Neural network model predictive control of a styrene polymerization plant: online testing using an electronic worksheet
-
Brunno Santos
,
Manuela Leite
Abstract
The batch styrene polymerization process presents transient and nonlinear temperature behavior. In this work, manual control and open loop experiments were carried out in order to build a process knowledge database. Initially, a cascade feedback control loop was implemented by manipulating the thyristor unit of the electrical heater in the thermal fluid tank. Aiming at the MPC development, algebraic equations of a neural network and its adjusted parameters were implemented in an electronic worksheet. Every five seconds, the worksheet was updated with measurements (reactor temperature, thermal fluid temperature and thyristor position) by means of the OLE for the Process Control protocol (OPC). The one-step-ahead temperature prediction was then employed in the objective function of the worksheet solver which used Visual Basic Applications programming. The manipulated variable action was then calculated and sent to the process. A hybrid controller (cascade feedback and MPC) outperformed the pure strategies since the time-integral performance indexes, IAE and ITAE, were reduced by around 22 % and 32 %, respectively. Methodology for the Model Predictive Control presented in this study was considered feasible because the solver of Microsoft Office Excel (2007) is very friendly, easy to understand and ready to implement using VBA.
[1] Altınten, A., Ketevanlioğlu, F., Erdoğan, S., Hapoğlu, F., & Alpbaz, M. (2008). Self-tuning PID control of a jacketed batch polystyrene reactor using genetic algorithm. Chemical Engineering Journal, 138, 490–497. DOI: 10.1016/j.cej.2007.07.029. http://dx.doi.org/10.1016/j.cej.2007.07.02910.1016/j.cej.2007.07.029Search in Google Scholar
[2] Aumi, S., Corbett, B., & Mhaskar, P. (2011). Data-based modeling and control of nylon-6,6 batch polymerization. American Control Conference on O’Farrell Street, June 29–July 01, 2011 (pp. 2540–2545). San Francisco, CA, USA: American Automatic Control Council. Search in Google Scholar
[3] Aumi, S., & Mhaskar, P. (2011). Robust model predictive control and fault handling of batch processes. AIChE Journal, 57, 1796–1808. DOI: 101002/aic.12398. http://dx.doi.org/10.1002/aic.1239810.1002/aic.12398Search in Google Scholar
[4] Bolf, N., Kopčić, N., Briški, F., & Gomzi, Z. (2007). Software sensors for monitoring of a solid waste composting process. Chemical Papers, 61, 98–102. DOI: 10.2478/s11696-007-0005-8. http://dx.doi.org/10.2478/s11696-007-0005-810.2478/s11696-007-0005-8Search in Google Scholar
[5] Fujiki, T. L., Schulz, C., da Silva, F. V., & Fileti, A. M. F. (2009). Artificial intelligence based controllers applied to a bromelain recovery process. In Proceedings of the 11th IASTED International Conference on Control and Applications, July 13–15, 2009 (Vol. 1. pp. 219–224). Cambridge, UK: ACTAPress. Search in Google Scholar
[6] Ghasem, N. M., Sata, S. A., & Hussian, M. A. (2007). Temperature control of a bench-scale batch polymerization reactor for polystyrene production. Chemical Engineering & Technology, 30, 1193–1202. DOI: 10.1002/ceat.200700165. http://dx.doi.org/10.1002/ceat.20070016510.1002/ceat.200700165Search in Google Scholar
[7] Hungenberg, K. D., Nieken, U., Zöllner, K., Gao, J., & Szekely, S. (2005). Modeling safety aspects of styrene polymerization processes. Industrial & Engineering Chemistry Research, 44, 2518–2524. DOI: 10.1021/ie0495372. http://dx.doi.org/10.1021/ie049537210.1021/ie0495372Search in Google Scholar
[8] Lepore, R., Wouwer, A. V., Remy, M., Findeisen, R., Nagy, Z., & Allgöwer, F. (2007). Optimization strategies for a MMA polymerization reactor. Computers and Chemical Engineering, 31, 281–291. DOI: 10.1016/j.compchemeng.2006.07.005. http://dx.doi.org/10.1016/j.compchemeng.2006.07.00510.1016/j.compchemeng.2006.07.005Search in Google Scholar
[9] Mahmood, M., & Mhaskar, P. (2008). Enhanced stability regions for model predictive control of nonlinear process systems. AIChE Journal, 54, 1487–1498. DOI: 10.1002/aic.11458. http://dx.doi.org/10.1002/aic.1145810.1002/aic.11458Search in Google Scholar
[10] Özkan, G., Hapoglu, H., & Alpbaz, M. (1998). Generalized predictive control of optimal temperature profiles in a polystyrene polymerization reactor. Chemical Engineering and Processing, 37, 125–139. DOI: 10.1016/s0255-2701(97)00047-0. http://dx.doi.org/10.1016/S0255-2701(97)00047-010.1016/S0255-2701(97)00047-0Search in Google Scholar
[11] Simões, P. S. R. (2001). Studies on the feasibility of simulation and diffusive effects prediction of polymerization reactions using first principles modeling and neural networks. PhD Thesis, FEQ/UNICAMP, Campinas, SP, Brazil. (in Portuguese) Search in Google Scholar
[12] Sui, D., Feng, L., & Hovd, M. (2009). Explicit moving horizon control and estimation: A batch polymerization case study. In 4th IEEE Conference on Industrial Electronics and Applications, ICIEA 2009, May 25–27, 2009 (pp. 1656–1661). DOI: 10.1109/iciea.2009.5138476. 10.1109/ICIEA.2009.5138476Search in Google Scholar
[13] Teixeira, R. (2001). Training artificial neural networks using multipurpose optimization: a new approach for the polarization and variance equilibrium. Ph.D. thesis, PPGEE-UFMG, Belo Horizonte, MG, Brazil. (in Portuguese) Search in Google Scholar
[14] Yoo, K. Y., Jeong, B. G., & Rhee, H. K. (1999). Molecular weight distribution control in a batch polymerization reactor using the on-line two-step method. Industrial & Engineering Chemistry Research, 38, 4805–4814. DOI: 10.1021/ie980799b. http://dx.doi.org/10.1021/ie980799b10.1021/ie980799bSearch in Google Scholar
[15] Zhang, J. (2004). A reliable neural network model based optimal control strategy for a batch polymerization reactor. Industrial & Engineering Chemistry Research, 43, 1030–1038. DOI: 10.1021/ie034136s. http://dx.doi.org/10.1021/ie034136s10.1021/ie034136sSearch in Google Scholar
© 2012 Institute of Chemistry, Slovak Academy of Sciences
Articles in the same Issue
- Determination of sulphur species in solidified cryolite melts
- Separation of alicyclic and aromatic hydrocarbons on a PLOT column coated with 3-benzylketoiminepropyl group
- Analysis and improvement of stability of pepsin-solubilized collagen from skin of carp (Cyprinus carpio)
- Effects of elicitors on the enhancement of asiaticoside biosynthesis in cell cultures of centella (Centella asiatica L. Urban)
- Increase of biogas production from pretreated hay and leaves using wood-rotting fungi
- Neural network model predictive control of a styrene polymerization plant: online testing using an electronic worksheet
- Influence of purine on copper behavior in neutral and alkaline sulfate solutions
- A parametric study on coal gasification for the production of syngas
- Tungstate sulfuric acid: preparation, characterization, and application in catalytic synthesis of novel benzimidazoles
- Synthesis of conjugated (E,E)-1,3-diene-containing troponoid-based compounds
- Reaction of aniline with ammonium persulphate and concentrated hydrochloric acid: Experimental and DFT studies
- Erratum to: “Zakaria Salmi, Sarra Gam-Derouich, Samia Mahouche-Chergui, Mireille Turmine, Mohamed M. Chehimi: On the interfacial chemistry of aryl diazonium compounds in polymer science”
Articles in the same Issue
- Determination of sulphur species in solidified cryolite melts
- Separation of alicyclic and aromatic hydrocarbons on a PLOT column coated with 3-benzylketoiminepropyl group
- Analysis and improvement of stability of pepsin-solubilized collagen from skin of carp (Cyprinus carpio)
- Effects of elicitors on the enhancement of asiaticoside biosynthesis in cell cultures of centella (Centella asiatica L. Urban)
- Increase of biogas production from pretreated hay and leaves using wood-rotting fungi
- Neural network model predictive control of a styrene polymerization plant: online testing using an electronic worksheet
- Influence of purine on copper behavior in neutral and alkaline sulfate solutions
- A parametric study on coal gasification for the production of syngas
- Tungstate sulfuric acid: preparation, characterization, and application in catalytic synthesis of novel benzimidazoles
- Synthesis of conjugated (E,E)-1,3-diene-containing troponoid-based compounds
- Reaction of aniline with ammonium persulphate and concentrated hydrochloric acid: Experimental and DFT studies
- Erratum to: “Zakaria Salmi, Sarra Gam-Derouich, Samia Mahouche-Chergui, Mireille Turmine, Mohamed M. Chehimi: On the interfacial chemistry of aryl diazonium compounds in polymer science”
