Gearbox fault diagnosis based on LMD energy entropy and support vector machine

Aiming at the problem that it is difficult to extract and classify multiple fault features of gearbox in the case of small samples, a fault diagnosis method based on local mean decomposition (LMD) energy entropy and support vector machine (SVM) is proposed. Firstly, the collected gearbox vibration signal is decomposed by LMD method to obtain finite pf components; Then, according to the uneven distribution of gearbox vibration signals in frequency domain under different faults, the dispersion of PF component energy in different frequency domain is analyzed, that is, the LMD energy entropy is calculated; Finally, SVM multi fault classifier is used to train and test the extracted features for gearbox fault classification. The experimental results show that even in the case of small samples and non single and multiple gearbox faults at the same time, the feature extraction and accurate classification of gearbox faults can be realized based on LMD energy entropy and SVM.