Multi-mode control of structures by using neural networks with marquardt algorithms

C. A. Jeng, Shih-Ming Yang, J. N. Lin

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

This paper presents an integrated approach of identification, estimation and vibration control of smart structures by using neural networks with Marquardt adaptation algorithm. An identification neural network is first constructed to model the system dynamics of a composite laminate structure embedded with piezoelectric sensor and actuator. Based on the identification network, a neural controller is then developed to meet the vibration suppression performance specified by a reference model. In addition, an estimation neural network is also developed that enables the measurement of a single piezoelectric sensor to represent the state variables of displacement and velocity of the structure. The neural controller can then minimize the structure vibration by using a pair of piezoelectric sensors and actuators. Experimental verification shows that the vibration amplitude of the smart structure under two-mode harmonic excitation and random excitation can be reduced by 80% and 60%, respectively.

Original languageEnglish
Pages (from-to)1035-1043
Number of pages9
JournalJournal of Intelligent Material Systems and Structures
Volume8
Issue number12
DOIs
Publication statusPublished - 1997 Jan 1

Fingerprint

Intelligent structures
Neural networks
Identification (control systems)
Sensors
Actuators
Controllers
Vibration control
Laminates
Dynamical systems
Composite materials

All Science Journal Classification (ASJC) codes

  • Materials Science(all)
  • Mechanical Engineering

Cite this

@article{721c53fae699469aab79241488a285e6,
title = "Multi-mode control of structures by using neural networks with marquardt algorithms",
abstract = "This paper presents an integrated approach of identification, estimation and vibration control of smart structures by using neural networks with Marquardt adaptation algorithm. An identification neural network is first constructed to model the system dynamics of a composite laminate structure embedded with piezoelectric sensor and actuator. Based on the identification network, a neural controller is then developed to meet the vibration suppression performance specified by a reference model. In addition, an estimation neural network is also developed that enables the measurement of a single piezoelectric sensor to represent the state variables of displacement and velocity of the structure. The neural controller can then minimize the structure vibration by using a pair of piezoelectric sensors and actuators. Experimental verification shows that the vibration amplitude of the smart structure under two-mode harmonic excitation and random excitation can be reduced by 80{\%} and 60{\%}, respectively.",
author = "Jeng, {C. A.} and Shih-Ming Yang and Lin, {J. N.}",
year = "1997",
month = "1",
day = "1",
doi = "10.1177/1045389X9700801204",
language = "English",
volume = "8",
pages = "1035--1043",
journal = "Journal of Intelligent Material Systems and Structures",
issn = "1045-389X",
publisher = "SAGE Publications Ltd",
number = "12",

}

Multi-mode control of structures by using neural networks with marquardt algorithms. / Jeng, C. A.; Yang, Shih-Ming; Lin, J. N.

In: Journal of Intelligent Material Systems and Structures, Vol. 8, No. 12, 01.01.1997, p. 1035-1043.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Multi-mode control of structures by using neural networks with marquardt algorithms

AU - Jeng, C. A.

AU - Yang, Shih-Ming

AU - Lin, J. N.

PY - 1997/1/1

Y1 - 1997/1/1

N2 - This paper presents an integrated approach of identification, estimation and vibration control of smart structures by using neural networks with Marquardt adaptation algorithm. An identification neural network is first constructed to model the system dynamics of a composite laminate structure embedded with piezoelectric sensor and actuator. Based on the identification network, a neural controller is then developed to meet the vibration suppression performance specified by a reference model. In addition, an estimation neural network is also developed that enables the measurement of a single piezoelectric sensor to represent the state variables of displacement and velocity of the structure. The neural controller can then minimize the structure vibration by using a pair of piezoelectric sensors and actuators. Experimental verification shows that the vibration amplitude of the smart structure under two-mode harmonic excitation and random excitation can be reduced by 80% and 60%, respectively.

AB - This paper presents an integrated approach of identification, estimation and vibration control of smart structures by using neural networks with Marquardt adaptation algorithm. An identification neural network is first constructed to model the system dynamics of a composite laminate structure embedded with piezoelectric sensor and actuator. Based on the identification network, a neural controller is then developed to meet the vibration suppression performance specified by a reference model. In addition, an estimation neural network is also developed that enables the measurement of a single piezoelectric sensor to represent the state variables of displacement and velocity of the structure. The neural controller can then minimize the structure vibration by using a pair of piezoelectric sensors and actuators. Experimental verification shows that the vibration amplitude of the smart structure under two-mode harmonic excitation and random excitation can be reduced by 80% and 60%, respectively.

UR - http://www.scopus.com/inward/record.url?scp=0031313023&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031313023&partnerID=8YFLogxK

U2 - 10.1177/1045389X9700801204

DO - 10.1177/1045389X9700801204

M3 - Article

VL - 8

SP - 1035

EP - 1043

JO - Journal of Intelligent Material Systems and Structures

JF - Journal of Intelligent Material Systems and Structures

SN - 1045-389X

IS - 12

ER -