Research On Aero-Engine Condition Assessment Based On D-S Evidence Theory

Aero-engine is one of the most important parts of aircraft,and its safety,reliability and economy have been the focus of the aero-engine manufacturers,maintenance manufacturers and airlines.In order for the aeroengine to run safely,aiming at the multi-parameter,uncertainty and conflict of aero-engine condition monitoring data,this paper presents the aero-engine health condition evaluation based on D-S evidence theory.Firstly,the D-S evidence theory is used to evaluate the aero-engine state.Based on the membership function and weight,the evidence body is constructed,and the health state of aero-engine is evaluated by multi-source information fusion.Secondly,on the basis of evidence theory,an evaluation model combining artificial neural network with evidence theory is established.The sensor parameters after membership degree calculation are taken as the input of neural network,and the neural network is trained to construct the basic credibility value of evidence theory with the output recognition rate,after the information fusion processing obtains the concrete health status rank.The simulation results show that the method based on D-S evidence theory and neural network is effective in the field of condition assessment.Finally,the condition-based maintenance strategy and condition-based maintenance decision-making model are described.Based on the results of aero-engine condition assessment,the selection of aero-engine maintenance modes under different conditions is discussed,based on the semi-markov process,an engine imperfect maintenance model is established,which lays a foundation for the further development of maintenance strategy.