Identification of a controlled object using frequency responses obtained from a dynamic neural network model of a control system
We present results of a study aimed at identification of a controlled objects channels based on postprocessing of measurements with development of a model of a multiple-input controlled object and subsequent active modelling experiment. The controlled object model is developed using approximation of...
Main Authors: | , |
---|---|
Format: | Article |
Language: | Russian |
Published: |
Institute of Computer Science
2017-10-01
|
Series: | Компьютерные исследования и моделирование |
Subjects: | |
Online Access: | http://crm.ics.org.ru/uploads/crmissues/crm_2017_5/2017_05_04.pdf |
id |
doaj-a6140003177349b6b67755d9bcaba524 |
---|---|
record_format |
Article |
spelling |
doaj-a6140003177349b6b67755d9bcaba5242020-11-24T21:30:42ZrusInstitute of Computer ScienceКомпьютерные исследования и моделирование2076-76332077-68532017-10-019572974010.20537/2076-7633-2017-9-5-729-7402619Identification of a controlled object using frequency responses obtained from a dynamic neural network model of a control systemAleksandr Georgievich ShumixinAnna Sergeevna AleksandrovaWe present results of a study aimed at identification of a controlled objects channels based on postprocessing of measurements with development of a model of a multiple-input controlled object and subsequent active modelling experiment. The controlled object model is developed using approximation of its behavior by a neural network model using trends obtained during a passive experiment in the mode of normal operation. Recurrent neural network containing feedback elements allows to simulate behavior of dynamic objects; input and feedback time delays allow to simulate behavior of inertial objects with pure delay. The model was taught using examples of the objects operation with a control system and is presented by a dynamic neural network and a model of a regulator with a known regulation function. The neural network model simulates the systems behavior and is used to conduct active computing experiments. Neural network model allows to obtain the controlled objects response to an exploratory stimulus, including a periodic one. The obtained complex frequency response is used to evaluate parameters of the objects transfer system using the least squares method. We present an example of identification of a channel of the simulated control system. The simulated object has two input ports and one output port and varying transport delays in transfer channels. One of the input ports serves as a controlling stimulus, the second is a controlled perturbation. The controlled output value changes as a result of control stimulus produced by the regulator operating according to the proportional-integral regulation law based on deviation of the controlled value from the task. The obtained parameters of the objects channels transfer functions are close to the parameters of the input simulated object. The obtained normalized error of the reaction for a single step-wise stimulus of the control system model developed based on identification of the simulated control system doesnt exceed 0.08. The considered objects pertain to the class of technological processes with continuous production. Such objects are characteristic of chemical, metallurgic, mine-mill, pulp and paper, and other industries.http://crm.ics.org.ru/uploads/crmissues/crm_2017_5/2017_05_04.pdfobject with control systemidentificationneural networkmodelingcomplex frequency responsetransfer function |
collection |
DOAJ |
language |
Russian |
format |
Article |
sources |
DOAJ |
author |
Aleksandr Georgievich Shumixin Anna Sergeevna Aleksandrova |
spellingShingle |
Aleksandr Georgievich Shumixin Anna Sergeevna Aleksandrova Identification of a controlled object using frequency responses obtained from a dynamic neural network model of a control system Компьютерные исследования и моделирование object with control system identification neural network modeling complex frequency response transfer function |
author_facet |
Aleksandr Georgievich Shumixin Anna Sergeevna Aleksandrova |
author_sort |
Aleksandr Georgievich Shumixin |
title |
Identification of a controlled object using frequency responses obtained from a dynamic neural network model of a control system |
title_short |
Identification of a controlled object using frequency responses obtained from a dynamic neural network model of a control system |
title_full |
Identification of a controlled object using frequency responses obtained from a dynamic neural network model of a control system |
title_fullStr |
Identification of a controlled object using frequency responses obtained from a dynamic neural network model of a control system |
title_full_unstemmed |
Identification of a controlled object using frequency responses obtained from a dynamic neural network model of a control system |
title_sort |
identification of a controlled object using frequency responses obtained from a dynamic neural network model of a control system |
publisher |
Institute of Computer Science |
series |
Компьютерные исследования и моделирование |
issn |
2076-7633 2077-6853 |
publishDate |
2017-10-01 |
description |
We present results of a study aimed at identification of a controlled objects channels based on postprocessing of measurements with development of a model of a multiple-input controlled object and subsequent active modelling experiment. The controlled object model is developed using approximation of its behavior by a neural network model using trends obtained during a passive experiment in the mode of normal operation. Recurrent neural network containing feedback elements allows to simulate behavior of dynamic objects; input and feedback time delays allow to simulate behavior of inertial objects with pure delay. The model was taught using examples of the objects operation with a control system and is presented by a dynamic neural network and a model of a regulator with a known regulation function. The neural network model simulates the systems behavior and is used to conduct active computing experiments. Neural network model allows to obtain the controlled objects response to an exploratory stimulus, including a periodic one. The obtained complex frequency response is used to evaluate parameters of the objects transfer system using the least squares method. We present an example of identification of a channel of the simulated control system. The simulated object has two input ports and one output port and varying transport delays in transfer channels. One of the input ports serves as a controlling stimulus, the second is a controlled perturbation. The controlled output value changes as a result of control stimulus produced by the regulator operating according to the proportional-integral regulation law based on deviation of the controlled value from the task. The obtained parameters of the objects channels transfer functions are close to the parameters of the input simulated object. The obtained normalized error of the reaction for a single step-wise stimulus of the control system model developed based on identification of the simulated control system doesnt exceed 0.08. The considered objects pertain to the class of technological processes with continuous production. Such objects are characteristic of chemical, metallurgic, mine-mill, pulp and paper, and other industries. |
topic |
object with control system identification neural network modeling complex frequency response transfer function |
url |
http://crm.ics.org.ru/uploads/crmissues/crm_2017_5/2017_05_04.pdf |
work_keys_str_mv |
AT aleksandrgeorgievichshumixin identificationofacontrolledobjectusingfrequencyresponsesobtainedfromadynamicneuralnetworkmodelofacontrolsystem AT annasergeevnaaleksandrova identificationofacontrolledobjectusingfrequencyresponsesobtainedfromadynamicneuralnetworkmodelofacontrolsystem |
_version_ |
1725962134029860864 |