| 基于时序趋势特征的回转窑喂煤SVM分类方法 |
| |
| 引用本文： | 赵晶晶,张小刚,陈华,林祈元.基于时序趋势特征的回转窑喂煤SVM分类方法[J].冶金自动化,2011,35(5). |
| |
| 作者姓名： | 赵晶晶 张小刚 陈华 林祈元 |
| |
| 作者单位： | 1. 湖南大学电气与信息工程学院,湖南长沙,410082
2. 湖南大学 |
| |
| 基金项目： | 国家自然科学基金资助项目(60874096) |
| |
| 摘 要： | 提出一种基于时序趋势特征的回转窑喂煤支持向量机（SVM）分类方法，根据回转窑多个热工数据之间的动态变化规律预测喂煤变化趋势，指导人工喂煤调节的操作。首先对回转窑热工数据进行预处理，将喂煤时间序列分段线性表示，并提取相应趋势特征，形成训练样本；然后采用粒子群（PSO）算法优化SVM参数，构建SVM分类器，进而对测试样本进行分类，实现对喂煤趋势的分类预测。通过采用现场数据进行对比分析，证明本文提出的喂煤趋势预测方法具有较高的预测准确率，提高了窑前控制的鲁棒性，模型达到了现场应用的水平。
|
| 关 键 词： | 回转窑 支持向量机 粒子群 时间序列 |
SVM classification for rotary kiln based on time series trend characteristics |
| |
| ZHAO Jing-jing,ZHANG Xiao-gang,CHEN Hua,LIN Qi-yuan.SVM classification for rotary kiln based on time series trend characteristics[J].Metallurgical Industry Automation,2011,35(5). |
| |
| Authors: | ZHAO Jing-jing ZHANG Xiao-gang CHEN Hua LIN Qi-yuan |
| |
| Affiliation: | ZHAO Jing-jing1,ZHANG Xiao-gang1,CHEN Hua2,LIN Qi-yuan1(1.College of Electrical and Information Engineering,Hunan University,Changsha 410082,China,2.Hunan University) |
| |
| Abstract: | A SVM classification for rotary kiln based on time series trend characteristics is presented.Coal feeding change trend is predicted according to dynamic change rules of thermal engineering data in rotary kiln,so that regulation operation of manual feeding coal is guided.Firstly,thermal engineering data of rotary kiln is preprocessed,time series of coal feeding is linearly represented in segment,trend characteristics of rotary kiln time series are extracted,and training samples are obtained.Then,SVM paramete... |
| |
| Keywords: | rotary kiln SVM(Support Vector Machine) particle swarm time series |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
