Demagnetization Fault Location of Direct-Drive Permanent Magnet Synchronous Motor Based on Search Coil Data-Driven

Demagnetization faults in direct-drive permanent magnet synchronous motors (DDPMSM) can cause significant performance degradation and unplanned downtime. Traditional fault location methods, which rely on manual feature extraction, exhibit limited accuracy and efficiency in complex and variable operating conditions. To address these limitations, this study presents a demagnetization fault location method based on a search coil employing a data-driven one-dimensional convolutional neural network (1D-CNN). Firstly, the arrangement of search coils was determined, and a partitioned mathematical model was established, using the residual back electromotive force (back-EMF) of the search coil over a single electrical cycle as the fundamental unit. Secondly, the residual back-EMF in the search coil is analyzed under various demagnetization parameters and operating conditions to assess the robustness of the proposed method. Furthermore, a 1D-CNN-based fault location model was developed using residual back-EMF signals as the input and targeting the identification of demagnetized permanent magnet types. Simulation and experimental results demonstrate that the proposed method can effectively detect and locate demagnetization faults across different operating conditions. When the demagnetization degree is not less than 10%, the fault location accuracy reaches 99.58%, and the minimum detectable demagnetization degree is 8%. The approach demonstrates excellent robustness and generalization, offering an intelligent solution for demagnetization fault location in PMSMs.