摘要
由于行星齿轮齿轮箱的振动信号具有非平稳、非线性特性,在复杂工况下,会对其早期微弱的故障信号造成干扰,不能正确地识别出故障信息。为解决以上问题,采用基于变分模态分解(variational mode decomposition,VMD)与灰狼优化支持向量机的故障诊断方法。利用中心频率近似方法,求解出了变分模态分解的参数K,对分解出的本征模态函数(intrinsic mode function,IMF)分量进行相关性分析,优选出分量进行信号重构。将重构信号进行故障特征提取,利用灰狼优化支持向量机的方法进行故障模式识别。实验结果表明:采用所提方法对行星齿轮箱的故障识别准确率达到99.375%。
Because the vibration signal of planetary gear box has the characteristics of non-stationary and nonlinear,which will cause interference to its early weak fault signal under complex working conditions,the fault information can not be correctly identified.In order to solve the above problems,a fault diagnosis method was adopted based on variational mode decomposition(VMD)and grey wolf optimized support vector machine(SVM).Using the method of approximating center frequency,the K-parameter of variational mode decomposition was solved.Then,the correlation analysis of the decomposed intrinsic mode function(IMF)components was carried out,and the components were optimally selected for signal reconstruction.The fault features were extracted from the reconstructed signals and input into grey wolf optimized support vector machine for fault classification.The experimental results show that the fault identification accuracy of planetary gearbox with the proposed method is 99.375%.
作者
吴正豪
白华军
闫昊
展先彪
温亮
贾希胜
WU Zheng-hao;BAI Hua-jun;YAN Hao;ZHAN Xian-biao;WEN Liang;JIA Xi-sheng(Shijiazhuang Campus,Army Engineering University of PLA,Shijiazhuang 050003,China)
出处
《科学技术与工程》
北大核心
2023年第16期6881-6888,共8页
Science Technology and Engineering
基金
国家自然科学基金(71871220)。
