Intelligent Fault Diagnosis Based on Vibration and Acoustic-monitored Data Fusion for Rolling Bearings

The signals of different modes often contain different information and reflect different aspects of the detected system. In the fault diagnosis of rolling bearings, the feature fusion of multimodal signals can make the diagnosis result more accurate and more robust. Therefore, the vibration signal and acoustic signal of the rolling bearing are adopted, and the 8-dimensional energy features of the two signals are extracted respectively by the wavelet packet transform (WPT) method. Then the features of the two modes are fused, and the fused feature vector is input to the K-nearest neighbors (KNN) classifier for fault classification. Experimental results show that the proposed method is superior to the single-mode signal fault diagnosis method, which shows the effectiveness and superiority of multimodal feature fusion.