Online faults diagnosis of wind turbine blades based on support vector machines

In this paper, an online fault diagnosis method of wind turbine blades that is based on SVM (support vector machines) is proposed. First, it uses normalized real-time data of temperature, humidity, brightness and brightness of wind turbine blades to construct feature vectors. Then based on SVM, online fault diagnosis of wind turbine blades can be implemented. Three type of faults which are skin cracking, leading edge cracking, tailing edge cracking are used to verify the method. The results show that it can achieve the expected effect.