Research on the Roller Bearing Fault Diagnosis of the Engineering Vehicle Based on Dynamic Clustering and Multi-class SVM Algorithm

In response to the roller bearing fault of the engineering vehicle, the excellent characteristics of time-frequency of wavelet packet is used to decompose the fault signal. Then we extract the necessary of the fault signals. Finally, we carry out the recognition of fault types using multi-class support vector machine and dynamic clustering algorithm brought forward in the paper. It is such a algorithm that we carry out the initial classification via dynamic clustering algorithm, then process more accurate classification via multi-class support vector machine algorithm. In the paper we not only analysis the general type of fault, but also work on the typical fault type of roller bearing of the engineering vehicles. after testing and comparison experiment, it proves that the method is not only efficient but also has good accuracy.