基于IWOA-VMD-MCKD模型的齿轮箱轴承故障诊断  

Fault Diagnosis of Gearbox Bearing Based on IWOA-VMDMCKD Model

作　　者：郭楠 滕伟[1] 陈晨 彭迪康 马志勇[1] 柳亦兵[1] Nan Guo;Wei Teng;Chen Chen;Di-kang Peng;Zhi-yong Ma;Yi-bing Liu(Key Laboratory of Power Station Energy Transfer Conversion and System,Ministry of Education,North China Electric Power University;China Datang Technological and Economic Research Institute Co.,Ltd.)

机构地区：[1]华北电力大学电站能量传递转化与系统教育部重点实验室 [2]中国大唐集团技术经济研究院有限责任公司

出　　处：《风机技术》2025年第2期59-66,共8页Chinese Journal of Turbomachinery

基　　金：国家自然科学基金(52105134)。

摘　　要：针对风电齿轮箱变工况和强噪声干扰条件下故障信号信噪比低,滚动轴承微弱故障特征难以提取的问题,提出一种结合改进鲸鱼优化算法(IWOA)、变分模态分解(VMD)和最大相关峭度解卷积(MCKD)的方法以提取滚动轴承的微弱故障特征。首先,引用Logistic混沌映射、余弦收敛因子和自适应权重改进鲸鱼优化算法(WOA);其次,IWOA利用最小平均包络熵为指标确定VMD与MCKD算法的最优参数,突出信号中的故障冲击成分;最后,通过包络谱提取出轴承故障特征频率。仿真数据和实际风场数据案例分析结果表明,该方法能够有效提取出强噪声背景下的滚动轴承微弱故障特征。Aiming at the problems of low signal-to-noise ratio of fault signals and being difficult to extract weak fault features of rolling bearings under variable working conditions and strong noise interference of wind turbine gearbox,a method based on improved whale optimization algorithm was proposed to optimize parameters and extract weak fault features of rolling bearings by combining variational mode decomposition(VMD)and maximum correlation kurtotic deconvolution(MCKD).Firstly,Logistic chaotic mapping,cosine convergence factor and adaptive weight improved whale optimization algorithm(WOA)are introduced.Secondly,IWOA uses the minimum average envelope entropy as the index to determine the optimal parameters of VMD and MCKD algorithms,and highlights the fault impact components in the signal.Finally,the bearing fault characteristic frequency is extracted by envelope spectrum.Simulation data and actual wind field data show that this method can effectively extract weak fault characteristics of rolling bearings under strong noise background.

关 键 词：变分模态分解 改进鲸鱼优化算法 最大相关峭度反卷积 故障诊断 齿轮箱轴承 

分 类 号：TH133.3[机械工程—机械制造及自动化]