Optimization of Transformer Fault Diagnosis Using Least Squares Support Vector Machine Based on Improved Bald Eagle Search

To solve the problem of low accuracy in fault diagnosis of oil immersed transformers, a transformer fault diagnosis method based on improved bald eagle search algorithm optimized least squares support vector machine is proposed. Aiming at the problem of difficulty in selecting the optimal values of the penalty factor γ and kernel function parameter σ based on manual experience and low fault diagnosis accuracy in least squares support vector machines, an improved Bald Eagle Search (IBES) algorithm is proposed to optimize its parameters. The results indicate that the proposed method has the characteristics of high diagnostic accuracy, simple model, and strong generalization ability.