Melt index prediction by neural networks based on independent component analysis and multi-scale analysis

Abstract Reliable estimation of melt index (MI) is crucial for the production of polypropylene. Propylene polymerization process is highly nonlinear and characterized by multi-scale nature with lots of variables and information that are highly correlated and derived at different sample rates from different sensors. A novel soft-sensor architecture based on radial basis function networks (RBF) combining independent component analysis (ICA) as well as multi-scale analysis (MSA) is proposed to infer the MI of polypropylene from other process variables. In the proposed model, ICA is carried out to select the most independent process features and to eliminate the correlations of the input variables, MSA is introduced to acquire approximate and detailed scale information of the process and make the model more robust to mismatches, and RBF networks are used to characterize the nonlinearity in every scale. The approach is evaluated and the results are compared with simplified approaches built with the same data set. The research results confirm the validity of the proposed model.

[1]  Erkki Oja,et al.  Independent component analysis: algorithms and applications , 2000, Neural Networks.

[2]  Bidyut Baran Chaudhuri,et al.  Efficient training and improved performance of multilayer perceptron in pattern classification , 2000, Neurocomputing.

[3]  Jose M. F. Moura.  A geometric and multiresolution analysis approach to robust detection , 2001, Proceedings of the 11th IEEE Signal Processing Workshop on Statistical Signal Processing (Cat. No.01TH8563).

[4]  Jooyoung Park,et al.  Universal Approximation Using Radial-Basis-Function Networks , 1991, Neural Computation.

[5]  Alex Arenas,et al.  Neural virtual sensor for the inferential prediction of product quality from process variables , 2002 .

[6]  Wei Ge,et al.  Multi-scale methodology for complex systems , 2004 .

[7]  I. Daubechies.  Ten Lectures on Wavelets , 1992 .

[8]  J. Macgregor,et al.  On‐line inference of polymer properties in an industrial polyethylene reactor , 1991 .

[9]  Timothy F. L. McKenna,et al.  Single particle modelling for olefin polymerization on supported catalysts: A review and proposals for future developments , 2001 .

[10]  W.P.M. van Swaaij,et al.  FBR for catalytic propylene polymerization: Controlled mixing and reactor modeling , 2002 .

[11]  Shang-Liang Chen,et al.  Orthogonal least squares learning algorithm for radial basis function networks , 1991, IEEE Trans. Neural Networks.

[12]  Peter J. Gawthrop,et al.  Neural networks for control systems - A survey , 1992, Autom..

[13]  M. Omizo,et al.  Modeling , 1983, Encyclopedic Dictionary of Archaeology.

[14]  Aapo Hyvärinen,et al.  An alternative approach to infomax and independent component analysis , 2002, Neurocomputing.

[15]  Jinghai Li,et al.  Exploring complex systems in chemical engineering - the multi-scale methodology , 2003 .

[16]  D. J. Murraysmith,et al.  Methods for the external validation of contiuous system simulation models:a review , 1998 .

[17]  S. Gupta,et al.  Dynamic simulation of propylene polymerization in continuous flow stirred tank reactors , 1993 .

[18]  Mohamed Azlan Hussain,et al.  Review of the applications of neural networks in chemical process control - simulation and online implementation , 1999, Artif. Intell. Eng..

[19]  Jian-Huang Lai,et al.  Face representation using independent component analysis , 2002, Pattern Recognit..

[20]  Yung C. Shin,et al.  Radial basis function neural network for approximation and estimation of nonlinear stochastic dynamic systems , 1994, IEEE Trans. Neural Networks.

[21]  Michèle Basseville,et al.  Modeling and estimation of multiresolution stochastic processes , 1992, IEEE Trans. Inf. Theory.

[22]  Zheng Hua,et al.  The ANN of UMCP forecast based on developed ICA , 2004, 2004 IEEE International Conference on Electric Utility Deregulation, Restructuring and Power Technologies. Proceedings.

[23]  Rihard Karba,et al.  Incorporating prior knowledge into artificial neural networks - an industrial case study , 2004, Neurocomputing.

[24]  Simone G. O. Fiori,et al.  Overview of independent component analysis technique with an application to synthetic aperture radar (SAR) imagery processing , 2003, Neural Networks.