A model to predict the residual life of aero-engine based upon Support Vector Machine
暂无分享,去创建一个
The residual life prediction of aero-engine is important for ensuring flight safety and reducing operating costs for airlines. Since there are varied performance parameters of aero-engine, it is difficult to use comprehensively these performance parameters to predict the residual life. This paper exploits Support Vector Regression Machine (SVR) in predicting the trend of varied performance parameters of aero-engine. Besides, a failure decision function based on Support Vector Classification Machine (SVC) is established, which considered varied performance parameters and time on wing. A method to predict the residual life of aero-engine is proposed based on trend prediction of varied performance parameters and failure decision function. The proposed approach is applied to predict the residual life of aero-engine based on the data of the actual gas path parameters monitoring information and failure event report from the aero-engine. The result shows that the validity and practicability of the method.
[1] Joseph Mathew,et al. Bearing fault prognosis based on health state probability estimation , 2012, Expert Syst. Appl..
[2] F Zhao,et al. Condition prediction based on wavelet packet transform and least squares support vector machine methods , 2009 .
[3] Wenbin Wang,et al. A model to predict the residual life of aircraft engines based upon oil analysis data , 2005 .
[4] Chih-Jen Lin,et al. LIBSVM: A library for support vector machines , 2011, TIST.