Research on Power Cable Fault Diagnosis Based on Sparrow Search Algorithm

With the increasing complexity of power systems, power cable fault diagnosis has become an urgent issue that needs to be addressed. Timely diagnosis of power cable faults is crucial to ensuring the stability and safety of power systems. However, traditional fault diagnosis methods often have certain limitations in terms of accuracy and efficiency. The aim of this study is to propose a power cable fault diagnosis method optimized by the SSA, in order to improve the accuracy and real-time performance of fault diagnosis. We first combine the Sparrow Search Algorithm (SSA) with the fault diagnosis model, optimizing the selection of fault features to improve diagnostic accuracy. The effectiveness of this method is verified through experiments, comparing the performance of different algorithms. BP, SSA, and SSA-BP algorithms are used to evaluate fault diagnosis accuracy as a fitness function to intuitively reflect the model's fitting effect. Through optimization experiments and comparisons, we analyze the differences in performance of the three algorithms in hyperparameter tuning. Experimental results show that the fault diagnosis method optimized by the SSA outperforms traditional fault diagnosis methods in terms of accuracy. The SSA-BP model shows strong advantages in evaluation metrics such as Precision, Recall, and F1 score, with Precision at 98.02%, Recall at 99.01%, and F1 score at 98.02%. The results demonstrate that SSA-BP has high accuracy and stability in power cable fault diagnosis, effectively improving the reliability and practicality of fault diagnosis.