Fault Diagnosis of Power Equipment Based on Improved SVM Algorithm

Fault diagnosis of power equipment is a crucial task to credit the safe and stable operation of equipment. However, fault diagnosis of power equipment faces challenges such as high dimensionality, complexity, and nonlinearity. Therefore, this study proposes an improved support vector machine model, combined with grey wolf optimization algorithm, aimed at improving the accuracy and efficiency of power equipment fault diagnosis. To validate the model’s performance, this study divided a dataset of 3870 power equipment defects into training and testing sets using an 8:2 ratio, with evaluation metrics including accuracy, recall, and F1 score. The results showed that the fault recognition rate of the support vector machine model based on the improved grey wolf optimization algorithm reached 92.76%, with an accuracy close to 0.95 and a loss rate of 0.13. The model exhibited faster convergence speed, as well as better stability and convergence. At the same time, the optimized model had good feature extraction ability on different types of model faults, and the comprehensive recognition error of the model was basically stable in the interval of (-0.005, 0.005). The experiment validates that the research model improves the optimization algorithm through modal decomposition strategy. Meanwhile, the improvement of support vector machine parameter selection has strengthened the recognition and analysis of fault characteristics, providing an effective solution for power equipment fault diagnosis.