欢迎访问《轻工机械》稿件在线采编系统!设为首页 | 加入收藏    
信息公告:  
文章检索:
稿件处理系统
期刊信息
  • 中国标准连:ISSN1005-2895
  • 续出版物号: CN 33-1180/TH
  • 主管单位:轻工业杭州机电设计研究院有限公司
  • 主办单位:轻工业杭州机电设计研究院有限公司、中国轻工机械协会、中国轻工业机械总公司
  • 社  长:刘安江
  • 主  编:黄丽珍
  • 地  址:杭州市余杭区高教路970号西溪联合科技广场4-711
  • 电子邮件:qgjxzz@126.com
理事单位          MORE>>
张亚雄1, 范玉刚2, 李枝荣1, 孙亚军1.基于小波包 核偏最小二乘的滚动轴承故障检测法[J].轻工机械,2023,41(3):60-65
基于小波包 核偏最小二乘的滚动轴承故障检测法
基于小波包 核偏最小二乘的滚动轴承 故障检测法
  
DOI:10.3969/j.issn.1005 2895.2023.03.009
中文关键词:  滚动轴承  故障检测  小波包  核偏最小二乘
英文关键词:rolling bearing  fault detection  WP(Wavelet Packet)  KPLS(Kernel Partial Least Squares)
基金项目:国家自然科学基金资助项目(62173168);云南省教育厅基金项目(2022J1723);云南省教育厅基金项目(2022J1724)。
作者单位
张亚雄1, 范玉刚2, 李枝荣1, 孙亚军1 1.云南轻纺职业学院 机电工程与自动化学院 云南 昆明650300 [JZ]2.昆明理工大学 信息工程与自动化学院 云南 昆明650500 
摘要点击次数: 226
全文下载次数: 165
中文摘要:
      为了解决滚动轴承故障检测中出现的振动信号非线性问题,课题团队提出了一种基于小波包 核偏最小二乘(wavelet packet and kernel partial least squares method,WP KPLS)的故障检测方法。首先对采集到的信号进行小波包分解,将振动信号分解到独立的频段,提取不同频段的能量谱,并构建反映频谱状态改变的能量谱特征向量;再对得到的能量谱特征向量进行核偏最小二乘分析,建立故障检测模型,利用T2及SPE统计量来检测故障是否发生。实验结果表明:该方法能够较为准确地检测到轴承的内外圈故障,证明该模型是有效的。该方法综合了小波包对信号的分析优势和核偏最小二乘法在非线性情况下的数据处理优点,为解决故障检测中的非线性数据处理问题提供了一种新方法。
英文摘要:
      In order to solve the nonlinear problem of rolling bearing vibration signal in fault detection, a fault detection method based on wavelet packet and kernel partial least squares method (WP KPLS) was proposed. Firstly, the collected signal was decomposed by wavelet packet, the vibration signal was decomposed into independent frequency bands, the energy spectrum of different frequency bands was extracted, and the energy spectrum eigenvectors reflecting the change of spectrum state were constructed. Then, the obtained energy spectrum eigenvectors were analyzed by kernel partial least squares, a fault detection model was established, the T2 and SPE statistics were used to detect whether the fault occurred. The experimental results show that the method can detect the faults of the inner and outer rings of bearings more accurately, which proves that the model is effective. This method combines the advantages of wavelet packets in signal analysis and the advantages of kernel partial least squares in data processing under nonlinear conditions, and provides a new method for solving nonlinear data processing problems in fault detection.
查看全文  查看/发表评论  下载PDF阅读器
关闭