Classification of faults in nuclear power plant

In this paper, the performance of traditional Support Vector Machine (SVM) is improved using Genetic Algorithm (GA). GA is used to determine the optimal values of SVM parameters that assure highest predictive accuracy and generalization ability simultaneously. The proposed scheme, called Support Vector Machine Genetic Algorithm (SVM-GA) Scheme, is applied on a beforehand data of a Nuclear Power Plant (NPP) to classify its associated faults. Compared to the standard SVM model, simulation of SVM-GA indicates its superiority when applied on the dataset with unbalanced classes. SVM-GA scheme can gain higher classification with accurate and faster learning speed.