Deep learning models for predictive control of technological processes
Received: 25 Oct 2026 Revised: 27 Oct 2026 Accepted: 30 Oct 2026
Published: 2026, vol. 30, issue 4, pp. 514–517
Abstract
Traditional control systems for complex technological processes require extensive expert tuning and often fail to adapt to the drift in real equipment characteristics. This study aims to develop purely data-driven predictive control algorithms, combining the end‑to‑end differentiability of the surrogate model with classical mathematical programming methods. The performance and transferability of the developed methods have been validated using data from the industrial Tennessee Eastman process simulator and a real oil refinery complex. The results demonstrate effective process control and reliable maintenance of technological parameters within specified operational constraints.
Keywords: structured state-space models, reinforcement learning, digital twin.
BibTeX
@article{IS-Lazuhin-Petrovskiy-Mashechkin2026,
author = {Lazuhin, Ivan Sergeevich and Petrovskiy, Mikhail Igorevich and Mashechkin, Igor Valeryevich},
title = {{Deep learning models for predictive control of technological processes}},
journal = {Intelligent Systems. Theory and Applications},
year = {2026},
volume = {30},
number = {4},
pages = {514--517},
}
AMSBIB
\Bibitem{IS-Lazuhin-Petrovskiy-Mashechkin2026}
\by I.\,S.~Lazuhin, M.\,I.~Petrovskiy, I.\,V.~Mashechkin
\paper Deep learning models for predictive control of technological processes
\jour Intelligent Systems. Theory and Applications
\yr 2026
\vol 30
\issue 4
\pages 514--517
\lang In Russian
RU