Bearing fault diagnosis model based on neighborhood adaptive locality preserving projections
Yang Wang-ca · Zhendong yu chongji · 2014
In order to diagnose fault effectively by using vibration signal,a bearing fault diagnosis model based on neighborhood adaptive locality preserving projections was proposed.A bearing vibration signal was decomposed into several smooth intrinsic mode functions(IMFs) by EMD and the auto-regressive(AR) model of IMF was established to construct an original characteristic subset.Then,the algorithm of neighborhood adaptive locality preserving projections was used to reduce the dimension of the original characteristic subset to gain low-dimension eigenvectors and projection matrix.The best reduced dimension and the best corresponding projection matrix were determined by studying the relationship between the fault recognition rate and the dimension of the low-dimension eigenspace,using low-dimension eigenvectors as inputs and least square support vector machine(LS-SVM)as classifier.Low-dimension eigenvectors converted from the original characteristic subset based on the best reduced dimension were put into LS-SVM for recognizing the conditions and fault states of bearing.The test results indicate that the proposed model is able to diagnose bearing fault with high accuracy.