| 基于多级SVM的回转窑烧结状态识别方法 |
| |
| 引用本文： | 姜慧研,周晓杰,柴天佑.基于多级SVM的回转窑烧结状态识别方法[J].东北大学学报(自然科学版),2009,30(1):54-57. |
| |
| 作者姓名： | 姜慧研 周晓杰 柴天佑 |
| |
| 作者单位： | 1. 东北大学,软件学院,辽宁,沈阳,110004;东北大学,流程工业综合自动化教育部重点实验室,辽宁,沈阳,110004
2. 东北大学,流程工业综合自动化教育部重点实验室,辽宁,沈阳,110004;东北大学,自动化研究中心,辽宁,沈阳,110004 |
| |
| 基金项目： | 国家自然科学基金，国家重点基础研究发展计划(973计划)，国家高技术研究发展计划(863计划) |
| |
| 摘 要： | 提出了一种新的基于多级SVM分类器的设计方法,并将该方法应用于回转窑的正常烧结、过烧结和欠烧结3种烧结状态的识别.即首先利用改进的双快速行进法从烧结图像中分割出物料区、黑把子区、火焰区、充分燃烧区等关心区域(ROIs),然后从ROIs中提取颜色、形状与纹理等特征,基于One-Versus-Another方法建立烧结状态预处理分类器模型,进行烧结状态的多类别分类;其次研究预处理分类器出错样本点的分布,将容易混淆的样本点作为一类;最后基于多级SVM方法重新建立分类器模型,进行烧结状态的分类.实验证明该方法快速、准确、推广性强.
|
| 关 键 词： | 烧结状态 SVM 模式识别 回转窑 |
Recognition Based on Multilevel SVM for Different Sintering States in Rotary Kiln |
| |
| JIANG Hui-yan,ZHOU Xiao-jie,CHAI Tian-you.Recognition Based on Multilevel SVM for Different Sintering States in Rotary Kiln[J].Journal of Northeastern University(Natural Science),2009,30(1):54-57. |
| |
| Authors: | JIANG Hui-yan ZHOU Xiao-jie CHAI Tian-you |
| |
| Institution: | JIANG Hui-yan1,2,ZHOU Xiao-jie2,3,CHAI Tian-you2,3(1.School of Software,Northeastern University,Shenyang 110004,China,2.Key Laboratory of Integrated Automation of Process Industry,Ministry of Education,3.Automation Research Center,China.) |
| |
| Abstract: | A new design method based on multilevel SVM classifier is presented to recognize the normal sintering,oversintering and undersintering states in rotary kiln.The ROIs(regions of interesting) were segmented from the images of sintered materials by an improved dual-fast marching method,including the zones of materials,blackbar,flame and full calcination.Then,the characteristics of colour,shape and vein were extracted from ROIs to develop a pre-treated classifier model based on One-Versus-Another method to clas... |
| |
| Keywords: | SVM |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《东北大学学报(自然科学版)》浏览原始摘要信息 |
| 点击此处可从《东北大学学报(自然科学版)》下载免费的PDF全文 |
|
