Adaptive neural network cascade control system with entropy-based design

Jianhua Zhang, Shuqing Zhou, Mifeng Ren, Hong Yue

Research output: Contribution to journalArticle

10 Citations (Scopus)
138 Downloads (Pure)

Abstract

A neural network (NN) based cascade control system is developed, in which the primary PID controller is constructed by NN. A new entropy-based measure, named the centred error entropy (CEE) index, which is a weighted combination of the error cross correntropy (ECC) criterion and the error entropy criterion (EEC), is proposed to tune the NN-PID controller. The purpose of introducing CEE in controller design is to ensure that the uncertainty in the tracking error is minimised and also the peak value of the error probability density function (PDF) being controlled towards zero. The NN-controller design based on this new performance function is developed and the convergent conditions are. During the control process, the CEE index is estimated by a Gaussian kernel function. Adaptive rules are developed to update the kernel size in order to achieve more accurate estimation of the CEE index. This NN cascade control approach is applied to superheated steam temperature control of a simulated power plant system, from which the effectiveness and strength of the proposed strategy are discussed by comparison with NN-PID controllers tuned with EEC and ECC criterions.
Original languageEnglish
Pages (from-to)1151-1160
Number of pages10
JournalIET Control Theory and Applications
Volume10
Issue number10
DOIs
Publication statusPublished - 27 Jun 2016

Fingerprint

Cascade control systems
Cascade Control
Entropy
Control System
Neural Networks
Neural networks
PID Controller
Controllers
Controller Design
Design
Gaussian Kernel
Temperature Control
Gaussian Function
Power Plant
Error Probability
Network Design
Kernel Function
Process Control
Temperature control
Probability density function

Keywords

  • neural network
  • error cross correntropy
  • Gaussian kernel function
  • cascade control

Cite this

Zhang, Jianhua ; Zhou, Shuqing ; Ren, Mifeng ; Yue, Hong. / Adaptive neural network cascade control system with entropy-based design. In: IET Control Theory and Applications . 2016 ; Vol. 10, No. 10. pp. 1151-1160.
@article{0da1edf27620457783611b87171428a9,
title = "Adaptive neural network cascade control system with entropy-based design",
abstract = "A neural network (NN) based cascade control system is developed, in which the primary PID controller is constructed by NN. A new entropy-based measure, named the centred error entropy (CEE) index, which is a weighted combination of the error cross correntropy (ECC) criterion and the error entropy criterion (EEC), is proposed to tune the NN-PID controller. The purpose of introducing CEE in controller design is to ensure that the uncertainty in the tracking error is minimised and also the peak value of the error probability density function (PDF) being controlled towards zero. The NN-controller design based on this new performance function is developed and the convergent conditions are. During the control process, the CEE index is estimated by a Gaussian kernel function. Adaptive rules are developed to update the kernel size in order to achieve more accurate estimation of the CEE index. This NN cascade control approach is applied to superheated steam temperature control of a simulated power plant system, from which the effectiveness and strength of the proposed strategy are discussed by comparison with NN-PID controllers tuned with EEC and ECC criterions.",
keywords = "neural network, error cross correntropy, Gaussian kernel function, cascade control",
author = "Jianhua Zhang and Shuqing Zhou and Mifeng Ren and Hong Yue",
note = "This paper is a postprint of a paper submitted to and accepted for publication in IET Control Theory and Applications and is subject to Institution of Engineering and Technology Copyright. The copy of record is available at IET Digital Library",
year = "2016",
month = "6",
day = "27",
doi = "10.1049/iet-cta.2015.0992",
language = "English",
volume = "10",
pages = "1151--1160",
journal = "IET Control Theory and Applications",
issn = "1751-8644",
number = "10",

}

Adaptive neural network cascade control system with entropy-based design. / Zhang, Jianhua; Zhou, Shuqing; Ren, Mifeng; Yue, Hong.

In: IET Control Theory and Applications , Vol. 10, No. 10, 27.06.2016, p. 1151-1160.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Adaptive neural network cascade control system with entropy-based design

AU - Zhang, Jianhua

AU - Zhou, Shuqing

AU - Ren, Mifeng

AU - Yue, Hong

N1 - This paper is a postprint of a paper submitted to and accepted for publication in IET Control Theory and Applications and is subject to Institution of Engineering and Technology Copyright. The copy of record is available at IET Digital Library

PY - 2016/6/27

Y1 - 2016/6/27

N2 - A neural network (NN) based cascade control system is developed, in which the primary PID controller is constructed by NN. A new entropy-based measure, named the centred error entropy (CEE) index, which is a weighted combination of the error cross correntropy (ECC) criterion and the error entropy criterion (EEC), is proposed to tune the NN-PID controller. The purpose of introducing CEE in controller design is to ensure that the uncertainty in the tracking error is minimised and also the peak value of the error probability density function (PDF) being controlled towards zero. The NN-controller design based on this new performance function is developed and the convergent conditions are. During the control process, the CEE index is estimated by a Gaussian kernel function. Adaptive rules are developed to update the kernel size in order to achieve more accurate estimation of the CEE index. This NN cascade control approach is applied to superheated steam temperature control of a simulated power plant system, from which the effectiveness and strength of the proposed strategy are discussed by comparison with NN-PID controllers tuned with EEC and ECC criterions.

AB - A neural network (NN) based cascade control system is developed, in which the primary PID controller is constructed by NN. A new entropy-based measure, named the centred error entropy (CEE) index, which is a weighted combination of the error cross correntropy (ECC) criterion and the error entropy criterion (EEC), is proposed to tune the NN-PID controller. The purpose of introducing CEE in controller design is to ensure that the uncertainty in the tracking error is minimised and also the peak value of the error probability density function (PDF) being controlled towards zero. The NN-controller design based on this new performance function is developed and the convergent conditions are. During the control process, the CEE index is estimated by a Gaussian kernel function. Adaptive rules are developed to update the kernel size in order to achieve more accurate estimation of the CEE index. This NN cascade control approach is applied to superheated steam temperature control of a simulated power plant system, from which the effectiveness and strength of the proposed strategy are discussed by comparison with NN-PID controllers tuned with EEC and ECC criterions.

KW - neural network

KW - error cross correntropy

KW - Gaussian kernel function

KW - cascade control

UR - http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=4079545

U2 - 10.1049/iet-cta.2015.0992

DO - 10.1049/iet-cta.2015.0992

M3 - Article

VL - 10

SP - 1151

EP - 1160

JO - IET Control Theory and Applications

JF - IET Control Theory and Applications

SN - 1751-8644

IS - 10

ER -