Geodesic
PI-controller neural tuner appliance to reject disturbances acting on plants of different dynamics
Informacionnye tehnologii i vyčislitelnye sistemy, no. 4 (2017), pp. 83-94.

Voir la notice de l'article provenant de la source Math-Net.Ru

Nowadays, as far as nonlinear industrial plants control is concerned, in most cases the same set of PIcontroller parameters is used both to follow a setpoint schedule and reject disturbances. This set is usually found to solve the first of the mentioned tasks. Not only does that lead to disturbances rejection time increase, but also it increases energy consumption. A neural tuner is developed in this research in order to adjust PI-controller parameters should step-like limited disturbances acting on a plant output emerge. An additional neural network is added to its structure to solve this task. Tuner structure, rule base and algorithm are also improved. The rule base is used to define both moments when to train the neural network and the learning rate values. Experiments are conducted with the help of heating furnace and rolling mill DC drive mathematical models and a real muffle electroheating furnace. Having analyzed obtained results, a conclusion could be made that the tuner usage allows to achieve 20% time decrease to reject disturbances in comparison with a conventional PI-controller. Moreover, energy consumption is decreased by 13.8% for furnace, and amount of rejected products is decreased by 1.5% for the DC drive.
Keywords: disturbance, neural tuner, adaptive control, neural network. 
@article{ITVS_2017_4_a6,
     author = {Y. I. Eremenko and A. I. Glushchenko and A. V. Fomin and V. A. Petrov},
     title = {PI-controller neural tuner appliance to reject disturbances acting on plants of different dynamics},
     journal = {Informacionnye tehnologii i vy\v{c}islitelnye sistemy},
     pages = {83--94},
     publisher = {mathdoc},
     number = {4},
     year = {2017},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/ITVS_2017_4_a6/}
}
TY  - JOUR
AU  - Y. I. Eremenko
AU  - A. I. Glushchenko
AU  - A. V. Fomin
AU  - V. A. Petrov
TI  - PI-controller neural tuner appliance to reject disturbances acting on plants of different dynamics
JO  - Informacionnye tehnologii i vyčislitelnye sistemy
PY  - 2017
SP  - 83
EP  - 94
IS  - 4
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/ITVS_2017_4_a6/
LA  - ru
ID  - ITVS_2017_4_a6
ER  - 
%0 Journal Article
%A Y. I. Eremenko
%A A. I. Glushchenko
%A A. V. Fomin
%A V. A. Petrov
%T PI-controller neural tuner appliance to reject disturbances acting on plants of different dynamics
%J Informacionnye tehnologii i vyčislitelnye sistemy
%D 2017
%P 83-94
%N 4
%I mathdoc
%U http://geodesic.mathdoc.fr/item/ITVS_2017_4_a6/
%G ru
%F ITVS_2017_4_a6
Y. I. Eremenko; A. I. Glushchenko; A. V. Fomin; V. A. Petrov. PI-controller neural tuner appliance to reject disturbances acting on plants of different dynamics. Informacionnye tehnologii i vyčislitelnye sistemy, no. 4 (2017), pp. 83-94. http://geodesic.mathdoc.fr/item/ITVS_2017_4_a6/