可再生能源2017，Vol.35Issue(12)：1862-1868,7.
基于深度信念网络的风电机组齿轮箱故障诊断方法
Fault diagnosis method of wind turbine gearbox based on deep belief network
摘要
Abstract
In view of the existing problem of wind turbine fault diagnosis of large amount of data,the fault feature extraction difficulties,combined with the theory of deep learning strong perception and self-learning ability,a wind turbine gearbox fault diagnosis method based on deep belief networks is proposed. The original time domain signal data is input into the deep belief network to train,and the whole network is adjusted by reverse trimming to improve the classification accuracy. At the same time,Batch Normalization is added to the training process to reduce the chance of over fitting and improve the convergence speed of the network. This method is applied to the fault diagnosis of wind turbine planetary gearbox,and the results show that this method is more accurate than the traditional BP neural network algorithm and DBN.关键词
风电机组齿轮箱/深度信念网络/Batch Normalization/故障诊断Key words
wind turbine gear/deep belief network/batch normalization/fault diagnosis分类
能源科技引用本文复制引用
刘秀丽,徐小力..基于深度信念网络的风电机组齿轮箱故障诊断方法[J].可再生能源,2017,35(12):1862-1868,7.基金项目
国家自然科学基金项目(51275052) （51275052）
国家高技术发展研究计划项目(2015AA043702) （2015AA043702）
北京市教委科研计划项目(KM201611232020). （KM201611232020）
