|
|||||
|
|
| 改进投票策略的多类SVM及在故障诊断中应用 | |
| 引用本文： | 吴德会. 改进投票策略的多类SVM及在故障诊断中应用[J]. 系统工程与电子技术, 2009, 31(4): 982-987 |
| 作者姓名： | 吴德会 |
| 作者单位： | 1. 九江大学数字控制技术与应用江西省重点实验室, 江西, 九江, 332005;2. 清华大学电机工程与应用电子技术系, 北京, 100084 |
| 摘 要： | 针对一对一(OVO)分解法,提出了一种改进的投票(MWV)策略,解决了传统策略中的不可分区域问题。首先,由训练ωi类和ωj(j≠i,j=1,…,n)类而得到的SVM决策函数;再对ωi类定义了一个取值在0~1之间的调节函数,并使改进的得票值等于传统得票值加上调节函数。最后,根据改进的得票值进行分类决策。对于可分区域的样本,改进MWV策略的分类结果与传统策略完全相同;对于不可分区域的数据,由调节函数的值决定。将所提法应用于齿轮传动箱故障诊断实例并与传统得票策略诊断进行了对比,实验结果验证了所提方法的上述优越性。 |
| 关 键 词： | 模式识别 多类支持向量机 投票法 故障诊断 一对一分解 |
| 收稿时间： | 2008-02-11 |
| 修稿时间： | 2008-04-20 |
Multi-class SVM based on improved voting strategy and its application in fault diagnosis |
|
| WU De-hui. Multi-class SVM based on improved voting strategy and its application in fault diagnosis[J]. System Engineering and Electronics, 2009, 31(4): 982-987 | |
| Authors: | WU De-hui |
| Affiliation: | 1. Key Lab of Numerical Control of Jiangxi Province, Jiujiang Univ., Jiujiang 332005, China;2. Dept. of Electrical Engineering, Tsinghua Univ., Beijing 100084, China |
| Abstract: | An improved max-wins-voting(MWV) strategy for one-versus-one(OVO) classification is developed and the unclassifiable regions existing in conventional one are resolved.Firstly,using the decision functions obtained by training the SVM for classes ωi and ωj(j≠i,j=1,…,n),for class ωi,a novel tuning function is defined in the range of 0~1.Secondly,the improved voting value for class ωi equals to the traditional voting value plus the tuning function.Finally,a classification decision is made according to the improved voting value.For the data in the classifiable regions,the classification results using improved MWV strategy are the same as that using the traditional one.Whereas,the data in the unclassifiable region are determined by the tuning function.The comparison is done with experimental data in the application of fault diagnosis for gearbox.Experimental results demonstrate the superiority of the presented strategy. |
| Keywords: | |
| 本文献已被 万方数据 等数据库收录！ | |
| 点击此处可从《系统工程与电子技术》浏览原始摘要信息 | |
| 点击此处可从《系统工程与电子技术》下载全文 | |