[go: up one dir, main page]
More Web Proxy on the site http://driver.im/ Skip to main content
Springer Nature Link
Log in

Time-varying neural networks for multi-input multi-output systems: a reactive batch distillation modeling case study

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

A novel time-varying neural network (TVNN) architecture incorporating time dependency explicitly, proposed recently, for modeling nonlinear non-stationary dynamic systems is further developed in the present study to extend it to multi-input multi-output (MIMO) systems, and two configurations are proposed to represent dynamics of multivariable batch chemical processes. The first model (TVNN-multi-input single-output (MISO) model) consists of an input layer with M inputs representing the past samples of process inputs and outputs, a hidden layer with polynomial activation function, and a second hidden layer of L neurons acted upon by an explicitly time-dependent modulation function, which are combined to result in the output layer with a single output. This model is developed for each output in the MIMO system. In the second model (TVNN-MIMO model), multiple outputs are incorporated in the output layer. Back-propagation learning algorithm is formulated for the proposed neural network structures to determine the weights for each network configuration. The modeling capability of these networks is evaluated by employing it to represent the dynamics of a reactive batch distillation column for an esterification reaction. The results show that both the proposed neural networks configurations represent each composition of the reactive batch distillation dynamics accurately. Further, both the TVNNs exhibited better performance than time-independent networks trained using the same configuration. Both the TVNN configurations resulted in comparable performance, while the TVNN-MIMO model is more compact and requires less number of parameters. The present study illustrates that the proposed approach can be applied to represent dynamics of any batch/semi-batch process.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
£29.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (United Kingdom)

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Data availability

The data used for model development have been generated through simulations and can be shared on specific request.

References

  1. MGM Abdolrasol SMS Hussain TS Ustun MR Sarker MA Hannan R Mohamed JA Ali S Mekhilef A Milad 2021 Artificial neural networks based optimization techniques: A review Electronics 10 21 2689

    Article  Google Scholar 

  2. Z Abdullah N Aziz Z Ahmad 2007 Nonlinear modeling applications in distillation column Chem. Prod. & Proce. Modl https://doi.org/10.2202/1934-2659.1082

    Article  Google Scholar 

  3. G Alam I Ihsanullah M Naushad M Sillanpaa 2022 Applications of artificial intelligence in water treatment for optimization and automation of adsorption processes: Recent advances and prospects Chem Eng J 427 130011

    Article  Google Scholar 

  4. A Bahar C Ozgen 2010 State estimation and inferential control for a reactive batch distillation column Eng Appl Artif Intell 23 262 270

    Article  Google Scholar 

  5. R Baratti S Corti A Servida 1997 A feed forward control strategy for distillation columns Artifi Intell Eng 11 405 412

    Article  Google Scholar 

  6. E Brizuela M Uria R Lamanna 1996 Predictive control of a multi-component distillation column based on neural networks. NICROSP '96 Venice Italy

    Google Scholar 

  7. B Ganesh V VarunKumar KY Rani 2014 Modeling of batch process using explicitly time dependent Artificial Neural Networks IEEE Trans.Neu. Net.Learn.sys. 25 5 970 979

    Article  Google Scholar 

  8. B Ganesh KY Rani 2023 Dynamic modeling and optimal control of reactive batch distillation: An experimental case study Chem Eng Res Des 196 451 467

    Article  Google Scholar 

  9. MA Greaves IM Mujtaba M Barolo A Trotta MA Hussain 2003 Neural network approach to dynamic optimization of batch distillation application to a middle-vessel column Trans. IChemE, Part A. 81 393

    Article  Google Scholar 

  10. M Haghighatlari J Hachmann 2019 Advances of machine learning in molecular modeling and simulation Curr Opin Chem Eng 23 51 57

    Article  Google Scholar 

  11. DM Himmelblau 2000 Applications of neural networks in chemical engineering Korean J Chem Eng 17 373 392

    Article  Google Scholar 

  12. RS Hiwale NV Bhate YS Mahajan SM Mahajani 2004 Industrial applications of reactive batch distillation: recent trends Int J Chem React Eng 2 R1

    Google Scholar 

  13. M Iatrou TW Berger VZ Marmarelis 1999 Modeling of non-stationary dynamic systems with a novel class of artificial neural networks IEEE Trans Neural Networks 2 327 339

    Article  Google Scholar 

  14. AK Jana PVRK Adari 2009 Nonlinear state estimation and control of a batch reactive distillation Chem Eng J 150 516 526

    Article  Google Scholar 

  15. J Jawad AH Hawari S Javaid Zaidi 2021 Artificial neural network modeling of wastewater treatment and desalination using membrane processes: A review Chem. Eng. Journal 419 129540

    Article  Google Scholar 

  16. O Karahan C Ozgen U Hahci K Leblebicioglu 1997 Nonlinear model predictive controller using neural network. Neural Networks Int Conf 2 690 693

    Google Scholar 

  17. P Kathel AK Jana 2010 Dynamic simulation and nonlinear control of a rigorous batch reactive distillation ISA Trans 49 130 137

    Article  Google Scholar 

  18. J-P Lai Y-M Chang C-H Chen P-F Pai 2020 A Survey of Machine Learning Models in Renewable Energy Predictions Appl Sci 10 17 5975

    Article  Google Scholar 

  19. C Li C Duan J Fang H Li 2019 Process intensification and energy saving of reactive distillation for production of ester compounds Chin J Chem Eng 27 6 1307 1323

    Article  Google Scholar 

  20. VZ Marmarelis X Zhao 1997 Volterra models and three-layer perceptrons IEEE Trans Neural Netw 8 1421 1433

    Article  Google Scholar 

  21. K McBride K Sundmacher 2019 Overview of Surrogate Modeling in Chemical Process Engineering Chem Ing Tec 91 228 239

    Article  Google Scholar 

  22. R Mo H Wang 2021 Review of Neural Network Algorithm and Its Application in Reactive Distillation Asian J Chem Sci 9 3 20 29

    Google Scholar 

  23. Mujtaba IM, Greaves MA (2006) Neural network based modeling and optimization in batch distillation. IchemE, 152.

  24. Mujtaba IM, Konakom K, Kittisupakorn P, Saengchan A (2010) Optimal policy tracking of a batch reactive distillation by neural network-based model predictive Control (NNMPC) strategy. Vol .II, WCECS 2010, October 20–22, San Francisco, USA.

  25. R Patel K Singh V Pareek MO Tade 2007 Dynamic simulation of reactive batch distillation column for ethyl acetate system Chem. Produ. & Proce. Model https://doi.org/10.2202/1934-2659.1069

    Article  Google Scholar 

  26. KY Rani SC Patwardhan 2004 Data-driven modeling and optimization of semi-batch reactors using artificial neural networks Ind Eng Chem Res 43 7539 7551

    Article  Google Scholar 

  27. PS Reddy KY Rani SC Patwardhan 2017 Multi-objective optimization of a reactive batch distillation process using reduced order model Comput Chem Engg 106 40 56

    Article  Google Scholar 

  28. J Savkovic-Stevanovic 1996 Neural net controller by inverse modeling for a distillation Plant Comput & Chem Eng 20 925 930

    Article  Google Scholar 

  29. C Shu X Li H Li 2022 Design and optimization of reactive distillation: a review Front Chem Sci Eng 16 799 818

    Article  Google Scholar 

  30. WK Sun ARC Paiva P Xu A Sundaram RD Braatz 2020 Fault detection and identification using Bayesian recurrent neural networks Comput Chem Eng 141 22

    Article  Google Scholar 

  31. P Turner A Montague AJ Morris O Agammenoni C Pritchard G Barton J Romagnoli 1996 Application of a model based predictive control scheme to a distillation column using neural networks Procee. Ameri. Cont. Conf Washington

    Google Scholar 

  32. V Venkatasubramanian 2019 The promise of artificial intelligence in chemical engineering: Is it here, finally? AIChE J 65 466 478

    Article  Google Scholar 

  33. C Wang C Li 2021 Application of artificial neural network in distillation system: A critical review of recent progress Asian J Res Comp Sci 11 1 8 16

    Google Scholar 

  34. O Wieder S Kohlbacher M Kuenemann A Garon P Ducrot T Seidel T Langer 2020 A compact review of molecular property prediction with graph neural networks Drug Discov Today Technol 37 1 12

    Article  Google Scholar 

  35. Z Wu S Pan F Chen G Long C Zhang PS Yu 2021 A Comprehensive Survey on Graph Neural Networks IEEE Trans Neural Netw Learn Syst 32 4 24

    Article  MathSciNet  Google Scholar 

  36. Yu X (2003) A Neuromorphic controller for a distillation column. 4th IEEE Int.conf. (ICCA), Montreal, Canada.

  37. S Zhang K Bi T Qiu 2019 Bidirectional Recurrent Neural Network-Based Chemical Process Fault Diagnosis Ind Eng Chem Res 59 824 834

    Article  Google Scholar 

Download references

Acknowledgements

The authors acknowledge the Director, CSIR-IICT, for support (MS Ref. No. IICT/pubs./2023/132).

Author information

Authors and Affiliations

  1. Process Dynamics & Control and Artificial Intelligence Group, Chemical Engineering & Process Technology Department, CSIR- Indian Institute of Chemical Technology, Hyderabad, 500007, India

    P. Naveen Kumar, B. Ganesh, M. Vamsi Teja & K. Yamuna Rani

  2. Academy of Scientific and Innovative Research (AcSIR), Ghaziabad, 201002, India

    P. Naveen Kumar & K. Yamuna Rani

  3. Chemical Engineering Department, Chaitanya Bharathi Institute of Technology, Gandipet, Hyderabad, 500075, India

    B. Ganesh

Authors
  1. P. Naveen Kumar
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. B. Ganesh
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. M. Vamsi Teja
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. K. Yamuna Rani
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to K. Yamuna Rani.

Ethics declarations

Conflict of Interest

The authors declare that they have no conflicts of interest to disclose.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Kumar, P.N., Ganesh, B., Teja, M.V. et al. Time-varying neural networks for multi-input multi-output systems: a reactive batch distillation modeling case study. Neural Comput & Applic 36, 9157–9170 (2024). https://doi.org/10.1007/s00521-024-09556-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-024-09556-7

Keywords

Search

Navigation