The methods of shaft torsional vibration fault diagnosis in marine basing on WPT and DAGSVM

Aim at the small-sample events of the torsional fault in marine, a method of shaft torsional vibration fault diagnosis in marine is proposed based on the theories of Shannon entropy of WT (Wavelet Packet) and DAGSVM (Directed Acyclic Graph Support Vector Machine). Firstly, the signals of four torsional vibration fault patterns are extracted relying on experimental platform of shaft torsional vibration in marine; then, extract the Shannon entropy of WPT for the input eigenvectors of SVM; Finally, identify the faults by using the SVM which advanced by the K-CV (K-fold Cross Validation) . The result shows that the method has higher recognition rate, providing a valuable on-line diagnostic method for the shaft torsional vibration fault diagnosis in marine.