Abstract：Good quality of molten iron is the guarantee for the reliability and stability of cast iron performance. The contents of sulfur (S) and silicon (Si) in molten iron are main indicators to measure the quality of molten iron. Therefore, the accurate determination of S and Si contents in molten iron before tapping is of great significance. A method for predicting the S and Si contents in molten iron by combining principal component analysis (PCA) with least squares support vector machine (LS-SVM) model was proposed. The online data of large blast furnace collected in a steel plant was used as the research object. Firstly, PCA was performed on the data that influencing the changes of S content and Si content in molten iron. The principal component was obtained for the input variable of model. Secondly, the LS-SVM model was established to predict the S content and Si content in molten iron. During the prediction process of S content, the prediction error was minimal when the regularization parameter (gam) and kernel function parameter (sig) was 20 and 700, respectively. Meanwhile, the root mean square error was 0.0012, and the simulation time was 0.423105 s. During the prediction process of Si content, the prediction error was minimal when gam and sig was 40 and 500, respectively. Meanwhile, the root mean square error was 0.0238, and the simulation time was 0.079522s. Finally, the experimental results were compared with the traditional LS-SVM model and PCA+BP model (PCA combined with back-propagation neural network). For the prediction of S content in traditional LS-SVM model and PCA+BP model, the root mean square error was 0.0015 and 0.0014, and the simulation time was 1.320842s and 2.245967s, respectively. For the prediction of Si content in traditional LS-SVM model and PCA+BP model, the root mean square error was 0.0316 and 0.0325, and the simulation time was 0.459671s and 2.061576s, respectively. The experimental results showed that the proposed method could more fully consider the influence of all factors on the change of S content and Si content in molten iron. This method exhibited the advantages such as short training time and high prediction accuracy.
赵宁, 王玉英, 杨凡, 杨卫轩. 主成分分析和最小二乘支持向量机模型在铁水硫和硅含量预测中的应用[J]. 冶金分析, 2020, 40(2): 1-6.
ZHAO Ning, WANG Yu-ying, YANG Fan, YANG Wei-xuan. Application of principal component analysis and least squaressupport vector machine model in prediction of sulfurand silicon content in molten iron. , 2020, 40(2): 1-6.
尹延平.铁水成分和温度是铸件质量保证[J].黑龙江冶金,2009,29(4):12-14.YIN Yan-ping.Iron liquid composition and temperature guarantee casting quality[J].Heilongjiang Metallorgy,2009,29(4):12-14.
Matias Waller,Henrik Saxen.Application of nonlinear time series analysis to the prediction of silicon content of pig iron[J].ISIJ International,2002,42(3):316-318.
[4]
邱东,仝彩霞,祁晓钰,等.基于神经网络的高炉铁水硅含量预报模型的研究[J].冶金分析,2009,29(2):49-52.QIU Dong,TONG Cai-xia,QI Xiao-yu,et al.Study on prediction model of silicon content in blast furnace liquid iron based on neural network[J].Metallurgical Analysis,2009,29(2):49-52.
Vladimir N Vapnik.Statistical learning theory[M].New York:John Wiley,1998:98-105.
[7]
渐令,刘祥官.支持向量机在铁水硅含量预报中的应用[J].冶金自动化,2005,29(3):33-36.JIAN Ling,LIU Xiang-guan.Application of SVM to prediction of silicon content in hot metal [J].Metallurgical Industry Automation,2005,29(3):33-36.
[8]
马淑艳.基于支持向量机的高炉铁水硅含量预测[D].杭州:浙江大学,2016.
[9]
Suykens J A K,Vandewalle J.Recurrent least squares support vector machines [J].IEEE Transactions on Circuits and Systems,I.Fundamental Theory and Applications,2000,47(7):1109-1114.
[10]
王龙辉,高嵩,屈星.基于最小二乘支持向量机的铁水含硅量软测量[J].工业控制计算机,2013,26(3):89-90.WANG Long-hui,GAO Song,QU Xing.Prediction of blast furnace hot metal silicon content based on least square support vector machine[J].Industrial Control Computer,2013,26(3):89-90.
[11]
郑俊华,吴铁军.高炉铁水硅含量预报的ICA-SVM建模方法[J].信息与控制,2008,37(2):247-252.ZHENG Jun-hua,WU Tie-jun.ICA-SVM-Based modeling for predicting silicon content in blast furnace hot metal[J].Information and Control,2008,37(2):247-252.
[12]
司守奎,孙玺.数学建模算法与应用[M].北京:国防工业出版社,2011:208-211.
[13]
廖芹,郝志峰,陈志宏.数据挖掘与数学建模[M].北京:国防工业出版社,2010:57-61.
[14]
J A K Suykens,J Vandewalle.Least squares support vector mchines classifiers[J].Neural Network Letters,1999,19(3):293-300.
