Research on KPCA fault diagnosis method based on multi-domain features

To gain reliable sensitive feature information and increase the completeness of fault information, kernel principal component analysis (KPCA) fault diagnosis method based on multi-domain features is proposed. The basic theory of KPCA is introduced, and signal pre-processing is given, multi-domain feature vector is extracted from time, time-frequency and frequency domain, faults are diagnosed with KPCA method. The new KPCA fault diagnosis method based on multi-domain features is tested on axial piston pump, the result shows that the method is effective, and studying multi-domain feature vector plays an important role in fault diagnosis system.