Study On Condition Monitoring Technology For Aeroengine Gas Path System

As the "heart" of aircraft,aeroengine is a large-scale system,because of its complex structure,poor working conditions and other factors,the effective health condition monitoring has become one of the key techniques in the aviation field that is difficult to resolve.Whether the health condition of aeroengine is good or not,directly impacts on flight safety of aircraft,which has a very important significance for improving the safety and reliability of aircraft flight.Therefore in order to monitor the health condition of aeroengine effectively,taking the aeroengine gas path system as an example,this paper puts forward aero engine condition monitoring and fault diagnosis method.Firstly,an overview of aeroengine condition monitoring research background,status and multi-source information fusion technology,makes a further study on fusion technology,the composition of engine gas path system and fault formation mechanism of failure symptoms.Based on aeroengine gas path system combining data's characteristics,the use of adaptive weighted fusion algorithm to the original data preprocessing,eliminated false information.And then it puts forward a kind of condition monitoring methods based on principal component analysis.This method can extract the principal component eigenvectors,dimension reduction and accurate fault detection engine and determine the fault source.Secondly,based on the feature vector of engine variables,it made a fault diagnosis model of neural network to condition monitor condition of aeroengine.Finally,in order to improve the monitoring accuracy,and effectively solve the problem of conflict between diagnosis information based on the neural network,the use of fuzzy integral preliminary monitoring of the three kinds of neural network results in conflict resolution,so as to effectively realize the state monitoring of aeroengine gas path system.By a certain type of aircraft engine real validation,it shows the method takes advantage of principal component analysis and fuzzy integral,improves the accuracy of condition monitoring and meet the aircraft engine condition monitoring of real-time requirements,which has a good value in engineering applications.