«Automation and Informatization of the fuel and energy complex»

A genetic algorithm application for searching the optimal composition of a reaction mixture based on a kinetic model of the process

UDC: 544.4:004.4
DOI: -

Authors:

¹ MIREA - Russian Technological University, Moscow, Russia
² Ufa University of Science and Technology, Ufa, Russia

Keywords: genetic algorithm, optimization, kinetics, software module, information system

Annotation:

The authors of the article present the main stages of a genetic algorithm software implementation for solving an optimization problem based on a kinetic model of the process. The development of effective methods and algorithms that allow reliable achievement of a global optimum for solving the problem is one of the scientific problems the solution of which required evaluating the effectiveness of various numerical approaches. Based on the evaluation carried out, a genetic algorithm was selected to solve the problem, which allows using the principles of stochastic search and global optimization to conduct the most effective study of the solution space regardless of the system parameters number. The software implementation of the algorithm, written in Python, was included in the computing core of a previously developed information system aimed at a comprehensive study of complex physical-chemical processes. To formulate the problem, determine the kinetic scheme of reactions and the main parameters of the algorithm, separate dialog boxes were created that determine the content of the web interface part of the system. The user gets the opportunity of forming a model of chemical transformations kinetics determined by the elementary reactions scheme. This program and other modules launching included in the computing core of this system is organized in a remote space using Docker containerization technology, which is a software virtualization at the operational system level. In order to demonstrate the functionality and capabilities of the created digital product, the main steps of the study of the kinetics of the Michaelis – Menten enzymatic reaction, which is widely used in scientific research and is one of the classic models in biochemical kinetics, are presented in detail. The integration of a genetic algorithm into the existing information system expands its capabilities and allows successful solution of optimization problems for a user-defined model description using remote network resources.

Bibliography:

1. Spivak S.I., Asadullin R.M. Methods of elimination and the problem of nonuniqueness of inverse problem solutions in models of non-stationary chemical kinetics // Studies in Surface Science and Catalysis. – 1997. – Vol. 109. – P. 577–586. – DOI: 10.1016/S0167-2991(97)80448-X
2. Application of gradient optimization methods in defining neural dynamics / P.S. Stanimirović, N. Tešić, D. Gerontitis [et al.] // Axioms. – 2024. – Vol. 13, No. 1. – P. 49. – DOI: 10.3390/axioms13010049
3. Panteleev A., Lobanov A. Gradient Optimization Methods in Machine Learning for the Identification of Dynamic Systems Parameters // Modelling and Data Analysis. – 2019. – Vol. 9, No. 4. – P. 88–99. – DOI: 10.17759/mda.2019090407
4. Takenaga S., Ozaki Y., Onishi M. Practical initialization of the Nelder-Mead method for computationally expensive optimization problems // Optimization Letters. – 2023. – Vol. 17. – P. 283–297. – DOI: 10.1007/s11590-022-01953-y
5. Tian Yingjie, Zhang Yuqi, Zhang Haibin. Recent Advances in Stochastic Gradient Descent in Deep Learning // Mathematics. – 2023. – Vol. 11, No. 3. – P. 682. – DOI: 10.3390/math11030682
6. Reyad M., Sarhan A.M., Arafa M. A modified Adam algorithm for deep neural network optimization // Neural Computing and Applications. – 2023. – Vol. 35. – P. 17095–17112. – DOI: 10.1007/s00521-023-08568-z
7. Panteleev A.V., Skavinskaya D.V., Aleshina E.A. Metaevristicheskie algoritmy poiska optimal'nogo programmnogo upravleniya. – M.: Infra-M, 2024. – 396 s.
8. Antipina E.V., Mustafina S.A., Antipin A.F. Poisk optimal'nogo upravleniya neftekhimicheskim protsessom s terminal'nymi ogranicheniyami na osnove metoda differentsial'noy evolyutsii // Avtomatizatsiya i informatizatsiya TEK. – 2023. – № 2(595). – S. 31–36. – DOI: 10.33285/2782-604X-2023-2(595)-31-36
9. Gad A.G. Particle Swarm Optimization Algorithm and Its Applications: A Systematic Review // Archives of Computational Methods in Engineering. – 2022. – Vol. 29, Issue 5. – P. 2531–2561. – DOI: 10.1007/s11831-021-09694-4
10. Grabusts P., Musatovs J., Golenkov V. The application of simulated annealing method for optimal route detection between objects // Procedia Computer Science. – 2019. – Vol. 149. – P. 95–101. – DOI: 10.1016/j.procs.2019.01.112
11. Katoch S., Chauhan S.S., Kumar V. A Review on Genetic Algorithm: Past, Present, and Future // Multimedia Tools and Applications. – 2021. – Vol. 80, Issue 5. – P. 8091–8126. – DOI: 10.1007/s11042-020-10139-6
12. Developing Methods and Algorithms for Cloud Computing Management Systems in Industrial Polymer Synthesis Processes / Miftakhov E., Mustafina S., Akimov A. [et al.] // Emerging Science J. – 2021. – Vol. 5, No. 6. – P. 964–973. – DOI: 10.28991/esj-2021-01324
13. Xu Delei, Xu Haoming. Application of genetic algorithm in model music composition innovation // Applied Mathematics and Nonlinear Sciences. – 2024. – Vol. 9, Issue 1. – P. 1–15. – DOI: 10.2478/amns.2023.2.00070
14. A Multifactorial Cellular Genetic Algorithm for Multimodal Multitask Optimization / E. Osaba, J. Del Ser, A.D. Martinez, J.L. Lobo // 2022 IEEE Congress on Evolutionary Computation (CEC), Padua, Italy, July 18–23, 2022. – P. 1–8. – DOI: 10.1109/CEC55065.2022.9870324
15. Aladdin A.M., Rashid T.A. A New Lagrangian Problem Crossover – A Systematic Review and Meta-Analysis of Crossover Standards // Systems. – 2023. – Vol. 11, No. 3. – P. 144. – DOI: 10.3390/systems11030144
16. Svidetel'stvo o gos. registratsii programmy dlya EVM 2023669318 Ros. Federatsiya. Issledovanie fiziko-khimicheskikh protsessov s primeneniem oblachnykh tekhnologiy / E.N. Miftakhov, S.A. Mustafina; pravoobladatel' FGBOU VO "Ufimskiy un-t nauki i tekhnologiy". – № 2023668618; zayavl. 08.09.2023; opubl. 13.09.2023, Byul. № 9.
17. Blazor for ASP.NET Web Forms Developers / D. Roth, J. Fritz, T. Southwick [et al.]. – Version 6.0. – Redmond, Washington: Microsoft Corporation, 2023. – IV, 92 p.
18. Ljungdahl V. Performance comparison of distributed MySQL and MongoDB in a cloud environment: Independent thesis Basic level (degree of Bachelor). – Karlskrona, Sweden: Blekinge Institute of Technology, 2023. – 46 p.
19. Kane S.P., Matthias K. Docker: Up & Running. – 3rd Edition. – O'Reilly Media, 2023. – 416 p.
20. Hangos K.M., Szederkényi G. Mass action realizations of reaction kinetic system models on various time scales // J. of Physics: Conf. Series. – 2011. – Vol. 268. 5th Int. Workshop on Multi-Rate Processes and Hysteresis (MURPHYS 2010), Pécs, Hungary, May 31 – June 3, 2010. – P. 012009. – DOI: 10.1088/1742-6596/268/1/012009