Neural modelling of Mooney viscosity of polybutadiene rubber

Abstract Mooney viscosity is one of the important quality properties of polybutadiene rubber (PBR). It is important to implement appropriate measures to maintain and guarantee a uniform product quality required by the rubber processing industries. One major step towards quality assurance is the on line quality prediction of the product from the process parameters. This can be accomplished by developing a reliable model that predicts product quality as a function of process parameters. Artificial neural networks (ANN), which are capable of mapping highly complex and non-linear dependencies, have been adapted to develop models to predict Mooney and solution viscosity of PBR from process variables. Of the different networks trained with input–output data collected from plant history to predict Mooney and fluid viscosity (FV) from process variables, generalized regression neural networks (GRNN) mapped the input–output well compared to that of other networks. The predicted Mooney viscosity of PBR from the reactor outlet by GRNN was deviated by mean square error of 0.0252 when tested with new data.

[1]  T.,et al.  Training Feedforward Networks with the Marquardt Algorithm , 2004 .

[2]  Babu Joseph,et al.  Predictive control of quality in batch polymerization using hybrid ANN models , 1996 .

[3]  The Math Works, Inc..  The Math Works Inc , 1991, International Conference on Advances in System Simulation.

[4]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[5]  Yaman Arkun,et al.  Study of the control-relevant properties of backpropagation neural network models of nonlinear dynamical systems , 1992 .

[6]  Pradeep B. Deshpande,et al.  Predict difficult-to-measure properties with neural analyzers , 1997 .

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

[8]  D. Marquardt.  An Algorithm for Least-Squares Estimation of Nonlinear Parameters , 1963 .

[9]  Ken-ichi Funahashi,et al.  On the approximate realization of continuous mappings by neural networks , 1989, Neural Networks.

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

[11]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[12]  Fu-Chuang Chen,et al.  Adaptive control of nonlinear systems using neural networks , 1992 .

[13]  Taizo Hanai,et al.  Analysis of initial conditions for polymerization reaction using fuzzy neural network and genetic algorithm , 2003, Comput. Chem. Eng..

[14]  Thomas J. McAvoy,et al.  Neural net based model predictive control , 1991 .

[15]  Kenneth Levenberg.  A METHOD FOR THE SOLUTION OF CERTAIN NON – LINEAR PROBLEMS IN LEAST SQUARES , 1944 .

[16]  Donald F. Specht,et al.  A general regression neural network , 1991, IEEE Trans. Neural Networks.