Multi-model fusion modeling method based on improved Kalman filtering algorithm

被引：0

作者：

Zhu, Pengfei ^{[1
]}

Xia, Luyue ^{[1
]}

Pan, Haitian ^{[1
]}

机构：

[1] School of Chemical Engineering, Zhejiang University of Technology, Hangzhou, 310032, Zhejiang

来源：

Huagong Xuebao/CIESC Journal | 2015年 / 66卷 / 04期

基金：

中国国家自然科学基金;

关键词：

Hybrid modeling; Improved Kalman filtering; Multi-model fusion; Polymerization; Prediction; Principal component analysis;

D O I：

10.11949/j.issn.0438-1157.20141030

中图分类号：

学科分类号：

摘要：

A multi-model fusion modeling method based on improved Kalman filter algorithm was presented for soft sensor of key quality index or state variable in the polymerization process. First, a data-driven soft-sensor modeling method was proposed by combining mixtures of kernels principal component analysis (K2PCA) with artificial neural network (ANN). Second, a parallel hybrid model was constructed by fusing the data-driven model with a mechanism model through an improved Kalman filtering algorithm. Moreover, a linear smoothing filter and a model variance updating method were adopted for optimizing the hybrid model, which could enhance performance and improve prediction stability of the hybrid model. The application of the proposed multi-model fusion modeling method in the vinyl chloride polymerization rate prediction verified that the hybrid model was more effective in comparison with single-model cases (thermodynamic mechanism model or K2PCA-ANN model). The proposed multi-model fusion modeling method would provide basic conditions for control and optimization of PVC polymerization process in further research. ©, 2015, Chemical Industry Press. All right reserved.

引用

页码：1388 / 1394

页数：6

共 21 条

[1]

Cao P., Luo X., Modeling of soft sensor for chemical process, CIESC Journal, 64, 3, pp. 788-800, (2013)

[2]

Yang H., Zhang S., Tao Z., A hybrid model for inference estimation of the performance figure in polymerization process, Journal of Chemical Engineering of Chinese Universities, 17, 5, pp. 552-558, (2003)

[3]

Zahedi G., Lohi A., Mahdi K.A., Hybrid modeling of ethylene to ethylene oxide heterogeneous reactor, Fuel Processing Technology, 92, 9, pp. 1725-1732, (2011)

[4]

Mjalli F.S., Ibrehem A.S., Optimal hybrid modeling approach for polymerization reactors using parameter estimation techniques, Chemical Engineering Research and Design, 89, 7, pp. 1078-1087, (2011)

[5]

Wang J.S., Guo Q.P., D-FNN based soft-sensor modeling and migration reconfiguration of polymerizing process, Applied Soft Computing, 13, 4, pp. 1892-1901, (2013)

[6]

Wu Y., Luo X., Design of output data fusion soft sensor based on adaptive extended Kalman filtering algorithm, CIESC Journal, 61, 10, pp. 2627-2635, (2010)

[7]

Chen K., Ji J., Wang H., Et al., Adaptive local kernel-based learning for soft sensor modeling of nonlinear processes, Chemical Engineering Research and Design, 89, 10, pp. 2117-2124, (2011)

[8]

Chen H., Hou D., Combination forecasting model based on forecasting effective measure with standard deviate, Journal of Systems Engineering, 18, 3, pp. 203-210, (2003)

[9]

Muller K.R., Mika S., Ratsch G., Tsuda K., Scholkopf B., An introduction to kernel-based learning algorithms, IEEE Transaction on Neural Networks, 12, 2, pp. 181-201, (2001)

[10]

Wang H., Yu J., Studies on modeling using mixture of kernels partial least squares and its application to soft Sensing, Computers and Applied Chemistry, 24, 2, pp. 239-242, (2007)

← 1 2 3 →