A Novel Fault Diagnosis Method Using PCA and ART-Similarity Classifier Based on Yu’s Norm

Zeng Bing Xu; Jian Ping Xuan; Tie Lin Shi; Bo Wu; You Min Hu

doi:10.4028/www.scientific.net/KEM.413-414.569

Paper Titles

A Steam Turbine Fault Diagnostic System Based on the Web and Database Technologies
p.539

Research on the Fault Diagnosis Technology of Diesel Engine Based on the Instantaneous Speed
p.547

Diagnose and Analysis of Coupling Faults on Nonlinear Rotor-Bearing-Seal System Prediction
p.553

Fault Recognition Method of Rolling Bearings Based on Volterra Series and HMM
p.561

A Novel Fault Diagnosis Method Using PCA and ART-Similarity Classifier Based on Yu’s Norm
p.569

Wavelet Selection for Bearing Defect Diagnosis
p.575

Research on Nonlinear Process Monitoring and Fault Diagnosis Based on Kernel Principal Component Analysis
p.583

Shaft Crack Analysis and Diagnosis for the 600MW Steam Turbine Generator
p.591

Experimental Investigation of Pedestal Looseness in a Rotor-Bearing System
p.599

HomeKey Engineering MaterialsKey Engineering Materials Vols. 413-414A Novel Fault Diagnosis Method Using PCA and...

A Novel Fault Diagnosis Method Using PCA and ART-Similarity Classifier Based on Yu’s Norm

Abstract:

In this paper, a novel similarity classifier which synthesizes the adaptive resonance theory (ART) and the similarity classifier based on the Yu’s norm is proposed. The proposed ART-similarity classifier can not only carry out training without forgetting previously trained patterns but also be adaptive to changes in the environment. In order to test the proposed classifier, it is applied to the fault diagnosis of rolling element bearings. Before application to the fault diagnosis of bearings, considering computation burden principal component analysis (PCA) is proposed to reduce the number of features. The PCs are input the proposed classifier to diagnose the faulty bearings. The experiment results testify that the proposed classifier can identify the faults accurately. Furthermore, in order to validate the effectiveness of the proposed classifier further, it compares with other neural networks, such as the fuzzy ART, self-organising feature maps (SOFMs) and radial basis function (RBF) neural network through diagnosing the bearings under the same conditions. The comparison results confirm the superiority of the proposed method.