| 用聚类支持向量机模型监测环保设备运行状态 |
| |
| 引用本文： | 曹晓莉,甘思源,江朝元. 用聚类支持向量机模型监测环保设备运行状态[J]. 重庆大学学报(自然科学版), 2009, 32(6): 674-679 |
| |
| 作者姓名： | 曹晓莉 甘思源 江朝元 |
| |
| 作者单位： | 重庆工商大学,废油资源化技术与装备教育部工程研究中心,重庆,400067;重庆工商大学计算机科学与信息工程学院,重庆,400067;重庆大学自动化学院重庆,400030;重庆工商大学计算机科学与信息工程学院,重庆,400067 |
| |
| 基金项目： | 重庆市教委资助项目，废油资源化技术与装备教育部工程研究中心重大项目 |
| |
| 摘 要： | 针对环保设备多状态监测与识别问题,提出了一种基于多分类聚类支持向量机的分类算法模型.该算法模型充分利用多个相关联被监测设备及其状态属性特征,采用神经网络聚类分析获得关联特征的聚类子空间,再对聚类子空间构造二叉树支持向量机进行多分类识别.该算法模型避免了盲目分类,与单纯的支持向量机算法比较具有更好的分类性能.通过对日本大晃船用污水处理装置实测样本的训练、检验表明,该算法具有98%以上的分类识别率.
|
| 关 键 词： | 支持向量机 设备状态 多分类 聚类 |
| 收稿时间： | 2009-02-12 |
Running condition monitoring for environmental protection equipment based on a clustering support vector machine |
| |
| CAO Xiao-li,GAN Si-yuan and JIANG Chao-yuan. Running condition monitoring for environmental protection equipment based on a clustering support vector machine[J]. Journal of Chongqing University(Natural Science Edition), 2009, 32(6): 674-679 |
| |
| Authors: | CAO Xiao-li GAN Si-yuan JIANG Chao-yuan |
| |
| Affiliation: | 1a.Engineering Research Center for Waste Oil Recovery Technology and Equipment;b.College of Computer Science and Information Engineering;Chongqing Technology and Business University;Chongqing 400067;P.R.China;2.College of Automation;Chongqing University;Chongqing 400030;P.R.China |
| |
| Abstract: | A multi-classification clustering model based on Support Vector Machines(SVM) is proposed to address problems of condition monitoring and identification in environmental protection equipment.Based on the associated attributes of monitoring equipment and their condition features,a neural network is adopted for clustering analysis to obtain clustering subspaces.The clustering subspace is employed to design a binary tree architecture based multi-classification SVM for multi-classification recognition.Compared ... |
| |
| Keywords: | support vector machines equipment condition multi-classification cluster |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《重庆大学学报(自然科学版)》浏览原始摘要信息 |
|
点击此处可从《重庆大学学报(自然科学版)》下载全文 |
