Acceleration-based damage indicators for building structures using neural network emulators

Yuyin Qian, Akira Mita

研究成果: Article

18 引用 (Scopus)

抄録

In this paper we propose the use of artificial neural network (ANN) emulators for an acceleration-based approach to evaluating building structures under earthquake excitation. The input layer of the ANN is a forced vibration, described as ground acceleration and the acceleration data of several floors. The approach is improved by using the acceleration at later time steps as the output of the neural network (NN). This time delay is optimized as a tunable band to provide the most sensitive signals. Minimally, this approach requires only one sensor, making it highly practicable and flexible. It is applicable to structures under diverse excitations including even very small impacts. Based on numerical simulation of a 5-story shear structure, we determined appropriate parameters for use of an NN and studied the generality and efficacy of the approach. The damage index, the relative root mean square error, was calculated for the case of a single structural damage as well as for cases of double damages at different damage locations, and appropriate parameters for the NN emulator were proposed according to the damage patterns. Variant ground motions were used to certify the generality of the approach. The numerical simulations of the proposed approach were verified experimentally.

元の言語English
ページ(範囲)901-920
ページ数20
ジャーナルStructural Control and Health Monitoring
15
発行部数6
DOI
出版物ステータスPublished - 2008 10

Fingerprint

Neural networks
Computer simulation
Mean square error
Time delay
Earthquakes
Sensors

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Building and Construction
  • Mechanics of Materials

これを引用

@article{a51c9276f538492e9eab499e1a26ef21,
title = "Acceleration-based damage indicators for building structures using neural network emulators",
abstract = "In this paper we propose the use of artificial neural network (ANN) emulators for an acceleration-based approach to evaluating building structures under earthquake excitation. The input layer of the ANN is a forced vibration, described as ground acceleration and the acceleration data of several floors. The approach is improved by using the acceleration at later time steps as the output of the neural network (NN). This time delay is optimized as a tunable band to provide the most sensitive signals. Minimally, this approach requires only one sensor, making it highly practicable and flexible. It is applicable to structures under diverse excitations including even very small impacts. Based on numerical simulation of a 5-story shear structure, we determined appropriate parameters for use of an NN and studied the generality and efficacy of the approach. The damage index, the relative root mean square error, was calculated for the case of a single structural damage as well as for cases of double damages at different damage locations, and appropriate parameters for the NN emulator were proposed according to the damage patterns. Variant ground motions were used to certify the generality of the approach. The numerical simulations of the proposed approach were verified experimentally.",
keywords = "Building structures, Damage identification, Damage indicators, Neural network emulator, Structural health monitoring",
author = "Yuyin Qian and Akira Mita",
year = "2008",
month = "10",
doi = "10.1002/stc.226",
language = "English",
volume = "15",
pages = "901--920",
journal = "Structural Control and Health Monitoring",
issn = "1545-2255",
publisher = "John Wiley and Sons Ltd",
number = "6",

}

TY - JOUR

T1 - Acceleration-based damage indicators for building structures using neural network emulators

AU - Qian, Yuyin

AU - Mita, Akira

PY - 2008/10

Y1 - 2008/10

N2 - In this paper we propose the use of artificial neural network (ANN) emulators for an acceleration-based approach to evaluating building structures under earthquake excitation. The input layer of the ANN is a forced vibration, described as ground acceleration and the acceleration data of several floors. The approach is improved by using the acceleration at later time steps as the output of the neural network (NN). This time delay is optimized as a tunable band to provide the most sensitive signals. Minimally, this approach requires only one sensor, making it highly practicable and flexible. It is applicable to structures under diverse excitations including even very small impacts. Based on numerical simulation of a 5-story shear structure, we determined appropriate parameters for use of an NN and studied the generality and efficacy of the approach. The damage index, the relative root mean square error, was calculated for the case of a single structural damage as well as for cases of double damages at different damage locations, and appropriate parameters for the NN emulator were proposed according to the damage patterns. Variant ground motions were used to certify the generality of the approach. The numerical simulations of the proposed approach were verified experimentally.

AB - In this paper we propose the use of artificial neural network (ANN) emulators for an acceleration-based approach to evaluating building structures under earthquake excitation. The input layer of the ANN is a forced vibration, described as ground acceleration and the acceleration data of several floors. The approach is improved by using the acceleration at later time steps as the output of the neural network (NN). This time delay is optimized as a tunable band to provide the most sensitive signals. Minimally, this approach requires only one sensor, making it highly practicable and flexible. It is applicable to structures under diverse excitations including even very small impacts. Based on numerical simulation of a 5-story shear structure, we determined appropriate parameters for use of an NN and studied the generality and efficacy of the approach. The damage index, the relative root mean square error, was calculated for the case of a single structural damage as well as for cases of double damages at different damage locations, and appropriate parameters for the NN emulator were proposed according to the damage patterns. Variant ground motions were used to certify the generality of the approach. The numerical simulations of the proposed approach were verified experimentally.

KW - Building structures

KW - Damage identification

KW - Damage indicators

KW - Neural network emulator

KW - Structural health monitoring

UR - http://www.scopus.com/inward/record.url?scp=55349117117&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=55349117117&partnerID=8YFLogxK

U2 - 10.1002/stc.226

DO - 10.1002/stc.226

M3 - Article

AN - SCOPUS:55349117117

VL - 15

SP - 901

EP - 920

JO - Structural Control and Health Monitoring

JF - Structural Control and Health Monitoring

SN - 1545-2255

IS - 6

ER -