基于AFMD和SVDD的风电机组变桨轴承损伤识别  

DAMAGE IDENTIFICATION OF WIND TURBINE PITCH BEARING BASED ON AFMD AND SVDD

作　　者：王晓龙[1] 张博文 金韩微 付锐棋 杨秀彬 吴鹏[2] Wang Xiaolong;Zhang Bowen;Jin Hanwei;Fu Ruiqi;Yang Xiubin;Wu Peng(Department of Mechanical Engineering,North China Electric Power University,Baoding 071003,China;Engineering Training and Innovation and Entrepreneurship Education Center,North China Electric Power University,Baoding 071003,China)

机构地区：[1]华北电力大学机械工程系,保定071003 [2]华北电力大学工程训练与创新创业教育中心,保定071003

出　　处：《太阳能学报》2025年第3期514-523,共10页Acta Energiae Solaris Sinica

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

摘　　要：针对风电机组变桨轴承损伤识别问题,提出基于自适应特征模态分解和奇异值分解降噪的损伤识别方法。该方法首先利用龙格库塔优化策略对特征模态分解算法中的频带数量及滤波器长度参数进行搜索,确定最优参数组合后对原始振动信号进行自适应特征模态分解,从中提取出蕴含丰富特征信息的模态分量;继而计算出所提取模态分量的包络信号并做进一步奇异值分解降噪处理,从而增强包络信号的信噪比;最后对比理论损伤特征频率及包络谱中幅值突出的频率成分,用于判断变桨轴承的故障损伤。实验数据分析结果表明,所提方法能从复杂原始振动信号中有效提取出微弱特征信息,实现变桨轴承损伤部位的准确甄别,具有一定工程参考借鉴价值。Aiming at the problem of damage identification of pitch bearings of wind turbine,a damage identification method based on adaptive feature mode decomposition and singular value decomposition denoising is proposed.Firstly,Runge kutta optimization is used to search for the frequency band number and the filter length parameters of the feature mode decomposition algorithm,then the optimal combination of influencing parameters is determined and the original vibration signal is processed by adaptive feature mode decomposition,and the mode component containing rich feature information is extracted.Subsequently,the envelope signal of the extracted mode component is calculated and the singular value decomposition denoising is further operated to enhance the signal-tonoise ratio of the envelope signal.Finally,the theoretical damage characteristic frequency and the frequency component with prominent amplitude in the envelope spectrum are compared to judge the fault damage of the pitch bearing.Experimental data analysis results show that the proposed method can effectively extract weak feature information from complex original vibration signal and accurately identify the damage part of pitch bearing,which has certain engineering reference value.

关 键 词：风电机组 变桨轴承 损伤识别 自适应特征模态分解 奇异值分解降噪 

分 类 号：TH17[机械工程—机械制造及自动化]