Transformer fault identification based on GWO-optimized Dual-channel M-A method.

Autor: Ji N; Skill Training Center of State Grid Jiangsu Electric Power Co., Ltd., Suzhou, China., Chen X; Skill Training Center of State Grid Jiangsu Electric Power Co., Ltd., Suzhou, China., Qin X; Skill Training Center of State Grid Jiangsu Electric Power Co., Ltd., Suzhou, China., Wei W; Skill Training Center of State Grid Jiangsu Electric Power Co., Ltd., Suzhou, China., Jiang C; Skill Training Center of State Grid Jiangsu Electric Power Co., Ltd., Suzhou, China., Bo Y; Skill Training Center of State Grid Jiangsu Electric Power Co., Ltd., Suzhou, China., Tao K; College of Automation & College of Artificial Intelligence, Nanjing University of Posts and Telecommunications, Nanjing, China.
Jazyk: angličtina
Zdroj: PloS one [PLoS One] 2024 Oct 28; Vol. 19 (10), pp. e0312474. Date of Electronic Publication: 2024 Oct 28 (Print Publication: 2024).
DOI: 10.1371/journal.pone.0312474
Abstrakt: In order to improve the accuracy of the transformer fault identification using nature-inspired algorithms, an identification method based on the GWO (Grey Wolf Optimizer)-optimized Dual-channel MLP (Multilayer Perceptron)-Attention is proposed. First, a Dual-channel model is constructed by combining the AM (Attention Mechanism) and MLP. Subsequently, the GWO algorithm is used to optimize the number and the nodes of the hidden layer in the Dual-channel MLP-Attention model. Typical transformer faults are simulated using DDRTS (Digital Dynamic Real-Time Simulator) system. Experiments showed that the GWO- optimized method has an accuracy rate of 95.3%-96.7% in identifying the transformer faults. Compared with BP, SVM, MLP, and single-channel M-A models, the proposed method improved the accuracy by14.1%, 9.6%, 9.3%, and 3.3% respectively. This result indicates the rationality and effectiveness of the proposed method in transformer fault identification.
Competing Interests: The authors have declared that no competing interests exist.
(Copyright: © 2024 Ji et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)
Databáze: MEDLINE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje