| 基于时变自回归模型阶次判定值的滚动轴承特征提取 |
| |
| 引用本文： | 魏巍,彭涛.基于时变自回归模型阶次判定值的滚动轴承特征提取[J].电子测量与仪器学报,2012,26(3):255-260. |
| |
| 作者姓名： | 魏巍 彭涛 |
| |
| 作者单位： | 1. 湖南工业大学电气与信息工程学院,株洲,412008
2. 中南大学信息科学与工程学院,长沙,410083 |
| |
| 基金项目： | 国家自然科学基金资助项目（60774069、61170101）; 中国博士后科学基金资助项目（20070410462） |
| |
| 摘 要： | 针对滚动轴承振动信号的非平稳性,提出了一种基于时变自回归模型阶数判定值的特征提取方法。通过用时变自回归模型定阶过程中的判定值构建特征量,并以支持向量机的分类识别率为依据选择最佳的特征向量维数,输入支持向量机进行滚动轴承运行状态的识别。仿真实验表明,所提方法能够有效地提取滚动轴承的故障信息进而实现其故障诊断。
|
| 关 键 词： | 特征提取 时变自回归参数模型 AIC准则 滚动轴承 故障诊断 |
Feature extraction of roller bearings based on decision value of TVAR model order |
| |
| Wei Wei
,
Peng Tao.Feature extraction of roller bearings based on decision value of TVAR model order[J].Journal of Electronic Measurement and Instrument,2012,26(3):255-260. |
| |
| Authors: | Wei Wei Peng Tao |
| |
| Affiliation: | Wei Wei Peng Tao(1.College of Electrical and Information Engineering,Hunan University of Technology,Zhuzhou 412008,China;2.School of Information Science and Engineering,Central South University,Changsha 410083,China) |
| |
| Abstract: | Aiming at the non-stationary of rolling bearing vibration signal,a feature extraction method based on the decision values of time-varying autoregressive（TVAR） model order is proposed.The recognition rate of the support vector machine classifier is used to select the best feature vector dimension.Then,the support vector machine classifier is trained to recognize the running state of the rolling bearing.The simulation results in fault diagnosis show the effectiveness of the feature extraction method. |
| |
| Keywords: | feature extract time-varying autoregressive model AIC criterion rolling bearing fault diagnosis |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
