| Extracting invariable fault features of rotating machines with multi-ICA networks |
| |
| 作者姓名： | 焦卫东 杨世锡 吴昭同 |
| |
| 作者单位： | Department of Mechanical Engineering，Zhejiang University，Department of Mechanical Engineering，Zhejiang University，Department of Mechanical Engineering，Zhejiang University Hangzhou 310027，China，Hangzhou 310027，China，Hangzhou 310027，China |
| |
| 基金项目： | ProjectsupportedbytheNationalNaturalScienceFoundation (No . 50 2 0 5025)andtheNaturalScienceFoundationofZhejiangProvince (No.50 0 1 0 0 4 ) |
| |
| 摘 要： | INTRODUCTIONRotatingmachinessuchaselectromotor,dy namotor,turbocompressor,etc .areimportantequipmentsinmanyindustryfields.Peoplehadbeenpayingconsiderableattentiontotheircon ditionmonitoringandfaultdiagnosis (Xu ,19 98) .Theoretically ,anyfluctuationofforc…
|
Extracting invariable fault features of rotating machines with multi-ICA networks |
| |
| JIAO Wei-dong,YANG Shi-xi,Wu Zhao-tong.Extracting invariable fault features of rotating machines with multi-ICA networks[J].Journal of Zhejiang University Science,2003(5). |
| |
| Authors: | JIAO Wei-dong YANG Shi-xi Wu Zhao-tong |
| |
| Abstract: | This paper proposes novel multi-layer neural networks based on Indep e ndent Component Analysis for feature extraction of fault modes. By the use of IC A,invariable features embedded in multi-channel vibration measurements under different operating conditions (rotating speed and/or load) can be captured toge t her. Thus,stable MLP classifiers insensitive to the variation of operation cond itions are constructed. The successful results achieved by selected experiments indicate great potential of ICA in health condition monitoring of rotating machi nes. |
| |
| Keywords: | Independent Component Analysis (ICA) Mutual Inform ation (MI) Principal Component Analysis (PCA) Multi-Layer Perceptron (MLP) R esidual Total Correlation (RTC) |
| 本文献已被 CNKI 等数据库收录！ |
