Fault Diagnosis of Switching Power Supplies Using Dynamic Wavelet Packet Transform and Optimized SVM.

Switch mode power supplies (SMPSs) are prone to various faults under complex operating environments and variable load conditions. To improve the accuracy and reliability of fault diagnosis, this paper proposes an intelligent diagnosis method based on Dynamic Wavelet Packet Transform (DWPT) and Improved Artificial Bee Colony Optimized Support Vector Machine (APABC-SVM). First, an adaptive wavelet packet decomposition mechanism is used to refine the time-frequency feature extraction of the signal to improve the feature differentiation. Then, a dynamic window statistics method is introduced to construct comprehensive dynamic feature vectors to capture the transient changes in fault signals. Finally, the APABC is used to optimize the SVM classifier parameters to improve the classification performance and avoid the local optimum problem. The experimental results show that the method achieves an average accuracy of 99.091% in the complex fault diagnosis of switching power supplies, which is 21.8 percentage points higher than that of the traditional spectrum analysis method (77.273%). This study provides an efficient solution for the accurate diagnosis of complex fault modes in switching power supplies.