首页 | 本学科首页   官方微博 | 高级检索  
     

基于支持向量机预报模型的烧结终点模糊控制
引用本文:吴晓峰,费敏锐. 基于支持向量机预报模型的烧结终点模糊控制[J]. 浙江大学学报(工学版), 2007, 41(10): 1722-1726
作者姓名:吴晓峰  费敏锐
作者单位:1.上海大学 机电工程与自动化学院,上海 200072;2.莱芜钢铁集团有限公司 自动化部,山东 莱芜 271104
摘    要:针对烧结过程存在时间滞后和参数不确定问题,在分析烧结过程热状态的基础上,提出应用支持向量机优良的时序预测性能,建立了基于风箱废气温度预报烧结终点的预报模型.结合烧结终点预报模型,将模糊控制策略应用于烧结终点控制系统开发.介绍了控制系统的组成与烧结终点模糊控制器的设计方法.仿真结果和现场应用均证实了烧结终点控制系统的有效性,在存在较大干扰的情况下,能保持较好的控制品质.控制系统可准确、快速地预报烧结终点,具有稳定烧结终点和优化过程操作的作用.

关 键 词:烧结终点  烧结过程  支持向量机  预报模型  模糊控制
文章编号:1008-973X(2007)10-1722-05
修稿时间:2007-06-23

Fuzzy control applied to burning through point based on support vector machines prediction model
WU Xiao-feng,FEI Min-rui. Fuzzy control applied to burning through point based on support vector machines prediction model[J]. Journal of Zhejiang University(Engineering Science), 2007, 41(10): 1722-1726
Authors:WU Xiao-feng  FEI Min-rui
Affiliation:1. College of Mechatronics Engineering and Automation, Shanghai University, Shanghai 200072, China; 2. Automation Department of laiwu Iron and steel Group Company, Laiwu 271104, China
Abstract:In order to solve the problem of time delay and parameter uncertainty in burning through point(BTP),based on the heat pattern analysis for sintering processes,a BTP prediction method was proposed using support vector machines(SVMs) with excellent time series prediction performance.Fuzzy control strategy was applied to developed a BTP control system with the prediction model.The constitution of the control system and the design method of BTP fuzzy controller were presented.The simulation and the field application verified the effectiveness of the control system.Good control performance can be obtained in the case of large disturbances.The control system can perform exact BTP prediction and control and quickly achieve the stabilization of BTP and the optimization of the process operation.
Keywords:burning through point(BTP)  sintering process  support vector machines(SVMs)  prediction model  fuzzy control
本文献已被 CNKI 维普 等数据库收录!
点击此处可从《浙江大学学报(工学版)》浏览原始摘要信息
点击此处可从《浙江大学学报(工学版)》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号