| 机电BIT故障特征选择方法研究 |
| |
| 引用本文： | 王新峰,邱静,刘冠军.机电BIT故障特征选择方法研究[J].中国机械工程,2004,15(12):1048-1050,1062. |
| |
| 作者姓名： | 王新峰 邱静 刘冠军 |
| |
| 作者单位： | 国防科学技术大学机电工程与自动化学院,长沙,410073 |
| |
| 摘 要： | 提出一种故障特征选择方法，该方法采用类内类间距离作为特征评价准则，并利用遗传算法良好的寻优能力，解决特征的优选问题。轴承诊断实例证明，该方法有较好的寻优特征子集的能力，能够提高BIT系统的诊断精度，降低系统的虚警率，因而在机电BIT故障特征选择中有较好的应用前景。
|
| 关 键 词： | 机电BIT 特征选择 距离准则 遗传算法 |
| 文章编号： | 1004-132X(2004)12-1048-03 |
Research on Mechantronics BIT Fault Feature Selection Method |
| |
| Wang Xinfeng Qiu Jing Liu Guanjun National University of Defense Technology,Changsha.Research on Mechantronics BIT Fault Feature Selection Method[J].China Mechanical Engineering,2004,15(12):1048-1050,1062. |
| |
| Authors: | Wang Xinfeng Qiu Jing Liu Guanjun National University of Defense Technology Changsha |
| |
| Affiliation: | Wang Xinfeng Qiu Jing Liu Guanjun National University of Defense Technology,Changsha,410073 |
| |
| Abstract: | A method of feature selection was proposed. A between-calss and within-class distance measurement criterion and genetic algorithm (GA) for optimal feature selection were presented. According to the results of bearing diagnosis example,it is proved that this method possesses excellent optimization property,and can enhance the diagnostic correctness,decrease false alarm rate. The method has good prospects in the BIT(built-in test) fault feature selection. |
| |
| Keywords: | mechantronics BIT (MEBIT) feature selection distance measurement genetic algorithm |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
