Modeling of a linear neural network with inverse error propagation for the main channels of acetic acid synthesis reactor control
DOI:
https://doi.org/10.33216/1998-7927-2023-279-3-31-36Keywords:
neural networks, error back propagation, reactorAbstract
Nowadays, to control technological objects, one can use neural networks, fuzzy logic and genetic algorithms. There have been few attempts to use artificial intelligence technologies to build automatic control systems.
However, only in recent years, with the growth of research in the field of nonlinear control, the use of artificial intelligence technologies in the management of technological processes has become widespread.
Simulation and research of the work of artificial neural networks can be carried out with the help of software simulators. The most common packages for modeling the properties of neural networks are Neural Works Pro Plus, Neuro Solution, Matlab (Neural Network Toolbox), Neuro Wisard, ANsim, Neural Ware and others. Programs differ in complexity, number of types of neurons and learning algorithms supported in the system.
The article investigates the construction of linear neural networks with backpropagation of the error for the main control channels of the acetic acid synthesis reactor.
To construct and study the properties of the neural network, statistical data of the acetic acid synthesis reactor in the stationary mode of the Severodonetsk acetic acid workshop of CJSC "Azot" were used.
The MATLAB 2021 software simulator environment was used for simulation. This program is recommended for modeling different neural networks with different number of neurons and different type of activation function. An iterative procedure was used to build the neural network.
Neural network architecture: the first layer contains first 9 neurons, then 23 neurons, and later 46 neurons with tansig activation function. The second layer contains one neuron with purelin activation function. Input change range [8900-9800].
Neural network training was performed for 50 cycles. Then network modeling was performed. At the end of the simulation, the relative error for the network output was calculated.
In the event that the dependencies are linear in nature, linear neural networks with backpropagation of the error can be used to approximate the data. All created and modeled neural networks for all main control channels showed satisfactory data approximation quality. The quality of data approximation was less than 1% in all cases. This will allow the use of neural networks to control technological processes of acetic acid synthesis and the prospects for further research in this area.
References
1. Бойко С. Застосування нейронних мереж при автоматизації діагностики стану авіаційного генератора гвинтокрила.// С. Бойко, Є. Волканін, О. Городній, О. Борисенко, Л. Вершняк.- ТЕХНІЧНІ НАУКИ ТА ТЕХНОЛОГІЇ.- 2018.-№ 3 (13), С.152-160
2. Маковецька, С. В. Застосування штучних нейронних мереж для прогнозування динаміки технологічного процесу в умовах невизначеності / С. В. Маковецька, О. М. Мягшило // Сучасні методи, інформаційне, програмне та технічне забезпечення систем управління організаційно-технічними та технологічними комплексами: програма та матеріали ІІ Міжнародної науково-технічної Internet-конференції, 25 листопада 2015 р. [Електронний ресурс] – К.: НУХТ, 2015. – С. 188-189. - Режим доступу: https://nuft.edu.ua/page/view/konferentsii.
3. Гончаренко Т. А. Застосування технології штучних нейронних мереж для моделювання рельєфу будівельного майданчика/Т. А. Гончаренко// Управління розвитком складних систем: зб. наук. робіт / Київ. нац. ун-т буд-ва та архітектури; гол. ред. Лізунов П. П. – Київ: КНУБА, 2017. – № 29. – С. 116 – 120.
4. Paredes-Astudillo Y.A. Comparing linear and non-linear modelling approaches of learning effects in 2-stage flow-shop scheduling problems/ Y. A. Paredes-Astudillo, V. Botta-Genoulaz, J. R. Montoya-Torres // IFAC Papers OnLine .- 55-10 (2022), P. 842–847
5. Steentjes Tom R.V. Handling unmeasured distur-bances in data-driven distributed control with virtual reference feedback tuning/ Tom R.V. Steentjes, Paul M.J. Van den Hof, Mircea Lazar // IFAC Pa-persOnLine.- 54-7 (2021), P. 204–209
6. Borg D. Neural networks as a diagnosing tool for industrial level measurement through non contacting radar type and support to the decision for its better application / D. Borg, F. F. Pinto, M. Suetake, D. Brandão// IFAC-PapersOnLine.- 49-30 (2016).-p. 349–354
7. Topolski N.G. Computer Aided Fire safety Systems in Chemical Industries. / N.G.Topolski, V.S.Vatagin, // Mary Kay O’Connor Process Safety Center Symposium. -Proceeding.- October 24-25.- 2000.- Reed Arena.- Texas A&M. -University, College Station, Texas- p.348-349.
8. Baskin I.I. Quantitative chemical structure – proper-ty/activity relationship studies using artificial neural networks. / I.I. Baskin, M.I.Skvortsova, V.A.Palyulin, N.S.Zefirov // Foun-dations of Com-puting and Decision Sciences. - 1997. - Vol. 22, № 2. – P. 107-116.
9. PorkujanOlga «Neuralnetworksimulationinrunningofaceticacids-yntesisunitwhilestart-up»/ OlgaPorkujan, ZhannaSamojlova.- TEKA, Польща, AcademyofSciences (PAN), withregisteredofficesinWarsaw, 2013, p.188-192
10. Tronci S. A Gain-Scheduling PI Control Based on Neural Networks/ Stefania Tronci , Roberto Barat-ti//Hindawi Complexity Volume 2017, Article ID 9241254, 8 pages
11. Joschka W. Overcoming the modeling bottleneck: A methodology for dynamic gray-box modeling with optimized training data / Winz J. , Fromme F., Engell S. Process Dynamics and Operations Group, TU Dortmund University, Energy reports, -Issue 10. - November 2023, pages 396-406
12. Moon Un-Chul. A comparative study of water wall model with a linear model and a neural network model/ Un-Chul Moon, Jaewoo Lim, Geon Go, Kwang. Y. Lee//Proceedings of the 19th World Congress The International Federation of Automatic Control Cape Town, South Africa. August 24-29, 2014, p.1446-1451
13. Самойлова Ж.Г. Розробка математичної моделі технологічних процесів в реакторі синтезу оцтової кислоти/ Ж.Г.Самойлова// Eastern-European Journal of Enterprise Technologies, 5/2 ( 113 ), 2021, С.94-104
