REMAINING USEFUL LIFE PREDICTION OF WIND TURBINE BLADES BASED ON OPTIMIZED LSTM MODEL
Aiming at the problems of complex calculation,time consuming and inapplicability of traditional life prediction methods,a wind turbine blade remaining useful life(RUL)prediction model based on optimized Long Short-Term Memory(LSTM)is proposed.In this study,the multidimensional sensor monitoring data were visualized to observe the data features and perform initial feature screening.Then,the filtered data were normalized and the data were fused using principal component analysis(PCA)to remove redundant information and reduce feature dimensionality.Furthermore,the adaptive moment estimation(AME)algorithm was employed to provide independent adaptive learning rates for different network parameters,and the smoothed mean absolute error(SMAE)loss function was utilized to synthesize the characteristics of two traditional regression loss functions.After several experiments,the optimal number of LSTM layers and neurons was selected.The model was experimentally validated using multi-scale time-series monitoring data of complex systems as an arithmetic example.The experimental results demonstrate that the optimized LSTM prediction model outperforms other traditional machine learning models in terms of evaluation index and prediction error distribution under one fault mode.This indicates that the proposed model offers higher accuracy and stability.
wind turbine bladesprincipal component analysisLong short-term memorylife predictionprediction model
NETL
NSTL
万方数据
