The Performance of Electronic Current Transformer Fault Diagnosis Model: Using an Improved Whale Optimization Algorithm and RBF Neural Network

With the widely application of electronic transformers in smart grids, transformer faults have become a pressing problem. However, reliable fault diagnosis current (ECT) is still an open problem due to complexity and diversity types. In order solve this problem, paper proposes ECT model based on radial basis function neural network (RBFNN) optimizes parameters size RBFNN simultaneously via improved whale optimization algorithm (WOA) improve classification accuracy robustness RBFNN. Since classical WOA easy fall into locally optimal performance, hybrid multi-strategies (CASAWOA) proposed for further improvement performance. Firstly, we introduced tent chaotic map strategy population WOA. Secondly, nonlinear convergence factor adaptive inertia weight enhance exploitation ability Finally, premise ensuring speed algorithm, modified simulated annealing mechanism prevent premature convergence. The benchmark tests show that CASAWOA outperforms other state-of-the-art algorithms terms exploration ability. Furthermore, validate performance CASAWOA-RBFNN, comprehensive analysis eight methods conducted samples collected from detection circuit. experimental results CASAWOA-RBFNN achieves 97.77% diagnosis, which 9.8% better than WOA-RBF shows promising engineering practicality.