Class activation map을 활용한 변위/변형률 정보 기반 구조물 손상 탐지 기법

@article{ART002759738},
author={ 정인호 and 김태성 and 조해성 },
title={Class activation map을 활용한 변위/변형률 정보 기반 구조물 손상 탐지 기법},
journal={풍력에너지저널},
issn={2093-5099},
year={2021},
volume={12},
number={3},
pages={45-54},
doi={10.33519/kwea.2021.12.3.006},
url={http://dx.doi.org/10.33519/kwea.2021.12.3.006}

TY - JOUR
AU - 정인호
AU - 김태성
AU - 조해성
TI - Class activation map을 활용한 변위/변형률 정보 기반 구조물 손상 탐지 기법
T2 - 풍력에너지저널
PY - 2021
VL - 12
IS - 3
PB - 한국풍력에너지학회
SP - 45-54
SN - 2093-5099
AB - Initial structural damage to a structure propagates and leads to failure. Detecting damage at an early stage is important to prevent failure. Recently, studies on measuring the displacement of a structure and predicting the strain field using digital image correlation (DIC) have been actively conducted. However, when the degree of damage is small or occurs in an area where stress is concentrated, it is difficult to identify it by visual inspection. Yet, it is impossible to process the real-time strain field data of large structures such as wind turbine blades, bridges, etc. In this paper, a novel real-time damage detection method using a class activation map (CAM) is developed. The CAM learns the relationship between strain field and structural damage location. After training is finished, the CAM is not only able to detect damage location from an untrained structural strain field, but also to print images of damage locations. The developed model predicts damage with 99.2 % accuracy.
KW - 손상탐지, 디지털영상처리, 분류 활성도맵, 구조건전성 모니터링, 인공신경망
DO - 10.33519/kwea.2021.12.3.006
UR - http://dx.doi.org/10.33519/kwea.2021.12.3.006
ER -

정인호 , 김태성 and 조해성 (2021). Class activation map을 활용한 변위/변형률 정보 기반 구조물 손상 탐지 기법. 풍력에너지저널, 12( 3), 45- 54.

정인호 , 김태성 and 조해성 . 2021, “Class activation map을 활용한 변위/변형률 정보 기반 구조물 손상 탐지 기법”, 풍력에너지저널, vol. 12, no. 3, pp. 45-54. Available from: doi:10.33519/kwea.2021.12.3.006

정인호 김태성 et al. 조해성 “Class activation map을 활용한 변위/변형률 정보 기반 구조물 손상 탐지 기법” 풍력에너지저널 12.3 pp. 45-54 (2021): 45.

정인호 , 김태성 , 조해성 . Class activation map을 활용한 변위/변형률 정보 기반 구조물 손상 탐지 기법 풍력에너지저널 [Internet]. 2021; 12( 3), : 45-54. Available from: doi:10.33519/kwea.2021.12.3.006

정인호 , 김태성 and 조해성 . “Class activation map을 활용한 변위/변형률 정보 기반 구조물 손상 탐지 기법” 풍력에너지저널 12, no.3 (2021): 45-54. doi: 10.33519/kwea.2021.12.3.006

홈 권호 목록 논문 목록 논문 상세

Class activation map을 활용한 변위/변형률 정보 기반 구조물 손상 탐지 기법

풍력에너지저널

약어 : -

2021, vol.12, no.3, pp.45 - 54

DOI : 10.33519/kwea.2021.12.3.006

발행기관 : 한국풍력에너지학회

연구분야 : 기타공학

정인호¹ , 김태성² , 조해성³

¹전북대학교 항공우주공학과

²Technical University of Denmark

³전북대학교

인용한 논문 수 : - 서지 간략 보기

초록

Initial structural damage to a structure propagates and leads to failure. Detecting damage at an early stage is important to prevent failure. Recently, studies on measuring the displacement of a structure and predicting the strain field using digital image correlation (DIC) have been actively conducted. However, when the degree of damage is small or occurs in an area where stress is concentrated, it is difficult to identify it by visual inspection. Yet, it is impossible to process the real-time strain field data of large structures such as wind turbine blades, bridges, etc. In this paper, a novel real-time damage detection method using a class activation map (CAM) is developed. The CAM learns the relationship between strain field and structural damage location. After training is finished, the CAM is not only able to detect damage location from an untrained structural strain field, but also to print images of damage locations. The developed model predicts damage with 99.2 % accuracy.

키워드

손상탐지, 디지털영상처리, 분류 활성도맵, 구조건전성 모니터링, 인공신경망

참고문헌(11)

[학술지] Wang, F. / 2019 / Initial crack propagation and the influence factors of aircraft pipe pressure / Materials 12 (19) : 3098
[학술지] Yang, Y. / 2017 / -field, high-spatial-resolution detection of local structural damage from low-resolution random strain field measurements / Journal of Sound and Vibration 399 : 75 ~ 85
[학술지] Fritzen, C. P. / 2005 / Vibration-based structural health monitoring–concepts and applications / Key Engineering Materials 293 : 3 ~ 20
[학술지] Sierra-Pérez, J. / 2012 / Damage detection by using FBGs and strain field pattern recognition techniques / Smart materials and structures 22 (2) : 025011
[학술지] Hu, Y. / 2019 / Local damage detection of membranes based on Bayesian operational modal analysis and three-dimensional digital image correlation / Mechanical Systems and Signal Processing 131 : 633 ~ 648
[학술지] Pan, B. / 2009 / Two-dimensional digital image correlation for in-plane displacement and strain measurement: a review / Measurement science and technology 20 (6) : 062001
[학술지] Reagan, D. / 2018 / Feasibility of using digital image correlation for unmanned aerial vehicle structural health monitoring of bridges / Structural Health Monitoring 17 (5) : 1056 ~ 1072
[학술지] Gulgec, N. S. / 2020 / Structural sensing with deep learning:Strain estimation from acceleration data for fatigue assessment / Computer‐Aided Civil and Infrastructure Engineering 35 (12) : 1349 ~ 1364
[학술지] Sierra-Pérez, J. / 2016 / Damage and nonlinearities detection in wind turbine blades based on strain field pattern recognition. FBGs, OBR and strain gauges comparison / Composite Structures 135 : 156 ~ 166
[학술지] Sierra-Perez, J. / 2015 / Structural health monitoring by means of strain field pattern recognition on / IFAC-PapersOnLine 48 (28) : 987 ~ 992
[학술지] 김아람 / 2018 / 딥러닝과 영상처리기법을 이용한 콘크리트 지반 구조물 균열 탐지 / 한국지반공학회논문집 34 (12) : 145 ~ 154