Comparative Research on Prediction Model of Billet Temperature for 1700 Reheating Furnace in Tangsteel Company

详细信息    查看官网全文

• 英文论文题名：Comparative Research on Prediction Model of Billet Temperature for 1700 Reheating Furnace in Tangsteel Company
• 论文作者：Wang Xiaolin ; Li Xiaohua
• 英文论文作者：Wang Xiaolin ; Li Xiaohua ; School of Electronic and Information Engineering ; University of Science and Technology
• 年：2017
• 作者机构：School of Electronic and Information Engineering,University of Science and Technology,Liaoning,Anshan;
• 英文论文关键词：Reheating furnace ; billet temperature prediction ; mathematical model ; BP neural network ; support vector machine
• 会议召开时间：2017-07-26
• 会议录名称：第36届中国控制会议论文集（B）
• 英文会议录名称：Proceedings of the 36th Chinese Control Conference（B）
• 语种：英文
• 分类号：TG307;TP18
• 学会代码：KZLL
• 会议名称：第36届中国控制会议
• 会议地点：中国辽宁大连
• 主办单位：中国自动化学会控制理论专业委员会
• 学会名称：中国自动化学会控制理论专业委员会
• 页数：5
• 文件大小：180k
• 原文格式：D
• 会议级别：全国

摘要

In this paper, two modeling methods are studied for billet temperature prediction model based on the actual production data of the reheating furnace in Tangsteel 1700 line. The two methods are the neural network and the support vector machine. Two prediction models are built by the two methods respectively. And the comparative research is done via MATLAB simulation aiming at the two modeling methods. The research results show that the support vector machine method is more applicable when there are less sample data, but the neural network modeling method has the better accuracy than the other one when the sample data are enough.
In this paper, two modeling methods are studied for billet temperature prediction model based on the actual production data of the reheating furnace in Tangsteel 1700 line. The two methods are the neural network and the support vector machine. Two prediction models are built by the two methods respectively. And the comparative research is done via MATLAB simulation aiming at the two modeling methods. The research results show that the support vector machine method is more applicable when there are less sample data, but the neural network modeling method has the better accuracy than the other one when the sample data are enough.

引文

[1]Li Ning,Wang Xi-huai,Li Shao-yuan,Xi Yu-geng.Modeling and Temperature Optimal Setpoint Strategy for Walking Beam Reheating Furnace.Journal of System Simulation,2001,13(03):361-363.(In Chinese)
    [2]Yang Zekuan,Kang Guoren.Mathematical Model For Optimum Control Of Reheating Furnace.Iron And Steel,1990,25(12):59-63.(In Chinese)
    [3]Yang Dazheng,Xu Dayong,Deng Wei,Zhang Yu,Liu Changpeng,Wang Lijuan,Xu Chunbai.The study on forecasting tapping temperature according to billet opening rolling temperature.Energy for Metallurgical Industry,2007,26(2):28-29.(In Chinese)
    [4]Liang Jun.Application of adaptive technology in the heating furnace control.Industrial furnace,1997,(1):59-64.(In Chinese)
    [5]Xiao Shali.Based on support vector machines research in temperature control systems.Wuhan University of Science and Techology,2010.(In Chinese)
    [6]Wang Zhongjie,Chai Tianyou,Shao Cheng.Slab Temperature Prediction Model Based on RBP Neural Network.Journal of System Simulation,1999,11(3):181-184.(In Chinese)
    [7]Zhang Wei.Application of Fuzzy Neural Network on Model Building and Control of Slab Exiting Temperature.Chongqing University,2007.(In Chinese)
    [8]Yang Yinghua,Yang Shaowei,Liu Xiaozhi,Chen Xiaobo.Billet Temperature Model of Reheating Furnace Based on Independent Component Regression.Journal of System Simulation,2008,20(10):2523-2525.(In Chinese)
    [9]Wang Weixiao.The Study on Temperature Optimal Control of Walking-Beam Reheating Furnace.Dalian University of Technology,2008.(In Chinese)
    [10]Duda R O,Hart P E,Stork D G.Pattem classification.2nd Edition.Beijing:China Machine Press,2003.
    [11]Liu Huimin,Wang Hongqiang,Li Xiang.A Study on Data Normalization for Target Recognition Based on RPROP Algorithm.Modern Radar,2009,31(5):55-60.(In Chinese)
    [12]Gyung Min Vhoi,Masashi Katsuki.Advanced low NO combustion using highly preheated air,Energy Conversion and Management,2001,22(2):639-652.
    [13]T J Williams.Energy saving and productivity increase with computers a case study of the steel ingot handling process,Computers in Industry,1983,17(4):1-18.
    [14]Chu Man-sheng,Yang Xue-feng,Shen Feng-man.Numerical Simulation of Innovative Operation of Blast Furnace Based on Multi-Fluid Model.Journal of iron and steel research international.2006,13(6):08-15.
    [15]Hongwei Zhang,Barry lennox.Integrate condition monitoring and control of fed-batch fermentation processes.Journal of Process Control,2004,14(01):41-50.
    [16]Sun Tong.Study of least squares support vector machine prediction model based on temperature of molten iron in the blast furnace.Inner Mongolia University of Science&Technology,2013.(In Chinese)
    [17]Wang Xiaochuan,Shi Feng,Yu Lei,and Li Yang.MATLAB neural network 43 cases analysis.Beihang University Press,2011.(In Chinese)
    [18]Yan Hui,Zhang Xuegong,Li Yanda.Relation between a support vector machine and the least square method,Journal of Tsinghua University,2001,41(9):77-81.(In Chinese)