韩光辉,韩守亮,李高鹏,郑维,纪秉男,张涛.纯电动车用驱动电机滚动轴承状态监测方法[J].电子测量与仪器学报,2021,35(2):130-135
纯电动车用驱动电机滚动轴承状态监测方法
Condition monitoring method of rolling bearing for driving motors of pure electric vehicles
  
DOI:
中文关键词:  纯电动车  滚动轴承  稀疏自编码器  支持向量机  状态监测
英文关键词:pure electric vehicles  rolling bearing  sparseauto encoder  support vector machine  condition monitoring
基金项目:国家重点研发计划(2017YFB010240401)、国防基础科研计划(JCKY2018205C002)、天津市自然科学基金(17JCZDJC40100)项目资助
作者单位
韩光辉 1.天津大学天津300072; 2.郑州宇通客车股份有限公司郑州450000 
韩守亮 2.郑州宇通客车股份有限公司郑州450000 
李高鹏 2.郑州宇通客车股份有限公司郑州450000 
郑维 2.郑州宇通客车股份有限公司郑州450000 
纪秉男 2.郑州宇通客车股份有限公司郑州450000 
张涛 2.郑州宇通客车股份有限公司郑州450000 
AuthorInstitution
Han Guanghui 1.Tianjin University,Tianjin 300072, China;2.Zhengzhou YuTong Bus Co.Ltd,Zhengzhou 450000,China 
Han Shouliang 2.Zhengzhou YuTong Bus Co.Ltd,Zhengzhou 450000,China 
Li Gaopeng 2.Zhengzhou YuTong Bus Co.Ltd,Zhengzhou 450000,China 
Zheng Wei 2.Zhengzhou YuTong Bus Co.Ltd,Zhengzhou 450000,China 
Ji Bingnan 2.Zhengzhou YuTong Bus Co.Ltd,Zhengzhou 450000,China 
Zhang Tao 2.Zhengzhou YuTong Bus Co.Ltd,Zhengzhou 450000,China 
摘要点击次数: 705
全文下载次数: 6
中文摘要:
      驱动电机轴承健康状态是实现纯电动车可靠运行,避免发生安全事故的重要前提,针对纯电动车电机滚动轴承状态监测方法缺失的问题,提出一种基于稀疏自编码器(sparse auto encoder, SAE)与支持向量机(support vector machine, SVM)的纯电动车用电机滚动轴承状态监测方法。在特征提取方面,利用电机轴承振动信号的时域、频域以及时频域特征集构建高维数据集,通过多层SAE进行数据融合从而消除特征的冗余性并获得更鲁棒的简明特征。在状态监测方面,将轴承状态的特征表示输入到SVM中进行训练得到轴承状态监测模型,最后通过设计纯电动客车用电机轴承状态变化实验评估该方法的有效性。试验结果表明,相比于传统特征+SVM,基于SAE SVM的监测方法对纯电动车用电机滚动轴承状态监测精度更加准确可靠。
英文摘要:
      The healthy condition of the drive motors bearing is an important premise to realize the reliable operation of the pure electric vehicles and avoiding safety accidents.Due to the lack of the state monitoring methods of the rolling bearing,a new method based on sparse auto encoder (SAE)and support vector machine (SVM) for rolling bearing of pure electric vehicles condition monitoring is proposed. In terms of feature extraction, the time domain, frequency domain and time frequency domain feature sets of rolling bearing vibration signals are used to construct high dimensional data sets, and the data fusion with multi layer SAE is performed to eliminate feature redundancy, which obtains more robust concise features.In terms of condition monitoring,the characteristic representation of bearing conditionis input into SVM for training to obtain a bearing condition monitoring model. Finally, the effectiveness of the method is evaluated by designing a bearing of pure electric vehicle motor condition experiment.The results show that comparing with the traditional feature + SVM, the monitoring method of rolling bearings of pure electric vehicles based on SAE SVM is more accurate and reliable.
查看全文  查看/发表评论  下载PDF阅读器