An adaptive PID controller with an online auto-tuning by a pretrained neural network

P. A. Chertovskikh; A. V. Seredkin; O. A. Gobyzov; A. S. Styuf; M. G. Pashkevich; M. P. Tokarev

doi:10.1088/1742-6596/1359/1/012090

An adaptive PID controller with an online auto-tuning by a pretrained neural network

P. A. Chertovskikh, A. V. Seredkin, O. A. Gobyzov, A. S. Styuf, M. G. Pashkevich, M. P. Tokarev

Research output: Contribution to journal › Conference article › peer-review

1 Citation (Scopus)

Abstract

This paper describes an intelligent adaptive PID controller design procedure. The controller consists of a discrete time PID and an auto-tuning neural network unit. First system identification with a nonlinear autoregressive model (NARX) was performed. This model was then used to train the neural PID tuner. A special MATLAB toolbox "SmatPID Toolbox" was developed to automate the process of controller synthesis. The resulting controller was tested in a laboratory coal-gas furnace control system to track specified air flow rates.

Original language	English
Article number	012090
Number of pages	6
Journal	Journal of Physics: Conference Series
Volume	1359
Issue number	1
DOIs	https://doi.org/10.1088/1742-6596/1359/1/012090
Publication status	Published - 21 Nov 2019
Event	4th All-Russian Scientific Conference Thermophysics and Physical Hydrodynamics with the School for Young Scientists, TPH 2019 - Yalta, Crimea, Ukraine Duration: 15 Sep 2019 → 22 Sep 2019

Access to Document

10.1088/1742-6596/1359/1/012090

Link to publication in Scopus

Fingerprint Dive into the research topics of 'An adaptive PID controller with an online auto-tuning by a pretrained neural network'. Together they form a unique fingerprint.

Cite this

@article{f292aad2c6b44043b504afc6461989ac,

title = "An adaptive PID controller with an online auto-tuning by a pretrained neural network",

abstract = "This paper describes an intelligent adaptive PID controller design procedure. The controller consists of a discrete time PID and an auto-tuning neural network unit. First system identification with a nonlinear autoregressive model (NARX) was performed. This model was then used to train the neural PID tuner. A special MATLAB toolbox {"}SmatPID Toolbox{"} was developed to automate the process of controller synthesis. The resulting controller was tested in a laboratory coal-gas furnace control system to track specified air flow rates.",

author = "Chertovskikh, {P. A.} and Seredkin, {A. V.} and Gobyzov, {O. A.} and Styuf, {A. S.} and Pashkevich, {M. G.} and Tokarev, {M. P.}",

year = "2019",

month = nov,

day = "21",

doi = "10.1088/1742-6596/1359/1/012090",

language = "English",

volume = "1359",

journal = "Journal of Physics: Conference Series",

issn = "1742-6588",

publisher = "IOP Publishing Ltd.",

number = "1",

note = "4th All-Russian Scientific Conference Thermophysics and Physical Hydrodynamics with the School for Young Scientists, TPH 2019 ; Conference date: 15-09-2019 Through 22-09-2019",

}

TY - JOUR

T1 - An adaptive PID controller with an online auto-tuning by a pretrained neural network

AU - Chertovskikh, P. A.

AU - Seredkin, A. V.

AU - Gobyzov, O. A.

AU - Styuf, A. S.

AU - Pashkevich, M. G.

AU - Tokarev, M. P.

PY - 2019/11/21

Y1 - 2019/11/21

N2 - This paper describes an intelligent adaptive PID controller design procedure. The controller consists of a discrete time PID and an auto-tuning neural network unit. First system identification with a nonlinear autoregressive model (NARX) was performed. This model was then used to train the neural PID tuner. A special MATLAB toolbox "SmatPID Toolbox" was developed to automate the process of controller synthesis. The resulting controller was tested in a laboratory coal-gas furnace control system to track specified air flow rates.

AB - This paper describes an intelligent adaptive PID controller design procedure. The controller consists of a discrete time PID and an auto-tuning neural network unit. First system identification with a nonlinear autoregressive model (NARX) was performed. This model was then used to train the neural PID tuner. A special MATLAB toolbox "SmatPID Toolbox" was developed to automate the process of controller synthesis. The resulting controller was tested in a laboratory coal-gas furnace control system to track specified air flow rates.

UR - http://www.scopus.com/inward/record.url?scp=85076473845&partnerID=8YFLogxK

U2 - 10.1088/1742-6596/1359/1/012090

DO - 10.1088/1742-6596/1359/1/012090

M3 - Conference article

AN - SCOPUS:85076473845

VL - 1359

JO - Journal of Physics: Conference Series

JF - Journal of Physics: Conference Series

SN - 1742-6588

IS - 1

M1 - 012090

T2 - 4th All-Russian Scientific Conference Thermophysics and Physical Hydrodynamics with the School for Young Scientists, TPH 2019

Y2 - 15 September 2019 through 22 September 2019

ER -