基于多元精细复合多尺度波动散布熵和累积欧氏距离矩阵测度的风电机组变桨轴承退化状态评估  

Degradation State Evaluation of Wind Turbine Generator Set Pitch Bearing Based on Multivariant Refined Composite Multiscale Fluctuation Dispersion Entropy and Cumulative Euclidean Distance Matrix Measure

作　　者：王晓龙[1,2] 李英晟 付锐棋 何玉灵[1,2] WANG Xiaolong;LI Yingsheng;FU Ruiqi;HE Yuling(Department of Mechanical Engineering,North China Electric Power University,Baoding 071000,Hebei Province,China;Hebei Key Laboratory of Electric Machinery Health Maintenance and Failure Prevention,North China Electric Power University,Baoding 071000,Hebei Province,China)

机构地区：[1]华北电力大学机械工程系,河北保定071000 [2]华北电力大学河北省电力机械装备健康维护与失效预防重点实验室,河北保定071000

出　　处：《动力工程学报》2024年第5期782-791,共10页Journal of Chinese Society of Power Engineering

基　　金：国家自然科学基金资助项目(52005180);河北省自然科学基金资助项目(E2022502003);河北省高等学校科学技术研究资助项目(QN2022190);中央高校基本科研业务费专项资金资助项目(2023MS127)。

摘　　要：针对风电机组变桨轴承服役过程环境噪声干扰严重、退化状态评估精度低的问题,提出一种基于多元精细复合多尺度波动散布熵和累积欧氏距离矩阵测度的退化状态评估模型。该模型将监测数据状态特征获取过程由单通道拓展为多通道进行,通过提出的多元精细复合多尺度波动散布熵算法来获取多通道监测数据的多尺度状态特征,并将累积和检验算法与欧氏距离矩阵测度方法相结合,用于定量衡量基准样本与待分析样本间的差异,从而实现变桨轴承退化状态评估。风电机组变桨轴承全寿命周期加速疲劳实验验证结果表明:该模型能够及时捕捉到变桨轴承的初始退化时刻并且准确跟踪整个退化过程。To solve the problems of serious environmental noise interference and low degradation state evaluation accuracy of wind turbine generator set pitch bearing during its service process,a degradation state evaluation model combining multivariant refined composite multiscale fluctuation dispersion entropy and cumulative Euclidean distance matrix measure was proposed.In this model,the feature acquisition process of monitoring data was expanded from single channel to multi-channels,and the multiscale features of multichannel monitoring data were extracted through the proposed multivariant refined composite multiscale fluctuation dispersion entropy algorithm.Then the combination of cumulative sum verification algorithm and Euclidean distance matrix measure was used to evaluate the difference between the benchmark samples and analyzed samples,and the degradation state evaluation of pitch bearing was realized.The verification results of whole life cycle accelerated fatigue experiment of wind turbine generator set pitch bearing show that the initial degradation moment of pitch bearing can be captured timely,and the whole degradation process can be accurately tracked using this proposed model.

关 键 词：风电机组 变桨轴承 退化状态评估 多元精细复合多尺度波动散布熵 累积欧氏距离矩阵测度 

分 类 号：TM315[电气工程—电机]