Synthesis of a neural network controller for an automated system controlling a cascade of centrifugal extractors
DOI: 10.21293/1818-0442-2024-27-4-97-102
DOI: 10.21293/1818-0442-2024-27-4-97-102
Abstract: The paper considers the synthesis of an automated control system for a cascade of centrifugal extractors with a neural network controller trained by the method of error back propagation through a direct neuroemmulator with a reference model. The identification of the control object was carried out, the given standard deviation is 1.63%. The quality indicators of the con-trol system with a thermostat are superior to the control system with a PID controller. The developed automated control system for the extraction unit based on a neural network controller has been tested for rudeness.
Keywords: automated control system, extraction, artificial neural network, neural network controller
Funding: The study was supported by the National Research Tomsk Polytechnic University program (PISH-NIR-2024-005).
For citation:
Emelyanov A. M., Kozlova Yu. M., Nadezhdin I. S. Synthesis of a neural network controller for an automated system controlling a cascade of centrifugal extractors. Doklady Tomskogo gosudarstvennogo universiteta sistem upravleniya i radioelektroniki, 2024, vol. 27, no. 4, pp. 97–102. DOI: 10.21293/1818-0442-2024-27-4-97-102
Authors and copyright holders:
Executive Secretary of the Editor’s Office
Editor’s Office: 40 Lenina Prospect, Tomsk, 634050, Russia
Phone / Fax: + 7 (3822) 701-582
Viktor N. Maslennikov
Executive Secretary of the Editor’s Office
Editor’s Office: 40 Lenina Prospect, Tomsk, 634050, Russia
Phone / Fax: + 7 (3822) 51-21-21 / 51-43-02