LS-SVM Parameter Optimization Using Genetic Algorithm To Improve Fault Classification Of Power Transformer

摘要

The LS-SVM (least square support vector machines) is applied to solve the practical problems of small samples and non-linear prediction better and it is suitable for the DGA in power transformers. The selection of the parameters, impact on the result of the diagnosis greatly, so it is necessary to optimize these parameters. The parameters of Support Vector Machine are optimized using GA (Genetic Algorithm). The GA generates the initial population randomly, expands the search space fast and improves the global search ability and convergence speed. Finally, the optimized LS-SVM is used for analysis of multiple sets of DGA (Dissolved gas analysis) data of transformers, the results show that the accuracy of fault diagnosis has been effectively improved