Skip to content
Licensed Unlicensed Requires Authentication Published by De Gruyter November 15, 2017

Recurrent Neural Network based Soft Sensor for Monitoring and Controlling a Reactive Distillation Column

Gaurav Kataria and Kailash Singh


For the real time monitoring of a Reactive Distillation Column (RDC), a Recurrent Neural Network (RNN) based soft sensor has been proposed to estimate the bottoms product composition of the RDC for the synthesis of n-Butyl Acetate using esterification reaction. This soft sensor acts as a measuring element in a closed loop involving a PI controller for the direct control of the RDC’s product concentration. The RNN acts as a dynamic network, which works on the sequential input data and output data with a recurrent connection. While using the RNN based soft sensor in the open loop, it has been observed that the sensor estimated the composition of butyl acetate in the bottoms with such an accuracy that it can be used for the control purpose. Closed loop results demonstrated that the system has been showing precise controlled results and soft sensor is showing small prediction Mean Square Error (MSE) when disturbances in feed flow rate and set point changes are introduced.


[1] Dong D, McAvoy T, Chang L. Emission monitoring using multivariate soft sensors. In: Proceedings of 1995 American Control Conference - ACC’95, volume 1, American Autom Control Council, Volume 1, 1995: 761–765.10.1109/ACC.1995.529353Search in Google Scholar

[2] Wang X, Luo R, Shao H. Designing a soft sensor for a distillation column with the fuzzy distributed radial basis function neural network. In: Proceedings of 35th IEEE Conference on Decision and Control, Volume 2, IEEE, Volume 2, 1996: 1714–1719.10.1109/CDC.1996.572803Search in Google Scholar

[3] Hong SJ, Jung JH, Han C, Tham MT, Montague GA, Morris AJ, Lant PA. A design methodology of a soft sensor based on local models. Comput Chem Eng. 1999;23:S351–S354.10.1016/S0098-1354(99)80086-6Search in Google Scholar

[4] Fortuna L, Graziani S, Xibilia M. Soft sensors for product quality monitoring in debutanizer distillation columns. Control Eng Pract. 2005;13:499–508.10.1016/j.conengprac.2004.04.013Search in Google Scholar

[5] Rani A, Singh V, Gupta JRP. Development of soft sensor for neural network based control of distillation column. ISA Trans. 2013;52:438–449.10.1016/j.isatra.2012.12.009Search in Google Scholar PubMed

[6] Shang C, Yang F, Huang D, Lyu W. Data-driven soft sensor development based on deep learning technique. J Process Control. 2014;24:223–233.10.1016/j.jprocont.2014.01.012Search in Google Scholar

[7] Jalee EA, Aparna K. Neuro-fuzzy soft sensor estimator for benzene toluene distillation column. Procedia Technol. 2016;25:92–99.10.1016/j.protcy.2016.08.085Search in Google Scholar

[8] Arpornwichanop A, Koomsup K, Kiatkittipong W. Production of n -butyl acetate from dilute acetic acid and n -butanol using different reactive distillation systems : economic analysis. J Taiwan Inst Chem Eng. 2009;40:21–28.10.1016/j.jtice.2008.07.009Search in Google Scholar

[9] Delgado-delgado R, Hernández S, Barroso-mu FO, Segovia-hernández JG, Castro-montoya AJ. From simulation studies to experimental tests in a reactive dividing wall distillation column. Chem Eng Res Des. 2012;90:855–862.10.1016/j.cherd.2011.10.019Search in Google Scholar

[10] Fernandez MF, Barroso B, Meyera X-M, Meyer M, Lann M-VL, Roux GCL, Brehelin M. Experiments and dynamic modeling of a reactive distillation column for the production of ethyl acetate by considering. Chem Eng Res Des. 2013;91:2309–2322.10.1016/j.cherd.2013.05.013Search in Google Scholar

[11] Gangadwala J, Kienle A, Stein E, Mahajani S. Production of butyl acetate by catalytic distillation : process design studies. Ind Eng Chem Res. 2004;43:136–143.10.1021/ie021011zSearch in Google Scholar

[12] Gangadwala J, Mankar S, Mahajani S, Kienle A, Stein E. Esterification of acetic acid with Butanol in the presence of Ion-Exchange resins as catalysts. Ind Eng Chem Res. 2003;42:2146–2155.10.1021/ie0204989Search in Google Scholar

[13] Hanika J, Kolena J, Smejkal Q. Butylacetate via reactive distillation * modelling and experiment. Chem Eng Sci. 1999;54:5205–5209.10.1016/S0009-2509(99)00241-9Search in Google Scholar

[14] Huss RS, Chen F, Malone MF, Doherty MF. Reacti v e distillation for methyl acetate production. Comp Chem Eng. 2003;27:1855–1866.10.1016/S0098-1354(03)00156-XSearch in Google Scholar

[15] Jimenez L, Garvn A, Costa-Lopez J. The production of butyl acetate and methanol via reactive and extractive distillation. I. Chemical equilibrium, Kinetics, and mass-transfer issues. Ind Eng Chem Res. 2002;41:6663–6669.10.1021/ie0107643Search in Google Scholar

[16] Kathel P, Jana AK. Dynamic simulation and nonlinear control of a rigorous batch reactive distillation. ISA Trans. 2010;49:130–137.10.1016/j.isatra.2009.09.007Search in Google Scholar PubMed

[17] Singh D, Kumar R, Kumar V. Simulation of a plant scale reactive distillation column for esterification of acetic acid. Comput Chem Eng. 2015;73:70–81.10.1016/j.compchemeng.2014.11.007Search in Google Scholar

[18] Steinigeweg S, Gmehling J. n -butyl acetate synthesis via reactive distillation : thermodynamic aspects, reaction kinetics, pilot-plant experiments, and simulation studies. Ind Eng Chem Res. 2002;41:5483–5490.10.1021/ie020179hSearch in Google Scholar

[19] Venimadhavan G, Malone MF, Doherty MF. A novel distillate policy for batch reactive distillation with application to the production of butyl acetate. Ind Eng Chem Res. 1999;38:714–722.10.1021/ie9804273Search in Google Scholar

[20] Bahar A, Özgen C. State estimation and inferential control for a reactive batch distillation column. Eng Appl Artif Intell. 2010;23:262–270.10.1016/j.engappai.2009.11.003Search in Google Scholar

[21] Khazraee SM, Jahanmiri AH. Composition estimation of reactive batch distillation by using adaptive Neuro-Fuzzy inference system. Chinese J Chem Eng. 2010;18:703–710.10.1016/S1004-9541(10)60278-9Search in Google Scholar

[22] Olanrewaju MJ, Al-Arfaj MA. Estimator-based control of reactive distillation system: application of an extended Kalman filtering. Chem Eng Sci. 2006;61:3386–3399.10.1016/j.ces.2005.12.009Search in Google Scholar

[23] Sumana C, Venkateswarlu C. Optimal selection of sensors for state estimation in a reactive distillation process. J Process Control. 2009;19:1024–1035.10.1016/j.jprocont.2009.01.003Search in Google Scholar

[24] Venkateswarlu C, Jeevan Kumar B. Composition estimation of multicomponent reactive batch distillation with optimal sensor configuration. Chem Eng Sci. 2006;61:5560–5574.10.1016/j.ces.2006.04.023Search in Google Scholar

[25] Vijaya Raghavan SR, Radhakrishnan TK, Srinivasan K. Soft sensor based composition estimation and controller design for an ideal reactive distillation column. ISA Trans. 2011;50:61–70.10.1016/j.isatra.2010.09.001Search in Google Scholar PubMed

[26] Sakhre V, Jain S, Sapkal VS, Agarwal DP. Modifi ed neural network based cascaded control for product composition of reactive distillation. Pol J Chem Technol Polish J Chem Technol. 2016;18:111–111.10.1515/pjct-2016-0037Search in Google Scholar

[27] Luyben WL, Yu C. Reactive distillation design and control. Hoboken, NJ, USA: John Wiley & Sons, Inc., 2008: 147–149.10.1002/9780470377741Search in Google Scholar

[28] Pascanu R, Gülçehre Ç, Cho K, Bengio Y. How to construct deep recurrent neural networks. CoRR, 2013; abs/1312.6026, in Google Scholar

Received: 2017-07-10
Revised: 2017-10-01
Accepted: 2017-10-28
Published Online: 2017-11-15

© 2018 Walter de Gruyter GmbH, Berlin/Boston