AC Motor Fault Diagnosis Based on Multi-Source Signal Fusion SDP

In order to solve the problem of the limited ability of a single signal to characterize the fault state of AC motors, this paper proposes an AC motor fault diagnosis method based on multi-source signal fusion SDP (Symmetric Dot Pattern). Firstly, the current and vibration signals acquired from the AC motor and converted to image by SDP image conversion method. Then, an adaptive parameter selection method is employed to adaptive acquire the optimal parameters to amplify the image differences between different fault states. Finally, the fault diagnosis model is built by AlexNet for diagnosing AC motor faults. To validate the effectiveness of the proposed method, it was tested on an AC motor fault experimental platform. The experimental results indicate that the proposed method diagnostic accuracy is 99.16%. By comparing with a single-signal source, the proposed method has the highest accuracy, further validating the advancement of the proposed method. This study provides an efficient and feasible diagnostic method for AC motor fault diagnosis.