Nowadays, mathematical modelling of technological processes has become an integral part of solving scientific and technical problems aimed at building automated control systems of technological processes.

We will consider the possibility of modeling absorption column properties and process control through it using radial basis functional properties and directly coupled neural networks. The input and output results for neural network training are derived from the absorption column model. The results obtained using neural network models are mainly compared with the simulation results. The result shows that relatively simple neural network models can be used to simulate the steady state of the absorption column. The type of neural network used in the simulation allows the application of modern control methods.

1.
I. G.
Svenger
,
I. R.
Nizamov
,
Bulletin of Tashkent Technological University
20
(
8
), (
2017
)
2.
A. N.
Kabirova
,
Methods and software complexes of neural network development, regulator models for controlling dynamic objects
, (
Kazan
,
2017
)
3.
V.A.
Teresov
,
I.Yu.
Tyukin
,
Synthesis of adaptive neural regulators of nonlinear dynamic objects,
(
Institute of Physical and Chemical Research (RIKEN
),
Japan
,
2017
)
4.
D.P.
Mukhitdinov
,
Y.B.
Kadyrov
,
O.
Sattarov
.
Composite Materials
.
Scientific-Technical and Production Journal
2
,
132
135
(
2019
)
5.
E.V.
Leonidovich
,
Development and research of neural network algorithms for control of stationary and non-stationary objects
, (
Moscow
,
2012
)
6.
G. F.
Filaretov
,
V. L.
Eliseev
, in
55th International Scientific Colloquium
(
Ilmenau University of Technology
,
2010
)
7.
N. R.
Yusupbekov
,
D. P.
Mukhitdinov
,
O. Y.
Sattarov
,
S. B.
Boibutaev
, in
International Journal of Advanced Research in Science, Engineering and Technology
6
(
6
), (
2019
)
8.
N. A.
Saprykina
, in
Nauka, obrazovaniye i eksperimental'noye proyektirovaniye
, (
Trudy MARKHI
,
2016
), pp.
277
283
9.
D. P.
Mukhitdinov
,
Y. B.
Kadyrov
,
O. Y.
Sattarov
,
S. B.
Boibutaev
, in
Scientific and Technical and Production Journal "Mining Bulletin of Uzbekistan"
4
, (
2014
)
10.
A.G.
Goryunov
,
Y. A.
Chursin
,
S.
Miksalevich
,
D.
Rogozny
.
Dynamical model of multicomponent nonequilibrium extraction process in a column extractor
, (
Izvestiya visshix uchebnix zavedeniy, Physics
,
2010
), pp.
210
214
11.
V.P.
Rykov
,
TSU Bulletin
,
19
(
2
), pp.
583
586
, (
2014
)
12.
M.
Beal
,
M.
Hagan
,
H.
Demuth
,
Neural Network ToolboxTM user's guide
, (
The Math Works, Inc
,
2015
), p.
406
13.
O. U.
Sattarov
, in
Scientific, Technical and Production Journal "Modern materials, equipment and technology"
8
, (
2017
)
14.
A.G.
Khumixin
and
A.S.
Boyarshinova
,
Application of neural networks of dynamic models in the setting of parametric identification of technological objects in the structure of control systems
, (
Vestnik PNIPU, Perm
.
2015
), pp.
21
36
15.
N.
Yusupbekov
,
D.
Mukhitdinov
,
Y.
Kadirov
and
O.
Sattarov
, in
International Journal of Emerging Trends in Engineering Researc
,
8
(
9
),
5273
5278
(
2020
)
16.
O.A.
Jumaev
,
R.R.
Sayfulin
,
A. R.
Samadov
,
E.I.
Arziyev
and
E. O.
Jumaboyev
, in
IOP Conference Series: Materials Science and Engineering
862
, (
2020
)
17.
N.R.
Yusupbekov
,
S. M.
Gulyamov
,
N. B.
Usmanova
, in
World Conference Intelligent System for Industrial Automation
, (
Springer, Cham
.,
2020
), pp.
246
253
18.
N.
Yusupbekov
,
H.
Igamberdiev
,
U.
Mamirov
, in
CEUR Workshop Proceedings
2782
,
228
234
(
2020
)
This content is only available via PDF.
You do not currently have access to this content.