An intelligent monitoring system for wind turbine blades based on machine learning uses high-precision sensors to acquire blade vibration and strain signals in real time,and preprocesses data by wavelet packet Decomposition and Empirical Mode Decomposition(EMD).On this basis,the improved Convolutional Neural Network(CNN)model is used to diagnose the fault types of the blades,and the remaining service life of the blades is predicted by the physical model.The experimental results show that the system still has good diagnosis and prediction performance under complex working conditions,the fault diagnosis accuracy is up to 98.7%,and the service life prediction error is less than 5%,which provides a new idea for intelligent operation and maintenance of wind turbines.
维普
万方数据