Transformer Fault Diagnosis Technology Based on Maximally Collapsing Metric Learning and Parameter Optimization Kernel Extreme Learning Machine.

Aiming at the problem of unsatisfactory diagnosis performance of conventional fault diagnosis methods for transformer, a novel method based on maximally collapsing metric learning algorithm (MCML) and parameter optimization kernel extreme learning machine (KELM) is proposed in this study. First, a new set of dissolved gas analysis (DGA) features combination, which can reflect the transformer fault information, is used to form the input feature space. Then, the MCML is employed to reduce the feature space dimension to extract a set of optimal DGA features combination. Finally, the salp swarm algorithm (SSA) is utilized to optimize the parameters in KELM to establish an SSA‐KELM model, which is adopted to diagnose and identify transformer faults. The proposed method is applied to the International Electrotechnical Commission (IEC) TC 10 database, and the results show that the feature extraction effect of MCML is superior than that of linear discriminant analysis, neighborhood preserving embedding, and Laplacian eigenmaps. The optimal DGA feature set is more advantageous than the frequent‐used DGA data, IEC ratios, Rogers ratios, and Doernenburg Ratios. The diagnosis accuracy of SSA‐KELM is better than that of KELM, particle swarm optimization‐KELM, genetic algorithm‐KELM, and loin swarm optimization‐KELM. Furthermore, the generalization and robustness ability of the MCML and SSA‐KELM is confirmed by the China DGA samples, the obtained results verify the reliability and validity of the proposed method again. © 2022 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC. [ABSTRACT FROM AUTHOR]