Rolling Bearing Fault Diagnosis Method Based on Principal Components Analysis and Probabilistic Neural Network

Abstract

Abstract In this paper, a rolling bearing fault diagnosismethod based on PCA and improved PNN network is proposed to solve the problems of high dimension, high redundancy, nonlinearity and nonstationarity of rolling bearingdata. Firstly, the principal components analysis (PCA) algorithm is used to extract the feature information of the original data and obtain the principal component informationafter dimension reduction. Then the principal component information is sent as a feature to the probabilistic neuralnetwork (PNN) for training and output the diagnosisresults. The method is verified using Case Western bearingdatasets. Through simulation comparison of this method and BP neural network method, the experimental results show that the method proposed in this paper is more accurate in bearing fault diagnosis.