Intelligent fault diagnosis based on support vector machine

Rolling bearing is one of the most important parts of a mechanical device. It has a higher failure rate, while the quality of the rolling bearing operating conditions affecting the operation of the entire device or even the entire production line. Therefore, the study of rolling bearing fault diagnosis is very important realistic significance and necessity. In this paper, we collect the bearing vibration signals by the sensor, and use wavelet threshold method to reduce the noise of the rolling bearing vibration signal wavelet and to remove the interference signal of signals. Then we use the wavelet packet technology to extract the energy band of noise signals. The energy spectrum feature vectors are extracted from the individual frequency bands, and they are set as the input vectors of SVM. Finally, the running condition of the rolling bearing is diagnosed intelligently by the analysis method of SVM.