| 多切面分类改进独立成份与支持向量机集成故障诊断方法 |
| |
| 引用本文： | 薄翠梅,柏杨进,杨海荣,张广明.多切面分类改进独立成份与支持向量机集成故障诊断方法[J].控制理论与应用,2012,29(2):229-234. |
| |
| 作者姓名： | 薄翠梅 柏杨进 杨海荣 张广明 |
| |
| 作者单位： | 1. 南京工业大学自动化与电气工程学院,江苏南京,210009
2. 上海宝信软件股份有限公司,上海,201203 |
| |
| 基金项目： | 国家自然科学基金资助项目(60804027); 江苏省自然科学基金资助项目(BK2011795); 中国博士后科学基金资助项目(20100471325); 江苏省博士后科学基金资助项目(0901011B). |
| |
| 摘 要： | 本文采用多切面分类方法改进独立成份(ICA)与支持向量机(SVM)集成诊断方法. 在高维独立成份特征空间中采用多切面分类方法在不同切面上分别建立SVM故障分类模型. 对不同切面的分类情况进行故障识别, 改善ICA--SVM集成故障诊断性能. 将ICA--MSVM集成故障诊断方法对动态执行器基准平台(DAMADICS)的19种阀门故障模式进行仿真验证, 结果表明改进的ICA--MSVM方法有效地提高了故障诊断精度.
|
| 关 键 词： | 多切面分类 独立成分分析 支持向量机 故障辨识 执行器基准平台 |
| 收稿时间： | 5/5/2011 12:00:00 AM |
| 修稿时间： | 2011/9/13 0:00:00 |
Multi-section classification improving integrated fault diagnosis method based on independent component analysis and support-vector-machines |
| |
| BO Cui-mei,BAI Yang-jin,YANG Hai-rong and ZHANG Guang-ming.Multi-section classification improving integrated fault diagnosis method based on independent component analysis and support-vector-machines[J].Control Theory & Applications,2012,29(2):229-234. |
| |
| Authors: | BO Cui-mei BAI Yang-jin YANG Hai-rong and ZHANG Guang-ming |
| |
| Affiliation: | School of Automation & Electrical Engineering, Nanjing University of Technology,School of Automation & Electrical Engineering, Nanjing University of Technology,Shanghai Baosight Software Limited Liability Company,School of Automation & Electrical Engineering, Nanjing University of Technology |
| |
| Abstract: | The integrated diagnosis method of independent component analysis (ICA) and support-vector-machines (SVM) is improved by multi-section classification. Fault classification model of SVM is designed for each section in the high dimensional characteristic space. By diagnosing the fault type in different section, we improve the ICA--SVM fault diagnosis performance. This method has been applied to diagnose 19 types of valve failures on the dynamic actuator reference platform (DAMADICS). Simulation results show that the ICA--MSVM fault diagnosis method based on multisection classification effectively improves the accuracy of fault diagnosis. |
| |
| Keywords: | multisession classification independent component analysis (ICA) support-vector-machine (SVM) fault diagnosis actuator reference platform (DAMADICS) |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《控制理论与应用》浏览原始摘要信息 |
|
点击此处可从《控制理论与应用》下载全文 |
