Research on Fault Diagnosis Method of Electrical Engineering Equipment Based on Fuzzy Neural Network

In this paper, a fuzzy neural network (FNN) based fault diagnosis method for electrical engineering equipment is proposed. The method generates a training sample set and a test sample set by collecting the operation data of electrical equipment, and extracts and classifies the fault features using a fuzzy neural network model. The structural configuration, parameter optimization and training process of the fuzzy neural network are analyzed in detail in the study, the cross-entropy is used as the optimization objective function, and the Adam algorithm is selected for training. By analyzing the fault cases of transformers and transmission lines, the results show that the diagnostic accuracy of this method reaches 99.20% and 98.15% for fault lines and fault types, respectively. In addition, this paper also explores the effect of noise interference on the fault diagnosis effect, and the results show that the method has anti-interference ability to a certain extent. Finally, through the comparative analysis with traditional machine learning and deep learning methods, the advantages of the fuzzy neural network-based fault diagnosis method in terms of accuracy and robustness are verified, which provides reliable technical support for the safe operation of the power system.