Fault diagnosis of turbo-generator based on support vector machine and genetic algorithm

Support vector machine (SVM) can overcome the drawbacks of artificial neural network, which has been widely used for pattern recognition in recent years. In the study, a novel method based on support vector machine and genetic algorithm (GA-SVM) model is adopted to fault diagnosis of turbo-generator, in which genetic algorithm (GA) dynamically optimizes the values of SVM´s parameters C and o. The real data sets are used to investigate its feasibility in fault diagnosis of turbo-generator. The experimental results show that GA-SVM has higher diagnostic accuracy than BP neural network.