Research on IPSO-RBF transformer fault diagnosis based on Adam optimization. Issue 1 (1st June 2022)

• Record Type: Journal Article
• Authors: Shao, Ningning; Chen, Xiaoqiang; Wang, Ying
• Is Part Of: Journal of physics. Volume 2290:Issue 1(2022)
• Publication Date: 2022-06-01
• Subjects: Physics -- Congresses; 530.5
• DOI: 10.1088/1742-6596/2290/1/012117
• Languages: English
• ISSNs: 1742-6588

Abstract

Abstract: As the lifeblood element of the power system, the transformer plays a pivotal role in power transmission and voltage conversion. The fault prediction of the transformer can not only realize the early warning before the fault but also provide theoretical support for the formulation of a transformer maintenance scheme, which can improve the safety and reliability of the power system. In this paper, a new method of transformer fault diagnosis based on dissolved gas in oil is proposed by combining the Adam optimization algorithm based on the classical momentum concept with the PSO algorithm. Firstly, a PSO-RBF transformer fault diagnosis model is constructed. Through the simulation experiment of nonlinear collocation of acceleration factors, the nonlinear exponential decreasing collocation is used to improve the optimization ability of particle swarm optimization. The simulation analysis is carried out based on the transformer fault data within the jurisdiction of Lanzhou electric power company. The diagnosis results verify that the diagnosis rate and stability of the IPSO-RBF-Adam transformer fault diagnosis model are better than the PSO-RBF model.