等距离映射和模糊C均值的滚动轴承故障识别
|
摘要
在滚动轴承的故障识别中,针对传统的等距离映射ISOMAP算法存在测地距离的计算偏差较大,故障识别部分混叠的问题,提出一种模糊C均值和等距离映射的滚动轴承故障识别方法。首先,对ISOMAP算法中的邻域大小k值用残差进行改进,保证映射结果很好地反映全局性质;其次可分性评价指标评价特征降维的效果;然后,采用了模糊C均值聚类方法,保证在拓扑空间中高维流形数据与低维空间光滑流形中的数据仍保持相近或相同的特性。最后,通过采集不同损伤程度下的滚动轴承振动数据进行实验验证,结果表明本文方法在分类效果和识别精度都有了明显的提升。
In the fault identification of rolling bearing,the traditional ISOMAP algorithm is met with the problem of large deviation of geodesic distance and aliasing in fault identification. So,this paper presents a fuzzy C-means and Isometric Feature Mapping of rolling bearing fault identification method. First of all,the neighborhood size k of ISOMAP algorithm is improved with residuals to ensure that the mapping results reflect the global nature well. Second,the index of category divisibility is used to evaluate the effect of feature dimensionality reduction.Then,a fuzzy C-means clustering method is adopted to ensure that the data in high-dimensional manifolds and the low-dimensional smooth manifold in the topological space are still close or the same. Finally,the experimental verification of vibration data of rolling bearing with different damage degrees shows that the combination of fuzzy C-means and improved ISOMAP has obvious improvement in both classification and identification accuracy.
In the fault identification of rolling bearing,the traditional ISOMAP algorithm is met with the problem of large deviation of geodesic distance and aliasing in fault identification. So,this paper presents a fuzzy C-means and Isometric Feature Mapping of rolling bearing fault identification method. First of all,the neighborhood size k of ISOMAP algorithm is improved with residuals to ensure that the mapping results reflect the global nature well. Second,the index of category divisibility is used to evaluate the effect of feature dimensionality reduction.Then,a fuzzy C-means clustering method is adopted to ensure that the data in high-dimensional manifolds and the low-dimensional smooth manifold in the topological space are still close or the same. Finally,the experimental verification of vibration data of rolling bearing with different damage degrees shows that the combination of fuzzy C-means and improved ISOMAP has obvious improvement in both classification and identification accuracy.
引文
[1]王亚萍,许迪,葛江华,等.基于SPWVD时频图纹理特征的滚动轴承故障诊断[J].振动.测试与诊断,2017,(1):115.
[2]时献江,罗建,宫秀芳.无传感器诊断方法及在风力发电中的应用与展望[J].哈尔滨理工大学学报,2014,19(6):82.
[3]杜冬梅,张昭,李红.基于LMD和增强动包络谱的滚轴承故障分析[J].振动、测试与诊断,2017,37(1):92.
[4] TENENBAUM J B,SILVA V D,LANGFORD J C. A Global Geometric Framework for Nonlinear Dimensionality Reduction[J].Science,2000,290:2319.
[5] ROWEIS S T,SAUL L K. Nonlinear Dimensionality Reduction by Locally Linear Embedding[J]. Science,2000,290:2323.
[6]李城梁,王仲生,姜洪开,等.自适应Hessian LLE在机械故障特征提取中的应用[J].振动工程学报,2013(5):758.
[7]王奉涛,陈旭涛,闫达文,等.流形模糊C均值方法及其在滚动轴承性能退化评估中的应用[J].机械工程学报,2016,52(15):59.
[8]姜万录,王浩楠,朱勇,等.变分模态分解消噪与核模糊C均值聚类相结合的滚动轴承故障识别方法[J].中国机械工程,2017,28(10):1215.
[9]郑直,姜万录,胡浩松,等.基于EEMD形态谱和KFCM聚类集成的滚动轴承故障诊断方法研究[J].振动工程学报,2015(2):324.
[10]蒋永华,李荣强,焦卫东.应用EMD和双谱分析的故障特征提取方法[J].振动、测试与诊断,2017,37(2):338.
[11]岳巧珍,张洪鑫,时献江.齿轮故障诊断信息提取复合方法研究[J].煤矿机械,2016,37(2):183.
[12]李媛媛,陈捷,洪荣晶,等.基于模糊C均值的转盘轴承剩余寿命预测[J].轴承,2017(3):50.
[13]刘来权,陈燕,雷燕瑞.模糊C均值聚类算法的有效性检验研究[J].软件,2017,38(2):16.
[14]王军辉,贾嵘,谭泊.基于EEMD和模糊C均值聚类的风电机组齿轮箱故障诊断[J].太阳能学报,2015,36(2):319.
[15]邓延丽,金炜东,李家会,等.基于聚集离散性与可分性的雷达信号特征评价[J].计算机应用,2013,33(7):1946.
[16]蒋栋年,李炜.基于数据驱动残差评价策略的故障检测方法[J].控制与决策,2017,32(7):1181.
[17]周卫庆,司风琪,徐治皋,等.基于KPCA残差方向梯度的故障检测方法及应用[J].仪器仪表学报,2017,38(10):2518.
[2]时献江,罗建,宫秀芳.无传感器诊断方法及在风力发电中的应用与展望[J].哈尔滨理工大学学报,2014,19(6):82.
[3]杜冬梅,张昭,李红.基于LMD和增强动包络谱的滚轴承故障分析[J].振动、测试与诊断,2017,37(1):92.
[4] TENENBAUM J B,SILVA V D,LANGFORD J C. A Global Geometric Framework for Nonlinear Dimensionality Reduction[J].Science,2000,290:2319.
[5] ROWEIS S T,SAUL L K. Nonlinear Dimensionality Reduction by Locally Linear Embedding[J]. Science,2000,290:2323.
[6]李城梁,王仲生,姜洪开,等.自适应Hessian LLE在机械故障特征提取中的应用[J].振动工程学报,2013(5):758.
[7]王奉涛,陈旭涛,闫达文,等.流形模糊C均值方法及其在滚动轴承性能退化评估中的应用[J].机械工程学报,2016,52(15):59.
[8]姜万录,王浩楠,朱勇,等.变分模态分解消噪与核模糊C均值聚类相结合的滚动轴承故障识别方法[J].中国机械工程,2017,28(10):1215.
[9]郑直,姜万录,胡浩松,等.基于EEMD形态谱和KFCM聚类集成的滚动轴承故障诊断方法研究[J].振动工程学报,2015(2):324.
[10]蒋永华,李荣强,焦卫东.应用EMD和双谱分析的故障特征提取方法[J].振动、测试与诊断,2017,37(2):338.
[11]岳巧珍,张洪鑫,时献江.齿轮故障诊断信息提取复合方法研究[J].煤矿机械,2016,37(2):183.
[12]李媛媛,陈捷,洪荣晶,等.基于模糊C均值的转盘轴承剩余寿命预测[J].轴承,2017(3):50.
[13]刘来权,陈燕,雷燕瑞.模糊C均值聚类算法的有效性检验研究[J].软件,2017,38(2):16.
[14]王军辉,贾嵘,谭泊.基于EEMD和模糊C均值聚类的风电机组齿轮箱故障诊断[J].太阳能学报,2015,36(2):319.
[15]邓延丽,金炜东,李家会,等.基于聚集离散性与可分性的雷达信号特征评价[J].计算机应用,2013,33(7):1946.
[16]蒋栋年,李炜.基于数据驱动残差评价策略的故障检测方法[J].控制与决策,2017,32(7):1181.
[17]周卫庆,司风琪,徐治皋,等.基于KPCA残差方向梯度的故障检测方法及应用[J].仪器仪表学报,2017,38(10):2518.