Gray-box modeling and control of polymer molecular weight distribution using orthogonal polynomial neural networks

Abstract A method of modeling and control on polymer molecular weight distribution (MWD) is presented in this paper. An orthogonal polynomial feedforward neural network (OPFNN) and a recurrent neural network (RNN) are combined to model the shape of MWD. In this combined neural networks, the weights of OPFNN are equivalent to moments of MWD through a linear transformation, when the polynomial used as the basis function of OPFNN satisfies some requirements. So the weights are given practical feature, and terms the neural network model a gray-box model. Then the requirements of polynomial are deduced. After modeling, an optimal control scheme is discussed on tracking the desired MWD during the polymerization process. The modeling error is added into the performance function to improve the control effect. The modeling and control method is tested on styrene polymerization reacted in CSTR, and simulation results proved the effectiveness of the method.

[1]  G. Févotte,et al.  Robust on-line measurement of conversion and molecular weight using NIR spectroscopy during solution polymerization , 2002 .

[2]  E. G. Chatzi,et al.  Recent Developments in Hardware Sensors For the On-Line Monitoring of Polymerization Reactions , 1999 .

[3]  Costas Kiparissides,et al.  A comprehensive model for the calculation of molecular weight–long-chain branching distribution in free-radical polymerizations , 1998 .

[4]  Sami Othman,et al.  On-line monitoring of methyl methacrylate–vinyl acetate emulsion copolymerization , 2000 .

[5]  Costas Kiparissides,et al.  Challenges in particulate polymerization reactor modeling and optimization: A population balance perspective , 2006 .

[6]  C. Kiparissides.  Polymerization reactor modeling: A review of recent developments and future directions , 1996 .

[7]  Enrique Luis Lima,et al.  In-line monitoring of weight average molecular weight in solution polymerizations using intrinsic viscosity measurements , 2001 .

[8]  W. Harmon Ray,et al.  The dynamic behavior of continuous polymerization reactors—I: Isothermal solution polymerization in a CSTR , 1981 .

[9]  Hyun-Ku Rhee,et al.  Online estimation and control of polymer quality in a copolymerization reactor , 2002 .

[10]  Hyun-Ku Rhee,et al.  Molecular Weight Distribution Control in a Batch Polymerization Reactor Using the On-Line Two-Step Method , 1999 .

[11]  José M. Asua,et al.  Control of Molecular Weight Distribution in Emulsion Polymerization Using On-Line Reaction Calorimetry , 2001 .

[12]  Lei Guo,et al.  Applying constrained nonlinear generalized PI strategy to PDF tracking control through square root B-spline models , 2004 .

[13]  Jyh-Shyong Chang,et al.  Optimization of Batch Polymerization Reactors Using Neural-Network Rate-Function Models , 2002 .

[14]  C. Georgakis,et al.  Nonlinear model predictive control of end-use properties in batch reactors , 2002 .

[15]  Ching-Shiow Tseng,et al.  An orthogonal neural network for function approximation , 1996, IEEE Trans. Syst. Man Cybern. Part B.

[16]  Zainal Ahmad,et al.  Modelling and control of different types of polymerization processes using neural networks technique: A review , 2010 .