Support vector machine with genetic algorithm for forecasting of key-gas ratios in oil-immersed transformer

Failures of power transformer are related with key-gas ratios C2H2/C2H4, CH4/H2 and C2H4/C2H6 strongly. Forecasting of these ratios of key-gas in power transformer oil is very significant to detect and identify incipient failures of transformer early. Forecasting of the ratios of key-gas in power transformer oil is a complicated problem due to its non-linearity and the small quantity of training data. In this study, support vector machine with genetic algorithm (SVMG) is proposed to forecast the ratios of key-gas in power transformer oil, among which genetic algorithm (GA) is used to determine free parameters of support vector machine. The experimental results indicate that the SVMG method can achieve greater accuracy than grey model, artificial neural network under the circumstance of small training data. Consequently, the SVMG model is a proper alternative for forecasting of the ratios of key-gas in power transformer oil.