Fault diagnosis of power transformer based on support vector machine with genetic algorithm |
| |
| Authors: | Sheng-wei Fei Xiao-bin Zhang |
| |
| Affiliation: | 1. School of Mechanical Engineering, Shanghai Jiaotong University, Shanghai 200240, China;2. Guangxi Special Equipment Supervision and Inspection Institute, Nanning 530022, China;1. Research Laboratory, Matériaux, Mesures et Applications (MMA), INSAT, Tunisia;2. Institut National des Sciences Appliquées et de Technologie (INSAT), Carthage University, Tunisia;3. Research Laboratory, LR-SITI, Ecole National d’Ingénieurs de Tunis (ENIT), Tunisia;1. Electrical Engineering Department, Faculty of Engineering, Ferdowsi University of Mashhad, Mashhad, Iran;2. Institute of Electric Power Systems, Division of High Voltage Engineering and Asset Management, Schering-Institute, Leibniz University of Hannover, Hannover, Germany;1. Group 203, School of Electronic and Information Engineering, Beihang University, Beijing 100191, China;2. Chair on Systems Science and the Energetic Challenge, European Foundation for New Energy-Electricité de France, Ecole Centrale Paris and Supelec, Paris, France;3. Dipartimento di Energia, Politecnico di Milano, Milano, Italy;1. School of Electronic and Information Engineering, Group 203, Beihang University, Beijing 100191, China;2. Department of Energy, Polytechnic of Milan, Via Ponzio 34/3, 20133 Milan, Italy;3. Ecole Central Paris et Supelec, Paris, France;1. Harbin Institute of Technology, Harbin, China;2. Bohai University, Jinzhou, China |
| |
| Abstract: | Diagnosis of potential faults concealed inside power transformers is the key of ensuring stable electrical power supply to consumers. Support vector machine (SVM) is a new machine learning method based on the statistical learning theory, which is a powerful tool for solving the problem with small sampling, nonlinearity and high dimension. The selection of SVM parameters has an important influence on the classification accuracy of SVM. However, it is very difficult to select appropriate SVM parameters. In this study, support vector machine with genetic algorithm (SVMG) is applied to fault diagnosis of a power transformer, in which genetic algorithm (GA) is used to select appropriate free parameters of SVM. The experimental data from several electric power companies in China are used to illustrate the performance of the proposed SVMG model. The experimental results indicate that the SVMG method can achieve higher diagnostic accuracy than IEC three ratios, normal SVM classifier and artificial neural network. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
