas Path Fault Diagnosis Using The Information Fusion

The fault diagnosis of aero-engine is main research areas in aero-engine industry. Because it is very important, it has become one research focus in home and abroad. Information fusion is a subject formed recently; it has been researched and applied in many fields. But, it is in staring stage in aero engine fault diagnosis. There are much available information in fault diagnosis, only when the available information is used, can the precision and credibility been proved, so the engine fault diagnostic is a process of information.The basic principles, hierarchical structure and methods of information fusion were presented; the basic structure, principles and classification algorithms of the BP neural network, RBF neural network and support vector machine were discussed which is applied in fault diagnosis field currently, and the JT9D engine gas path fault diagnosis was taken as the example to describe the design process and the fault diagnosis prototypes of these three kinds classifier; Combined with an analysis example, the method, models of the DS evidence theory has been explained. On this basis, a multiple classifiers fusion method of the engine fault diagnosis was presented, the simulation of the engine gas path fault diagnostic example show it is feasible and effective.