The Application Of The Improved LS-SVM In Fault Forecasting And Diagnosis Of Transformer

As the ultimate element in the electric power system, the safe of operating of transformer is correlative with the safety of the power system, so the fault forecasting and diagnosis of transformer is of great importance to the experts on the field of the power system.On the bases of oil chromatographic analysis, this paper introduces the prediction model and diagnosis model based on improved least square support vector machine based on the improved genetic algorithm. It improves the effects of the forecasting, and the precision greatly. The results show that: the accuracy of the LS-SVM based on the IGA is better than traditional LS-SVM models.At last,using VC # and SQL base on .NET platform and C / S developing a MIS of the transformer fault diagnosis and prediction. The system improves the maintenance efficiency of the state of information management.