%0 Journal Article
%T ITD-多尺度熵和ELM的风电轴承健康状态识别<br>Health Status Recognition of Wind Turbine Bearings based on ITD-MSE and ELM
%A 张朝林
%A 范玉刚
%A 冯早
%J 机械科学与技术
%D 2018
%X 对风力发电机机组的运行状况进行实时监测，并识别其健康状态，是保证机组正常运行的关键，为此提出一种固有时间尺度分解（Intrinsic time-scale decomposition，ITD）-多尺度熵（Multiscale entropy，MSE）的振动信号分析方法，对振动信号进行预处理，提取重构信号时域特征，并结合极限学习机（Extreme learning machine，ELM）对风电轴承健康状态进行识别。首先采用ITD方法对风电轴承的振动信号进行分解，得到一系列固有旋转分量，并计算其多尺度熵值，以多尺度熵值大小为依据，选取固有旋转分量并进行信号重构。计算重构信号的均方根值、峭度值、峰值因子与峰峰值，并将其作为特征指标值，建立ELM识别模型，识别风电轴承的健康状态。风电轴承试验结果表明，本文模型可以准确识别风电轴承健康状态。<br>In order to detect the operation fault of wind turbine in real-time and recognize its health status of the unit, a bearing health status recognition method based on vibration signal analysis using ITD (Intrinsic time-scale decomposition)-MSE (multiscale entropy)is proposed in this paper. The method is applied to ensure that the vibration signal is pretreated, and the time domain characteristics of the reconstructed signal are extracted, the ELM (Extreme learning machine) is then adopted to recognize the health status of wind turbine bearings. Firstly, the vibration signal of wind turbine bearings is decomposed using ITD to obtain a series of inherent rotation components. Then, MSE is calculated and used as a standard to select relevant components to reconstruct the signal. Afterwards, the reconstructed signals' RMS, kurtosis, crest factor and peak-to-peak value are calculated to input to the ELM model. Finally, the ELM model is established and the health status of wind turbine bearings can be recognized. The experimental results have shown that the proposed method is capable of recognizing the health status of wind turbine bearings accurately
%K 风电轴承
%K 固有时间尺度分解
%K 多尺度熵值
%K 极限学习机
%K 健康状态识别&lt
%K br&gt
%K wind turbine bearing
%K ITD
%K MSE
%K ELM
%K health status recognition
%U http://journals.nwpu.edu.cn/jxkxyjs/CN/abstract/abstract7169.shtml