Damage indicator for building structures using artificial neural networks as emulators

Akira Mita, Yuyin Qian

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Damage indicator for building structures using artificial neural networks (ANN) requiring only acceleration response is proposed. The ANN emulator used for emulating the structural response is tuned to properly model the hysteretic nature of building response. To facilitate the most realistic monitoring system using accelerometers, the acceleration streams at the same location but at different time steps were utilized. The prediction accuracy could be raised by the increment of number of acceleration streams at different time steps. In our proposed approach, damage occurrence alarm could be obtained practically and economically only using readily available acceleration time histories. Based on the numerical simulation for a 5-story shear structure, the adaptability, generality and appropriate parameter of the neural network were studied in. The damage is quantified by using relative root mean square (RRMS) error. Variant ground motions were used to certify the generality of this approach. The appropriate parameter of the neural network was suggested according to variant values of damage index corresponding to the different parameters.

Original languageEnglish
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
Volume6529 PART 2
DOIs
Publication statusPublished - 2007
EventSensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2007 - San Diego, CA, United States
Duration: 2007 Mar 192007 Mar 22

Other

OtherSensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2007
CountryUnited States
CitySan Diego, CA
Period07/3/1907/3/22

Fingerprint

damage
Neural networks
warning systems
root-mean-square errors
accelerometers
Accelerometers
Mean square error
histories
occurrences
shear
Monitoring
Computer simulation
predictions
simulation

Keywords

  • Artificial neural network
  • Damage detection
  • Health monitoring emulator

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Mita, A., & Qian, Y. (2007). Damage indicator for building structures using artificial neural networks as emulators. In Proceedings of SPIE - The International Society for Optical Engineering (Vol. 6529 PART 2). [65292O] https://doi.org/10.1117/12.715982

Damage indicator for building structures using artificial neural networks as emulators. / Mita, Akira; Qian, Yuyin.

Proceedings of SPIE - The International Society for Optical Engineering. Vol. 6529 PART 2 2007. 65292O.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Mita, A & Qian, Y 2007, Damage indicator for building structures using artificial neural networks as emulators. in Proceedings of SPIE - The International Society for Optical Engineering. vol. 6529 PART 2, 65292O, Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2007, San Diego, CA, United States, 07/3/19. https://doi.org/10.1117/12.715982
Mita A, Qian Y. Damage indicator for building structures using artificial neural networks as emulators. In Proceedings of SPIE - The International Society for Optical Engineering. Vol. 6529 PART 2. 2007. 65292O https://doi.org/10.1117/12.715982
Mita, Akira ; Qian, Yuyin. / Damage indicator for building structures using artificial neural networks as emulators. Proceedings of SPIE - The International Society for Optical Engineering. Vol. 6529 PART 2 2007.
@inproceedings{b82ca5157ff940de9c28987bb87482fb,
title = "Damage indicator for building structures using artificial neural networks as emulators",
abstract = "Damage indicator for building structures using artificial neural networks (ANN) requiring only acceleration response is proposed. The ANN emulator used for emulating the structural response is tuned to properly model the hysteretic nature of building response. To facilitate the most realistic monitoring system using accelerometers, the acceleration streams at the same location but at different time steps were utilized. The prediction accuracy could be raised by the increment of number of acceleration streams at different time steps. In our proposed approach, damage occurrence alarm could be obtained practically and economically only using readily available acceleration time histories. Based on the numerical simulation for a 5-story shear structure, the adaptability, generality and appropriate parameter of the neural network were studied in. The damage is quantified by using relative root mean square (RRMS) error. Variant ground motions were used to certify the generality of this approach. The appropriate parameter of the neural network was suggested according to variant values of damage index corresponding to the different parameters.",
keywords = "Artificial neural network, Damage detection, Health monitoring emulator",
author = "Akira Mita and Yuyin Qian",
year = "2007",
doi = "10.1117/12.715982",
language = "English",
isbn = "0819466506",
volume = "6529 PART 2",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

}

TY - GEN

T1 - Damage indicator for building structures using artificial neural networks as emulators

AU - Mita, Akira

AU - Qian, Yuyin

PY - 2007

Y1 - 2007

N2 - Damage indicator for building structures using artificial neural networks (ANN) requiring only acceleration response is proposed. The ANN emulator used for emulating the structural response is tuned to properly model the hysteretic nature of building response. To facilitate the most realistic monitoring system using accelerometers, the acceleration streams at the same location but at different time steps were utilized. The prediction accuracy could be raised by the increment of number of acceleration streams at different time steps. In our proposed approach, damage occurrence alarm could be obtained practically and economically only using readily available acceleration time histories. Based on the numerical simulation for a 5-story shear structure, the adaptability, generality and appropriate parameter of the neural network were studied in. The damage is quantified by using relative root mean square (RRMS) error. Variant ground motions were used to certify the generality of this approach. The appropriate parameter of the neural network was suggested according to variant values of damage index corresponding to the different parameters.

AB - Damage indicator for building structures using artificial neural networks (ANN) requiring only acceleration response is proposed. The ANN emulator used for emulating the structural response is tuned to properly model the hysteretic nature of building response. To facilitate the most realistic monitoring system using accelerometers, the acceleration streams at the same location but at different time steps were utilized. The prediction accuracy could be raised by the increment of number of acceleration streams at different time steps. In our proposed approach, damage occurrence alarm could be obtained practically and economically only using readily available acceleration time histories. Based on the numerical simulation for a 5-story shear structure, the adaptability, generality and appropriate parameter of the neural network were studied in. The damage is quantified by using relative root mean square (RRMS) error. Variant ground motions were used to certify the generality of this approach. The appropriate parameter of the neural network was suggested according to variant values of damage index corresponding to the different parameters.

KW - Artificial neural network

KW - Damage detection

KW - Health monitoring emulator

UR - http://www.scopus.com/inward/record.url?scp=35548969321&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=35548969321&partnerID=8YFLogxK

U2 - 10.1117/12.715982

DO - 10.1117/12.715982

M3 - Conference contribution

AN - SCOPUS:35548969321

SN - 0819466506

SN - 9780819466501

VL - 6529 PART 2

BT - Proceedings of SPIE - The International Society for Optical Engineering

ER -