Indirect adaptive control of nonlinear dynamic systems using self recurrent wavelet neural networks via adaptive learning rates

Sung Jin Yoo, Jin Bae Park, Yoon Ho Choi

Research output: Contribution to journalArticle

66 Citations (Scopus)

Abstract

This paper proposes an indirect adaptive control method using self recurrent wavelet neural networks (SRWNNs) for dynamic systems. The architecture of the SRWNN is a modified model of the wavelet neural network (WNN). However, unlike the WNN, since a mother wavelet layer of the SRWNN is composed of self-feedback neurons, the SRWNN can store the past information of wavelets. In the proposed control architecture, two SRWNNs are used as both an identifier and a controller. The SRWNN identifier approximates dynamic systems and provides the SRWNN controller with information about the system sensitivity. The gradient-descent method using adaptive learning rates (ALRs) is applied to train all weights of the SRWNN. The ALRs are derived from discrete Lyapunov stability theorem, which are applied to guarantee the convergence of the proposed control system. Finally, we perform some simulations to verify the effectiveness of the proposed control scheme.

Original languageEnglish
Pages (from-to)3074-3098
Number of pages25
JournalInformation sciences
Volume177
Issue number15
DOIs
Publication statusPublished - 2007 Aug 1

Fingerprint

Wavelet Neural Network
Adaptive Learning
Learning Rate
Nonlinear Dynamic System
Recurrent Neural Networks
Adaptive Control
Dynamical systems
Neural networks
Dynamic Systems
Wavelets
Adaptive control
Nonlinear dynamics
Adaptive learning
Dynamic systems
Controller
Gradient Descent Method
Controllers
Lyapunov Theorem
Lyapunov Stability
Stability Theorem

All Science Journal Classification (ASJC) codes

  • Software
  • Control and Systems Engineering
  • Theoretical Computer Science
  • Computer Science Applications
  • Information Systems and Management
  • Artificial Intelligence

Cite this

@article{b9360c7c26fe450a9cc5f52b5e8c3b52,
title = "Indirect adaptive control of nonlinear dynamic systems using self recurrent wavelet neural networks via adaptive learning rates",
abstract = "This paper proposes an indirect adaptive control method using self recurrent wavelet neural networks (SRWNNs) for dynamic systems. The architecture of the SRWNN is a modified model of the wavelet neural network (WNN). However, unlike the WNN, since a mother wavelet layer of the SRWNN is composed of self-feedback neurons, the SRWNN can store the past information of wavelets. In the proposed control architecture, two SRWNNs are used as both an identifier and a controller. The SRWNN identifier approximates dynamic systems and provides the SRWNN controller with information about the system sensitivity. The gradient-descent method using adaptive learning rates (ALRs) is applied to train all weights of the SRWNN. The ALRs are derived from discrete Lyapunov stability theorem, which are applied to guarantee the convergence of the proposed control system. Finally, we perform some simulations to verify the effectiveness of the proposed control scheme.",
author = "Yoo, {Sung Jin} and Park, {Jin Bae} and Choi, {Yoon Ho}",
year = "2007",
month = "8",
day = "1",
doi = "10.1016/j.ins.2007.02.009",
language = "English",
volume = "177",
pages = "3074--3098",
journal = "Information Sciences",
issn = "0020-0255",
publisher = "Elsevier Inc.",
number = "15",

}

Indirect adaptive control of nonlinear dynamic systems using self recurrent wavelet neural networks via adaptive learning rates. / Yoo, Sung Jin; Park, Jin Bae; Choi, Yoon Ho.

In: Information sciences, Vol. 177, No. 15, 01.08.2007, p. 3074-3098.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Indirect adaptive control of nonlinear dynamic systems using self recurrent wavelet neural networks via adaptive learning rates

AU - Yoo, Sung Jin

AU - Park, Jin Bae

AU - Choi, Yoon Ho

PY - 2007/8/1

Y1 - 2007/8/1

N2 - This paper proposes an indirect adaptive control method using self recurrent wavelet neural networks (SRWNNs) for dynamic systems. The architecture of the SRWNN is a modified model of the wavelet neural network (WNN). However, unlike the WNN, since a mother wavelet layer of the SRWNN is composed of self-feedback neurons, the SRWNN can store the past information of wavelets. In the proposed control architecture, two SRWNNs are used as both an identifier and a controller. The SRWNN identifier approximates dynamic systems and provides the SRWNN controller with information about the system sensitivity. The gradient-descent method using adaptive learning rates (ALRs) is applied to train all weights of the SRWNN. The ALRs are derived from discrete Lyapunov stability theorem, which are applied to guarantee the convergence of the proposed control system. Finally, we perform some simulations to verify the effectiveness of the proposed control scheme.

AB - This paper proposes an indirect adaptive control method using self recurrent wavelet neural networks (SRWNNs) for dynamic systems. The architecture of the SRWNN is a modified model of the wavelet neural network (WNN). However, unlike the WNN, since a mother wavelet layer of the SRWNN is composed of self-feedback neurons, the SRWNN can store the past information of wavelets. In the proposed control architecture, two SRWNNs are used as both an identifier and a controller. The SRWNN identifier approximates dynamic systems and provides the SRWNN controller with information about the system sensitivity. The gradient-descent method using adaptive learning rates (ALRs) is applied to train all weights of the SRWNN. The ALRs are derived from discrete Lyapunov stability theorem, which are applied to guarantee the convergence of the proposed control system. Finally, we perform some simulations to verify the effectiveness of the proposed control scheme.

UR - http://www.scopus.com/inward/record.url?scp=34248136083&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34248136083&partnerID=8YFLogxK

U2 - 10.1016/j.ins.2007.02.009

DO - 10.1016/j.ins.2007.02.009

M3 - Article

AN - SCOPUS:34248136083

VL - 177

SP - 3074

EP - 3098

JO - Information Sciences

JF - Information Sciences

SN - 0020-0255

IS - 15

ER -