Fault Diagnosis Method for Shearer Equipment of PCA-BP_Adaboost

Abstract

Aiming at the problem that the fault diagnosis method of shearer equipment based on BP neural network has weak noise sensitivity and generalization performance, this paper proposes a PCA-BP_Adaboostfault diagnosis method for shearer equipment. First, the principal component analysis method (PCA) is used to extract the principal components of the high-dimensional matrix composed of different parts of the shearer to mitigate the noise sensitivity problem. Secondly, construct the BP neural network structure for training the data features; To enhance the generalization ability of the network and improve the accuracy of coal mining machine fault identification, this paper combines the weak classifier of BP neural network into a strong classifier of BP_Adaboost, which is used to improve the accuracy of fault diagnosis and identification of shearer. The experimental results show that the proposed method can improve the recognition rate of coal mining machine fault diagnosis based on the efficiency of BP-based shearer fault diagnosis algorithm.