A Fault Diagnosis Method of Oil-Immersed Transformer Based on Improved Harris Hawks Optimized Random Forest

In order to improve the accuracy and reliability of fault diagnosis for oil-immersed transformers, a fault diagnosis method for oil-immersed transformers based on improved Harris Hawks optimized random forest is proposed in this paper. First, logistic chaotic mapping is used to adjust the key parameters of the algorithm; then a nonlinear energy factor adjustment strategy is used to control the algorithm to transition from global search to local search; finally, the method of Gaussian mutation is introduced to strengthen the local search ability, and when the algorithm is stagnant, firefly perturbation is performed on the optimal solution to make the algorithm jump out of local optimum. The number of n_trees and n_layers of the random forest are jointly optimized by the improved Harris Hawks optimization algorithm, and the fault diagnosis model of oil-immersed transformer is established. The noncoded ratios of dissolved characteristic gases in oil are used as the characteristic input of the diagnosis model to obtain the final diagnosis results. Compared with other models and verified by examples, the results show that the proposed method has the advantage of high diagnostic accuracy and has certain practical engineering application value.