Inferential control strategies using neural soft sensor in a high purity distillation column


  • Arioston Araújo de Morais Júnior
  • José Carlos Finiz Filho
  • Leopoldo Oswaldo Alcazar Rojas
  • Romildo Pereira Brito



High Purity Column, Soft Sensor, Artificial Neural Network, Inferential Control


High-purity distillation columns are processes in which you want to minimally increase the purity of a key component by separation. These processes are sensitive to disturbances, where small changes in the feed flowrate stream cause drastic changes in product compositions. Furthermore, when one wants to apply traditional control and optimization techniques to these processes, some difficulties have to be faced: the process is generally non-linear and has a long response time, there are many immeasurable disturbances, it is difficult to keep the process in steady-state, and the bottom and top compositions are highly coupled. Therefore, this paper presents a methodology for the development of soft sensors (SS), here in applied to an industrial 1,2-Dichloroethane separation plant. The process was simulated and validated with real data from the industrial plant. In the step second an algorithm based on multivariate statistics was developed for the selection of inputs SS variables. The configuration for training multilayer artificial neural network (ANN's) was optimize, accounting for the ANN's prediction capacity of responses and the rejection of disturbances inserted in the process. Thereafter, a temperature control was implemented to maintain the impurity compositions within specifications but failed due to the small temperature variations in the high purity column. To overcome these difficulty three inferential control strategies (impurity composition estimated by the SS) were implemented: a classic feedback control, a cascade control, and a ratio-cascade control. All control strategies acted to minimize the process disturbances effects. However, the inferential ratio-cascade control shown to be the most robust, because of the lowest integral error criteria value and percentage overshoot.


ANDERSON, R. H.; et al. Efficiency Comparison of Valve and Sieve Trays in Distillation Columns. Ind. Eng. Chem., Process Des. Dev., Vol. 15, No. 1. 1976.

BATTITI, R. First- and second-order methods for learning between steepest descent and Newton’s method. Neural Computation, vol. 4, no. 2, pp. 141-166. 1992.

CAMPOS, M.; et al. Advanced Control and Optimization in the Oil Industry. Ed. Interciência, Brazil. 2013.

COULIBALY, P.; et al. Daily reservoir inflow forecasting using artificial neural networks with stopped training approach. Journal of hydrology, Vol. 230, Issues 3–4, 8 May 2000, pp. 244-257. 2000.

DEMUTH, H., BEALE, M. Neural Network Toolbox for Use with Mathlab®, User’s Guide, Version 4. Mathworks Inc. 2002.

DIMIAN, A. C.; SORIN, C. B. Vinyl Chloride Monomer Process. Chemical Process Design: Computer-Aided Case Studies. Wiley-Vch & Co. KGa A, Weinheim. 2008.

FORTUNA, L.; et al. Soft sensors for product quality monitoring in debutanizer distillation columns. Control Engineering Practice, V. 13(4), 499-508. 2005.

G II-GLOBAL INFORMATION. Available in 2023.

GOLDBERG, Y. Neural Network Methods in Natural Language Processing. Synthesis Lectures on Human Language Technologies. Book 37, Morgan & Claypool Pub. 2017.

HAYKIN, S. Neural networks and learning machines. Book, Pearson Prentice Hall, 3rd ed. 2009.

HSIAO, YU-DA; et al. Development of Robust and Physically Interpretable Soft Sensor for Industrial Distillation Column Using Transfer Learning with Small Datasets. Processes 2021, 9, 667. 2021.

KADLEC, P.; GABRYS, B. Learnt topology gating artificial neural network. In Proceedings of the 2008 IEEE international joint conference on neural networks, pp. 2605–2612. 2008.

KADLEC, P.; et al. Data-driven Soft Sensors in the process industry. Computers and Chemical Engineering, pages 795–814. 2009.

KALBANI, F. AL.; ZHANG, J. Inferential Composition Control of a Distillation Column Using Active Disturbance Rejection Control with Soft Sensors. Sensors 2023, 23, 1019. 2023.

KANO, M.; et al. Inferential control system of distillation compositions using dynamic partial least squares regression. Journal of Process Control 10, 157-166. 2000.

KANO, M.; et al. Two-stage subspace identification for softsensor design and disturbance estimation. Journal of Process Control, pp. 179–186, doi:10.1016/j.jprocont.2008.04.004, Elsevier. 2009.

KERMANI, B.G.; et al. Performance of the Levenberg–Marquardt neural network training method in electronic nose applications. Science Direct, Sensors and Actuators B: Chemical, Volume 110, Issue 1, pp. 13-22. 2005.

LUO, R.F.; et al. Fuzzy-neural-net-based inferential control for a high-purity distillation column. Control Eng. Practice, Vol. 3, No. 1, pp. 31-40. 1995.

LUYBEN, W. L. Distillation design and control using Aspen simulation. 2nd ed., John Wiley & Sons, Inc. All rights reserved. 2013.

MEJDELL, T.; SKOGESTAD, S. Output estimation using multiple secondary measurements: High-Purity Distillation. AIChE Journal, 39 (10), 1641-1653. 1993.

MING-DA MA; et al. Development of adaptive soft sensor based on statistical identification of key variables. Control Engineering Practice, pp. 10-19. 2009.

MONTGOMERY, D.C.; RUNGER, G. C. Applied Statistics and Probability for Engineers. Sixth Edition, Book, Wiley. 2014.

MOORE, C.F. Selection of Controlled and Manipulated Variables, In Practical Distillation Control, Van Nostrand-Reinhold, pp. 140-177, Chapter 8. 1992.

MORAIS JR., A. A. Use of soft sensors to estimate impurities in high-purity distillation columns. PhD thesis, Federal University of Campina Grande-Pb, Brazil. 2015.

NYENG, I. Modeling of a 1,2-Dichloroethane Cracker. Thesis of the doctoral, Chemical Engineering and Biotechnology, IKP. University of Science and Technology Norwegian University of Science and Technology. 2015.

MORAIS Jr, A. A.; et al. Extended Kalman filter and artificial neural network for concentration estimation in a non-isothermal chemical reactor. Brazilian Journal of Development, Curitiba, v. 5, n. 11, p. 22751-22756, ISSN 2525-8761. 2019.

POLING, B. E.; et al. The properties of Gases and Liquids. 5ª Ed, New York, McGraw-Hill. 2001.

OLIVEIRA, T. C. L; et al. CFD Simulation of an Industrial Reactor for Thermal Cracking of 1,2-Dichloroethane. Brazilian Journal of Chemical Engineering, Vol. 34, No. 02, pp. 541 - 555, 2017.

RANI, A; et al. Development of soft sensor for neural network-based control of distillation column. ISA Transactions 52, pp. 438–449. 2013.

RUMELHART, D. E.; et al. Learning internal representations by error propagation. In Parallel Distributed Processing, Cambridge, MIT Press, vol 1, pp. 318-362. 2002.

SILVA, I. N.; et al. Artificial Neural Networks: A Practical Course. Springer International Publishing Switzerland. 2017.

WANG, Z. X.; et al. Comparison of variable selection methods for PLS-based soft sensor modeling. Journal of Process Control 26 PP. 56-72, 0959-1524, Elsevier. 2015.

WANGDONG NI, et al. A localized adaptive soft sensor for dynamic system modeling. Chemical Engineering Science 111, pp. 350–363. 2014.

WENXIANG, L.; et al. A New Strategy of Integrated Control and On-line Optimization on High-purity Distillation Process. Chinese Journal of Chemical Engineering, Volume 18, Pages 66–79, 1, 2010.

TAYLOR, B. J. Methods and procedures for the verification and validation of artificial neural networks. Book, Springer. 2006.

UDUGAMA, I. A.; et al. Novel Soft Sensor for Measuring and Controlling Product Recovery in a High-Purity, Multicomponent, Side-Draw Distillation Column. Ind. Eng. Chem. Res., 58, 43, 20026–20035. 2019.

ZAMPROGNA, E.; et al. 2005. Optimal selection of soft sensor inputs for batch distillation columns using principal component analysis. Journal of Process Control 15: 39–52. 2005.




How to Cite

Morais Júnior, A. A. de, Finiz Filho, J. C., Rojas, L. O. A., & Brito, R. P. (2024). Inferential control strategies using neural soft sensor in a high purity distillation column. Caderno Pedagógico, 21(5), e4402 .