Research and modeling of the process of sulfur production in the claus reactor using the method of artificial neural networks

Shangitova Z.H.Y.E. Orazbayev B.B. Kurmangaziyeva L.T. Ospanova T.T. Tuleuova R.U.
31 May 2021 Little Lion Scientific

Journal of Theoretical and Applied Information Technology
2021 #99 Issue 10 2333 - 2343 pp.

The Claus sulfur recovery process is the most important in natural gas desulfurization technology. Taking into account the large-tonnage facilities, it is urgent to solve the problem of effective management, which will allow obtaining a significant economic effect. When studying catalytic reactions and processes, mathematical modeling methods are most often used, which allow describing changes in the states of the system under study. An alternative approach to modeling chemical-technological processes can be the use of artificial neural networks, which make it possible to take into account the features of the processes under study as much as possible. The article is devoted to the study of the chemical-technological process of sulfur production in the Claus reactor by the method of artificial neural networks (ANN). This article describes the relevance of neural networks using in chemical-technological systems. Similar works on the research topic are presented. The analysis of the sulfur production unit as an object of management has been carried out. The main parameters influencing the process of sulfur production have been identified and investigated. The results of the study of sulfur production process using fuzzy logic are presented. Backpropagation algorithm is described. Based on the input data of a mathematical model with a multiple regression structure and real data from the Claus reactor, the Backpropagation Algorithm of multilayer neural networks in Python has been implemented. Based on the results of the program, the output values and errors dependences graphs have been built. As a result of the study, sufficient convergence of the results of modeling using mathematical models is shown on ANN and real production data.

Artificial Neural Networks , Backpropagation Algorithm , Multi-layer Neural Networks , Python , Sulfur

Text of the article Перейти на текст статьи

Faculty of Information Technology, Department of Information Systems, L.N. Gumilyov Eurasian National University, Nur-Sultan, Kazakhstan
Faculty of Information Technology, Department of System Analysis and Management, L.N. Gumilyov Eurasian National University, Nur-Sultan, Kazakhstan
Faculty of Physics, Mathematics and Information Technology, Department of Software Engineering, Kh. Dosmukhamedov Atyrau University, Atyrau, Kazakhstan
Faculty of Physics, Mathematics and Information Technology, Department of Mathematics and Methods of Teaching Mathematics, Kh. Dosmukhamedov Atyrau University, Atyrau, Kazakhstan

Faculty of Information Technology
Faculty of Information Technology
Faculty of Physics
Faculty of Physics

10 лет помогаем публиковать статьи Международный издатель

Книга Публикация научной статьи Волощук 2026 Book Publication of a scientific article 2026