Development of genetic programming based softsensor model for styrene polymerization process and its application in model based control

In recent years, soft sensors have been established as a valuable alternative to the traditional hardware sensors for the acquisition of critical information regarding "difficult-to-measure" process variables and/or parameters in chemical process monitoring and control. Soft-sensors can also be modified as a novel process identification tool for process monitoring and model based control. Often, in polymer industries the main polymerization reaction is highly nonlinear and complex to model accurately by the conventional "first principles" approach. In such cases, genetic programming (GP) - a novel artificial intelligence-based exclusively data-driven modeling technique - can be employed for process identification. In this work GP-based soft sensors have been developed for a continuous styrene polymerization reactor. The resulting GP-based models (soft sensor) showed high prediction and generalization performances. The best performing model was successfully utilized in designing a model predictive control (MPC) scheme for the polymerization reactor.

[1]  John R. Richards,et al.  Measurement and control of polymerization reactors , 2006, Comput. Chem. Eng..

[2]  Riccardo Poli,et al.  A Field Guide to Genetic Programming , 2008 .

[3]  H. Rhee,et al.  An experimental study for property control in a continuous styrene polymerization reactor using a polynomial ARMA model , 2002 .

[4]  Rahul Bindlish,et al.  Nonlinear model predictive control of an industrial polymerization process , 2015, Comput. Chem. Eng..

[5]  Myung-June Park,et al.  Polymer property control in a continuous styrene polymerization reactor using model-on-demand predictive controller , 2003 .

[6]  Mohd Azlan Hussain,et al.  Control of polystyrene batch reactors using neural network based model predictive control (NNMPC): An experimental investigation , 2011 .

[7]  Daniel R. Lewin,et al.  Automated Nonlinear Model Predictive Control using Genetic Programming , 2002 .

[8]  John R. Koza,et al.  Genetic Programming II , 1992 .

[9]  Ferenc Szeifert,et al.  Genetic programming for the identification of nonlinear input-output models , 2005 .

[10]  Hod Lipson,et al.  Distilling Free-Form Natural Laws from Experimental Data , 2009, Science.

[11]  Darci Odloak,et al.  Observer-based fault diagnosis in chemical plants , 2005 .

[12]  Jinfang Zhang,et al.  Predictive PDF control in shaping of molecular weight distribution based-on a new modelling Algorithm , 2015 .

[13]  In Sun Kim,et al.  Recent advances in polymer reaction engineering: Modeling and control of polymer properties , 2004 .

[14]  Babatunde A. Ogunnaike,et al.  Process Dynamics, Modeling, and Control , 1994 .

[15]  Bhaskar D. Kulkarni,et al.  Consider genetic programming for process identification , 1999 .

[16]  H. Rhee,et al.  Polynomial ARMA model identification for a continuous styrene polymerization reactor using on-line measurements of polymer properties , 2000 .

[17]  Sanjeev S. Tambe,et al.  Computational intelligence based models for prediction of elemental composition of solid biomass fuels from proximate analysis , 2017, Int. J. Syst. Assur. Eng. Manag..

[18]  Thomas F. Edgar,et al.  Process Dynamics and Control , 1989 .

[19]  S. S. Tambe,et al.  Prediction of Higher Heating Value of Solid Biomass Fuels Using Artificial Intelligence Formalisms , 2013, BioEnergy Research.