| 基于费舍尔判别分析法的故障诊断 |
| |
| 引用本文： | 梁亮,袁洪芳,曹晰.基于费舍尔判别分析法的故障诊断[J].计算机工程与设计,2008,29(11):2897-2900. |
| |
| 作者姓名： | 梁亮 袁洪芳 曹晰 |
| |
| 作者单位： | 北京化工大学,信息科学与技术学院,北京,100029 |
| |
| 摘 要： | 在化工流程故障诊断中,主元分析法(PCA)是最常见的降维技术.尽管PCA具有一定的优化性能,并在故障诊断中被广泛使用,却不是故障诊断的最佳方案.理论上,费舍尔判别分析法(FDA)在故障诊断分类方面更具优势.对现实化工厂故障数据进行了研究,得出在低维状态下选择FDA方法可以获得更好的处理效果.
|
| 关 键 词： | 故障诊断 主元分析法 费舍尔判别分析法 降维 模式识别 |
| 文章编号： | 1000-7024(2008)11-2897-04 |
| 修稿时间： | 2007年6月20日 |
Fault diagnosis based on Fisher's discriminant analysis |
| |
| LIANG Liang,YUAN Hong-fang,CAO Xi.Fault diagnosis based on Fisher's discriminant analysis[J].Computer Engineering and Design,2008,29(11):2897-2900. |
| |
| Authors: | LIANG Liang YUAN Hong-fang CAO Xi |
| |
| Affiliation: | LIANG Liang,YUAN Hong-fang,CAO Xi (College of Information Science , Technology,Beijing University of Chemical Technology,Beijing 100029,China) |
| |
| Abstract: | Principal component analysis(PCA)is the most commonly used dimensionality reduction technique for detecting and diagnosing faults in chemical processes. Although PCA contains certain optimality properties in terms of fault detection, and has been widely applied for fault diagnosis, it is not best suited for fault diagnosis. Theoretically, Fisher's discriminant analysis (FDA) has advantages on the classification techniques for fault diagnosis. Data collected from real chemical plant will be treated both in P... |
| |
| Keywords: | fault diagnosis principal component analysis Fisher's discriminant analysis dimensionality reduction pattern recognition |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
