An improved adaptive switching control based on quasi-ARX neural network for nonlinear systems

Imam Sutrisno, Chi Che, Takayuki Furuzuki

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

In this paper, an improved switching mechanism based on quasi-linear auto regressive exogenous (quasi-ARX) neural network (QARXNN) is presented for the adaptive control of nonlinear systems. The proposed switching control is composed of a QARXNN-based prediction model and an improved switching mechanism using two new adaptive control laws, first is moving average filter law and second is new switching law. Since the control result of nonlinear predictor is better than the linear predictor in most of the time, the adaptive control with a simple switching mechanism has many useless switching during the processing. Hence, the improved smooth switching mechanism is proposed to replace the original switching mechanism; it can improve the performance by reducing the useless switching while guaranteeing stability of the system control. The simulations show that the efficiency of the proposed control method is satisfied in stability, improve control accuracy and robustness.

Original languageEnglish
Pages (from-to)347-353
Number of pages7
JournalArtificial Life and Robotics
Volume19
Issue number4
DOIs
Publication statusPublished - 2014 Dec 10

Fingerprint

Nonlinear systems
Neural networks
Control systems
Processing

Keywords

  • Adaptive switching control
  • An improved switching mechanism
  • Quasi-ARX neural network prediction model

ASJC Scopus subject areas

  • Artificial Intelligence
  • Biochemistry, Genetics and Molecular Biology(all)

Cite this

An improved adaptive switching control based on quasi-ARX neural network for nonlinear systems. / Sutrisno, Imam; Che, Chi; Furuzuki, Takayuki.

In: Artificial Life and Robotics, Vol. 19, No. 4, 10.12.2014, p. 347-353.

Research output: Contribution to journalArticle

@article{9cf88902ac1742d5aa06269130186b17,
title = "An improved adaptive switching control based on quasi-ARX neural network for nonlinear systems",
abstract = "In this paper, an improved switching mechanism based on quasi-linear auto regressive exogenous (quasi-ARX) neural network (QARXNN) is presented for the adaptive control of nonlinear systems. The proposed switching control is composed of a QARXNN-based prediction model and an improved switching mechanism using two new adaptive control laws, first is moving average filter law and second is new switching law. Since the control result of nonlinear predictor is better than the linear predictor in most of the time, the adaptive control with a simple switching mechanism has many useless switching during the processing. Hence, the improved smooth switching mechanism is proposed to replace the original switching mechanism; it can improve the performance by reducing the useless switching while guaranteeing stability of the system control. The simulations show that the efficiency of the proposed control method is satisfied in stability, improve control accuracy and robustness.",
keywords = "Adaptive switching control, An improved switching mechanism, Quasi-ARX neural network prediction model",
author = "Imam Sutrisno and Chi Che and Takayuki Furuzuki",
year = "2014",
month = "12",
day = "10",
doi = "10.1007/s10015-014-0173-x",
language = "English",
volume = "19",
pages = "347--353",
journal = "Artificial Life and Robotics",
issn = "1433-5298",
publisher = "Springer Japan",
number = "4",

}

TY - JOUR

T1 - An improved adaptive switching control based on quasi-ARX neural network for nonlinear systems

AU - Sutrisno, Imam

AU - Che, Chi

AU - Furuzuki, Takayuki

PY - 2014/12/10

Y1 - 2014/12/10

N2 - In this paper, an improved switching mechanism based on quasi-linear auto regressive exogenous (quasi-ARX) neural network (QARXNN) is presented for the adaptive control of nonlinear systems. The proposed switching control is composed of a QARXNN-based prediction model and an improved switching mechanism using two new adaptive control laws, first is moving average filter law and second is new switching law. Since the control result of nonlinear predictor is better than the linear predictor in most of the time, the adaptive control with a simple switching mechanism has many useless switching during the processing. Hence, the improved smooth switching mechanism is proposed to replace the original switching mechanism; it can improve the performance by reducing the useless switching while guaranteeing stability of the system control. The simulations show that the efficiency of the proposed control method is satisfied in stability, improve control accuracy and robustness.

AB - In this paper, an improved switching mechanism based on quasi-linear auto regressive exogenous (quasi-ARX) neural network (QARXNN) is presented for the adaptive control of nonlinear systems. The proposed switching control is composed of a QARXNN-based prediction model and an improved switching mechanism using two new adaptive control laws, first is moving average filter law and second is new switching law. Since the control result of nonlinear predictor is better than the linear predictor in most of the time, the adaptive control with a simple switching mechanism has many useless switching during the processing. Hence, the improved smooth switching mechanism is proposed to replace the original switching mechanism; it can improve the performance by reducing the useless switching while guaranteeing stability of the system control. The simulations show that the efficiency of the proposed control method is satisfied in stability, improve control accuracy and robustness.

KW - Adaptive switching control

KW - An improved switching mechanism

KW - Quasi-ARX neural network prediction model

UR - http://www.scopus.com/inward/record.url?scp=84919390926&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84919390926&partnerID=8YFLogxK

U2 - 10.1007/s10015-014-0173-x

DO - 10.1007/s10015-014-0173-x

M3 - Article

AN - SCOPUS:84919390926

VL - 19

SP - 347

EP - 353

JO - Artificial Life and Robotics

JF - Artificial Life and Robotics

SN - 1433-5298

IS - 4

ER -