1 October 2011 Using OSL-SVM for the concentration prediction of 4-CBA
Author Affiliations +
Proceedings Volume 8285, International Conference on Graphic and Image Processing (ICGIP 2011); 828551 (2011) https://doi.org/10.1117/12.913370
Event: 2011 International Conference on Graphic and Image Processing, 2011, Cairo, Egypt
To track the dynamics of nonlinear time-varying systems, a new adaptive model based nonlinear function estimation is proposed for online monitoring of nonlinear processes. After Least Squares Support Vector Machine (LS-SVM) 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 4-Carboxybenzaldchydc (4-CBA) in purified terephthalic acid (PTA) oxidation process. Results indicate that the proposed method is effective and its accuracy is very high.
© (2011) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Yugang Fan, Yugang Fan, Hua Wang, Hua Wang, Jiande Wu, Jiande Wu, } "Using OSL-SVM for the concentration prediction of 4-CBA", Proc. SPIE 8285, International Conference on Graphic and Image Processing (ICGIP 2011), 828551 (1 October 2011); doi: 10.1117/12.913370; https://doi.org/10.1117/12.913370


Study on static and dynamic modeling of nonlinear system
Proceedings of SPIE (October 12 2008)
Fuzzy neural networks based on rough sets for process modeling
Proceedings of SPIE (September 01 2003)
A more robust unscented transform
Proceedings of SPIE (November 25 2001)
Multivariable analysis, correlation, and prediction
Proceedings of SPIE (April 28 2009)
Comparison of state- and information-based sensor fusion
Proceedings of SPIE (October 08 1998)

Back to Top