CFOA-VMD Based Soft Fault Diagnosis Method for Power Electronic Circuits

The performance degradation caused by soft faults in power electronic circuits has become a key bottleneck affecting system reliability. Aiming at the shortcomings of traditional fault diagnosis methods in terms of their insufficient sensitivity to weak features and the excessive influence of Variable Modal Decomposition (VMD) parameters on the results, this paper proposes a framework based on the Catch-Fishing Optimisation Algorithm (CFOA) collaborating with the Variable Modal Decomposition (VMD) and Support Vector Machines (SVM) for the soft fault diagnosis of power electronic circuits. fault diagnosis framework. The method dynamically optimises the number of modes (K) and the penalty factor (<tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\alpha$</tex>) of VMD by CFOA to achieve adaptive multi-scale decomposition of fault signals. On this basis, hybrid features based on the time-frequency characteristics of modal components are constructed, and SVM is used to train the classifier to complete the fault diagnosis. Experimental results show that the proposed method has high diagnostic accuracy and robustness in soft fault diagnosis of power electronic circuits.