自适应广义形态滤波和GG聚类在轴承故障识别中的应用研究
|
摘要
针对复杂工况下滚动轴承受机械噪声等因素影响轴承故障类型区分难的问题,提出了一种基于自适应广义形态滤波和GG聚类的轴承故障诊断方法。采用自适应广义形态滤波对轴承振动信号进行降噪处理,对降噪后的信号进行变模式分解,去除虚假分量和噪声分量,最后对去噪后故障特征较多的信号分量求解近似熵,作为特征向量输入GG聚类分类器中,达到故障分类。仿真实验结果证明该方法能有效提取信号特征信息,准确识别故障类型。
In order to improve the bearing type under the complicated working conditions and solve the difficulty to distinguish the bearing fault type,this paper proposes a bearing fault diagnosis method based on adaptive generalized morphological filtering and GG clustering. The method firstly uses adaptive generalized morphological filtering to denoise the bearing vibration signal,and then performs variable mode decomposition on the denoised signal to remove the false component and noise component. Finally,the signal component with more fault characteristics after denoising is solved by approximate entropy and is input into the GG cluster classifier as a feature vector to achieve the purpose of fault classification. The simulation results show that the method can effectively extract the signal characteristic information and accurately identify the fault type.
In order to improve the bearing type under the complicated working conditions and solve the difficulty to distinguish the bearing fault type,this paper proposes a bearing fault diagnosis method based on adaptive generalized morphological filtering and GG clustering. The method firstly uses adaptive generalized morphological filtering to denoise the bearing vibration signal,and then performs variable mode decomposition on the denoised signal to remove the false component and noise component. Finally,the signal component with more fault characteristics after denoising is solved by approximate entropy and is input into the GG cluster classifier as a feature vector to achieve the purpose of fault classification. The simulation results show that the method can effectively extract the signal characteristic information and accurately identify the fault type.
引文
[1]陈俊洵,程龙生,胡绍林,等.基于EMD的改进马田系统的滚动轴承故障诊断[J].振动与冲击,2017(5):151-156.
[2] HUANG N E,SHEN Z,LONG S R,et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear andnon-stationary time series analysis[J]. Proceedings of the Royal Society A Mathematical Physical&Engineering Sciences,1998,454(1971):903-995.
[3] WU Zhao-hua,HUANG N E,CHEN Xian-yao. The Multi-dimensional ensemble empirical mode decomposition method[J].Advances in Adaptive Data Analysis,2014,1(3):0900018
[4]姚刚,赵建军,姚跃亭,等.基于改进EMD方法的系统误差分离方法研究[J].振动与冲击,2014,33(14):176-180.
[5]胥永刚,孟志鹏,陆明.基于双树复小波包变换和SVM的滚动轴承故障诊断方法[J].航空动力学报,2014,29(1):67-73.
[6]任学平,庞震,辛向志,等.基于小波包最优熵与RVM的滚动轴承故障诊断方法[J].轴承,2014(11):48-53.
[7]胡荣华,楼佩煌,唐敦兵,等.基于EMD和免疫参数自适应SVM的滚动轴承故障诊断[J].计算机集成制造系统,2013,19(2):438-447.
[8]马泽玮,崔宝珍.基于广义形态学滤波和EEMD分解的滚动轴承故障诊断[J].中国农机化学报,2015,36(2):269-273.
[9]曹洁,谢希,吕景顺.自适应广义数学形态学抑制局部放电窄带干扰[J].电机与控制学报,2013,17(4):33-38.
[10]赵昕海,张术臣,李志深,等.基于VMD的故障特征信号提取方法[J].振动.测试与诊断,2018,38(1):11-19.
[11]张淑清,孙国秀,李亮,等.基于LMD近似熵和FCM聚类的机械故障诊断研究[J].仪器仪表学报,2013,34(3):714-720.
[12]王书涛,李亮,张淑清,等.基于EEMD样本熵和GK模糊聚类的机械故障识别[J].中国机械工程,2013,24(22):3036-3040.
[13] SERIR L,RAMASSO E,ZERHOUNI N. Evidential evolving Gustafson-Kessel algorithm for online data stre-amspartition-ing using belief function theory[J]. International Journal of Approximate Reasoning,2012,53(5):747-768.
[14]张淑清,包红燕,李盼,等.基于RQA与GG聚类的滚动轴承故障识别[J].中国机械工程,2015,26(10):1385-1390.
[15] Case Western Reserve University Bearing Data Center. Bearing data center fault test data[EB/OL].[2018-07-15]. ht-tp://www. eecs. case. edu/laboratory/bearing.
[2] HUANG N E,SHEN Z,LONG S R,et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear andnon-stationary time series analysis[J]. Proceedings of the Royal Society A Mathematical Physical&Engineering Sciences,1998,454(1971):903-995.
[3] WU Zhao-hua,HUANG N E,CHEN Xian-yao. The Multi-dimensional ensemble empirical mode decomposition method[J].Advances in Adaptive Data Analysis,2014,1(3):0900018
[4]姚刚,赵建军,姚跃亭,等.基于改进EMD方法的系统误差分离方法研究[J].振动与冲击,2014,33(14):176-180.
[5]胥永刚,孟志鹏,陆明.基于双树复小波包变换和SVM的滚动轴承故障诊断方法[J].航空动力学报,2014,29(1):67-73.
[6]任学平,庞震,辛向志,等.基于小波包最优熵与RVM的滚动轴承故障诊断方法[J].轴承,2014(11):48-53.
[7]胡荣华,楼佩煌,唐敦兵,等.基于EMD和免疫参数自适应SVM的滚动轴承故障诊断[J].计算机集成制造系统,2013,19(2):438-447.
[8]马泽玮,崔宝珍.基于广义形态学滤波和EEMD分解的滚动轴承故障诊断[J].中国农机化学报,2015,36(2):269-273.
[9]曹洁,谢希,吕景顺.自适应广义数学形态学抑制局部放电窄带干扰[J].电机与控制学报,2013,17(4):33-38.
[10]赵昕海,张术臣,李志深,等.基于VMD的故障特征信号提取方法[J].振动.测试与诊断,2018,38(1):11-19.
[11]张淑清,孙国秀,李亮,等.基于LMD近似熵和FCM聚类的机械故障诊断研究[J].仪器仪表学报,2013,34(3):714-720.
[12]王书涛,李亮,张淑清,等.基于EEMD样本熵和GK模糊聚类的机械故障识别[J].中国机械工程,2013,24(22):3036-3040.
[13] SERIR L,RAMASSO E,ZERHOUNI N. Evidential evolving Gustafson-Kessel algorithm for online data stre-amspartition-ing using belief function theory[J]. International Journal of Approximate Reasoning,2012,53(5):747-768.
[14]张淑清,包红燕,李盼,等.基于RQA与GG聚类的滚动轴承故障识别[J].中国机械工程,2015,26(10):1385-1390.
[15] Case Western Reserve University Bearing Data Center. Bearing data center fault test data[EB/OL].[2018-07-15]. ht-tp://www. eecs. case. edu/laboratory/bearing.