Mine fan fault diagnosis based on the lifting wavelet packet and support vector machines

In this research, we propose a new fault diagnosis method for mine fan, the lifting wavelet packet transform and support vector machines. With the lifting wavelet packet transform, fault feature factors can be extracted quickly and accurately from five typical fault patterns of mine fan, and taken as input samples for SVM provided with the outstanding non-linear pattern classification performances. The results showed the integrative method of the lifting WPT and SVM classifier is a valuable fault diagnosis method, and it is very fit for the intelligent diagnosis and fault patterns recognition, and it will lead to the possible development of an automated and online mine fan condition monitoring and diagnostic system.