基于小波降噪和BP神经网络的风力发电机组齿轮箱故障诊断研究

Research on Fault Diagnosis of Wind Turbine Gearbox Based on Wavelet Denoising and BP Neural Network

针对风电机组齿轮箱故障频发这一现象,为改善设备性能,提高其利用率,采用基于小波降噪和BP神经网络相融合进行风电机组齿轮箱故障诊断与研究的方案.首先利用小波对采样数据降噪,然后输入小波神经网络中进行诊断,以准确地识别齿轮箱中常见的故障,结果表明该方案具有可行性.并结合风电场应用实例,证明了方案的可行性,为提高风力发电机组齿轮箱的稳定性提供了一种有效方法.

In order to improve the performance of the wind turbine gearbox and improve its utilization rate,the fault diagnosis and research of wind turbine gearbox based on wavelet denoising and BP neural network fusion is adopted.In this paper,the wavelet is used to denoise the sampled data,and then input into the wavelet neural network for diagnosis to accurately identify the common faults in the gearbox.The results show that the scheme is feasible.Combined with the application examples of wind farms,the feasibility of the scheme is proved,which provides an effective method for improving the stability of wind turbine gearbox.