Using OSL-SVM for the Concentration Prediction of 4-CBA

摘要：

To track the dynamics of nonlinear timevarying systems, a new adaptive model based nonlinear function estimation is proposed for online monitoring of nonlinear processes. After Least Squares Support Vector Machine (LSSVM) was trained offline, the model is regulated online by the Kalman filter. The online regulated LS-SVM(OLS-SVM) is suitable for real time system recognition and time series prediction. Time series prediction can be a very useful tool in the field of process chemo metrics to forecast and to study the behavior of key process parameters in time. This creates the possibility to give early warnings of possible process malfunctioning. In this paper, OLS-SVM is applied to predict the concentration of 4Carboxybenzaldchydc (4-CBA) in purified terephthalic acid (PTA) oxidation process. Results indicate that the proposed method is effective and its accuracy is very high.

关键词： leastsquaressupportvectormachine PTA oxidation process kernel function time series prediction

作者: Yugang Fan Hua Wang Jiande Wu

作者单位: Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kun Faculty of Metallurgy and Energy Engineering, Kunming University of Science and Technology, Kunming,

会议类型: 国际会议

会议名称: 2010 International Conference on Signal and Information Processing(2010年IEEE信号与信息处理国际会议 ICSIP2010)

会议地点: 长沙

会议语种:英文

页码: 128-131

在线出版日期: 2010-12-14（万方平台首次上网日期，不代表论文的发表时间）