Affiliations: [a] College of Electrical and Information Engineering, Beihua University, Jilin, China
| [b] College of Mechanical and Electrical Engineering, Guangdong University of Science and Technology, Guangdong, Dongguan, China
| [c] Department of Mathematics, Faculty of Science, Tanta University, Tanta, Egypt
Correspondence:
[*]
Corresponding author. Dongmei Hu, College of Electrical and Information Engineering, Beihua University, Jilin 132021, China. E-mail: [email protected].
Abstract: To solve the problem that the operation state of transformer is difficult to quantify, a method of quantitative evaluation and prediction of transformer operating state is proposed, which combines the information entropy of matter element and Support Vector Machine. In the evaluation, various hydrogen gases in the transformer operation are taken as the evaluation indexes and the three-dimensional cross compound element is constructed. The analytic hierarchy process (AHP) is used to determine the theoretical weight of the evaluation index, and the entropy method is used to determine the objective weight of the evaluation index, and the final weight is the joint weight of the theoretical weight and the objective weight. Transformer Health index is calculated by using complex element correlation entropy. In prediction, the grid search, genetic algorithm (GA) and particle swarm optimization (PSO) are used to optimize the parameters of Support Vector Machine. and the prediction model of Health index is established by SVM. Experiment results show that the Support Vector Machine based on Gauss kernel function and genetic algorithm has a prominent effect on the prediction of health index.
Keywords: Transformer, health index, analytic hierarchy process (AHP), matter element information
entropy, support vector machine (SVM)
