Gearbox fault diagnosis method based on SVM trained by improved SFLA

A method of fault diagnosis based on support vector machine trained by the improved shuffled frog leaping algorithm (ISFLA-SVM) is proposed to promote the classification accuracy of the wind turbine gearbox fault diagnosis. Because the parameter selection for penalty factor and kernel function in support vector machine (SVM) have a great impact on the classification accuracy, we may use the improved shuffled frog leaping algorithm to select excellent SVM parameters, use the optimized parameters to train machine. Then three groups of data in UCI are used for performance evaluation. Finally ISFLA-SVM model will be applied to the wind turbine gearbox fault diagnosis. The result of the diagnosis indicates that the common fault of wind turbine gearbox can be exactly identified by this method. © Springer-Verlag Berlin Heidelberg 2014.