System identification of smart structures using neural networks

Shih-Ming Yang, G. S. Lee

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

A composite smart structure embedded with piezoelectric sensor/actuator is fabricated and its piezoelectric effectiveness is validated by static test and modal testing. Instead of identifying the structural parameters of the smart structure, system identification is conducted by estimating the connective weights of a backpropagation neural network with an adaptive learning rate. Experimental verification shows that the [6-7-2] neural network, a neural network with 6 input neurons, 7 hidden layer neurons, and 2 output neurons, is capable of representing the system dynamics both in time domain and in frequency domain. In addition, it is fault tolerant. All simulations are validated by experiments. Integration of smart structure and neural network not only avoids the complexity introduced by other traditional analytical or computational methods but also lays the corner stone for effective neural controller design.

Original languageEnglish
Pages (from-to)883-890
Number of pages8
JournalJournal of Intelligent Material Systems and Structures
Volume8
Issue number10
DOIs
Publication statusPublished - 1997 Jan 1

Fingerprint

Intelligent structures
Identification (control systems)
Neurons
Neural networks
Computational methods
Backpropagation
Dynamical systems
Actuators
Controllers
Sensors
Composite materials
Testing
Experiments

All Science Journal Classification (ASJC) codes

  • Materials Science(all)
  • Mechanical Engineering

Cite this

@article{6aeb8ca20ca746c98c9d22aa6fbe8a7c,
title = "System identification of smart structures using neural networks",
abstract = "A composite smart structure embedded with piezoelectric sensor/actuator is fabricated and its piezoelectric effectiveness is validated by static test and modal testing. Instead of identifying the structural parameters of the smart structure, system identification is conducted by estimating the connective weights of a backpropagation neural network with an adaptive learning rate. Experimental verification shows that the [6-7-2] neural network, a neural network with 6 input neurons, 7 hidden layer neurons, and 2 output neurons, is capable of representing the system dynamics both in time domain and in frequency domain. In addition, it is fault tolerant. All simulations are validated by experiments. Integration of smart structure and neural network not only avoids the complexity introduced by other traditional analytical or computational methods but also lays the corner stone for effective neural controller design.",
author = "Shih-Ming Yang and Lee, {G. S.}",
year = "1997",
month = "1",
day = "1",
doi = "10.1177/1045389X9700801008",
language = "English",
volume = "8",
pages = "883--890",
journal = "Journal of Intelligent Material Systems and Structures",
issn = "1045-389X",
publisher = "SAGE Publications Ltd",
number = "10",

}

System identification of smart structures using neural networks. / Yang, Shih-Ming; Lee, G. S.

In: Journal of Intelligent Material Systems and Structures, Vol. 8, No. 10, 01.01.1997, p. 883-890.

Research output: Contribution to journalArticle

TY - JOUR

T1 - System identification of smart structures using neural networks

AU - Yang, Shih-Ming

AU - Lee, G. S.

PY - 1997/1/1

Y1 - 1997/1/1

N2 - A composite smart structure embedded with piezoelectric sensor/actuator is fabricated and its piezoelectric effectiveness is validated by static test and modal testing. Instead of identifying the structural parameters of the smart structure, system identification is conducted by estimating the connective weights of a backpropagation neural network with an adaptive learning rate. Experimental verification shows that the [6-7-2] neural network, a neural network with 6 input neurons, 7 hidden layer neurons, and 2 output neurons, is capable of representing the system dynamics both in time domain and in frequency domain. In addition, it is fault tolerant. All simulations are validated by experiments. Integration of smart structure and neural network not only avoids the complexity introduced by other traditional analytical or computational methods but also lays the corner stone for effective neural controller design.

AB - A composite smart structure embedded with piezoelectric sensor/actuator is fabricated and its piezoelectric effectiveness is validated by static test and modal testing. Instead of identifying the structural parameters of the smart structure, system identification is conducted by estimating the connective weights of a backpropagation neural network with an adaptive learning rate. Experimental verification shows that the [6-7-2] neural network, a neural network with 6 input neurons, 7 hidden layer neurons, and 2 output neurons, is capable of representing the system dynamics both in time domain and in frequency domain. In addition, it is fault tolerant. All simulations are validated by experiments. Integration of smart structure and neural network not only avoids the complexity introduced by other traditional analytical or computational methods but also lays the corner stone for effective neural controller design.

UR - http://www.scopus.com/inward/record.url?scp=0031246733&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031246733&partnerID=8YFLogxK

U2 - 10.1177/1045389X9700801008

DO - 10.1177/1045389X9700801008

M3 - Article

VL - 8

SP - 883

EP - 890

JO - Journal of Intelligent Material Systems and Structures

JF - Journal of Intelligent Material Systems and Structures

SN - 1045-389X

IS - 10

ER -