Decentralized Structural Diagnosis and Monitoring System for Ensemble Learning on Dynamic Characteristics

Yoon-Soo Shin; Kyung-Won Min

doi:10.7734/COSEIK.2021.34.4.183

All Issue

2021 Vol.34, Issue 4 Preview Page Next Page

Research Paper

Decentralized Structural Diagnosis and Monitoring System for Ensemble Learning on Dynamic Characteristics 동특성 앙상블 학습 기반 구조물 진단 모니터링 분산처리 시스템

31 August 2021. pp. 183-189

PDF XML

Abstract

In recent years, active research has been devoted toward developing a monitoring system using ambient vibration data in order to quantitatively determine the deterioration occurring in a structure over a long period of time. This study developed a low-cost edge computing system that detects the abnormalities in structures by utilizing the dynamic characteristics acquired from the structure over the long term for ensemble learning. The system hardware consists of the Raspberry Pi, an accelerometer, an inclinometer, a GPS RTK module, and a LoRa communication module. The structural abnormality detection afforded by the ensemble learning using dynamic characteristics is verified using a laboratory-scale structure model vibration experiment. A real-time distributed processing algorithm with dynamic feature extraction based on the experiment is installed on the Raspberry Pi. Based on the stable operation of installed systems at the Community Service Center, Pohang-si, Korea, the validity of the developed system was verified on-site.

Keywords

ensemble learning

raspberry pi

sensor

LoRa

structural health monitoring

distributed computing

구조물에 장기적으로 발생하는 노후화를 정량적으로 파악하기 위해 상시진동 데이터를 활용한 일반화된 모니터링 시스템에 관한 연구가 세계적으로 활발히 수행중이다. 본 연구에서는 구조물에서 장기적으로 취득되는 동특성을 앙상블 학습에 활용하여 구조물의 이상을 감지하기 위한 보급형 엣지 컴퓨팅 시스템을 구축하였다. 시스템의 하드웨어는 라즈베리파이와 보급형 가속도계, 기울기센서, GPS RTK 모듈, 로라 모듈로 구성됐다. 실험실 규모의 구조물 모형 진동실험을 통해 동특성을 활용한 앙상블 학습의 구조물 이상감지를 검증하였으며, 실험을 기반으로 한 실시간 동특성 추출 분산처리 알고리즘을 라즈베리파이에 탑재하였다. 구축된 시스템을 하우징하고 포항시 행정복지센터에 설치하여 데이터를 취득함으로써 개발된 시스템의 현장 적용성을 검증하였다.

키워드

앙상블 학습

라즈베리파이

센서

로라

구조물 모니터링

분산처리

References

Buhus, E.R., Dimis, D., Apatean, A. (2016) Automatic Parking Access using Openalpr on Raspberry Pi3, Electron. & Telecommun., 57(3). pp.10~15.

Cyrel, O.M., Jesus, M.M., Jackson, L.B., Czarleine, K.P., Maria, K.T. (2015) Real-Time Integrated CCTV Using Face and Pedestrian Detection Image Processing Algorithm For Automatic Traffic Light Transitions, 8th IEEE International Conference Humanoid, 2015.

Ferdoush, S., Li, X. (2014) Wireless Sensor Network System Design using Raspberry Pi and Arduino for Environmental Monitoring Applications, Proc. Comput. Sci., 34(2014), pp.103~110. 10.1016/j.procs.2014.07.059

Hao, S., Aurélien, M., Germán, A., Prieto, M., Nafi T., Oral, B. (2017) Bayesian Characterization of Buildings using Seismic Interferometry on Ambient Vibrations, Mech. Syst. & Signal Process., 85 pp.468~486. 10.1016/j.ymssp.2016.08.038

Jang, S.H., Kim, J.S., Lim, K.H., Sung, J.Y., Park, K.J. (2011) Utilization Plan and Characteristic of Seismic Acceleration Response Signal, National Institute for Disaster Prevention.

Kim, J.H., Lynch, J.P. (2012) Subspace System Identification of Support Excited Structures Part II: Gray-Box Interpretations and Damage Detection, Earthq. Eng. & Struct. Dyn., 41(15), pp.2253~2271. 10.1002/eqe.2185

Kim, J.H., Sohn, H. (2013) Data-Driven Physical Parameter Estimation for Lumped Mass Structures from a Single Point Actuation Test, J. Sound & Vib., 332(18), pp.4390~4402. 10.1016/j.jsv.2013.03.006

Michal, V., Milan, S., Rudolf, Á. (2018) Ambient Vibration Measurements of Steel Truss Bridges, J. Meas. Eng., 6, pp.234~239. 10.21595/jme.2018.20419

Min, K.W., Kim, J.H., Park, S.A., Park, C.S. (2013) Ambient Vibration Testing for Story Stiffness Estimation of a Heritage Timber Building, The Sci. World J., 2013. 10.1155/2013/19848324227999PMC3817661

Narayan, P.P., Minsakshee, M.P. (2014) Driver Assistance System based on Raspberry Pi, Int. J. Comput. Appl., 95(16), pp.36~39. 10.5120/16682-6794

Shin, Y.S., Kim, J.H., Min, K.W. (2019) Design of Edge Computing System Utilizing Raspberry Pi for Structural Response Measurement, J.Comput. Struct. Eng. Inst. Korea, 32(6), pp.375~381. 10.7734/COSEIK.2019.32.6.375

Velez, F.J., Nadziejko, A. (2015) Wireless Sensor and Networking Technologies for Swarms of Aquatic Surface Drones, 2015 IEEE 82nd Vehicular, Technology Conference.10.1109/VTCFall.2015.7391193

Information

Publisher :Computational Structural Engineering Institute of Korea
Publisher(Ko) :한국전산구조공학회
Journal Title :Journal of the Computational Structural Engineering Institute of Korea
Journal Title(Ko) :한국전산구조공학회 논문집
Volume : 34
No :4
Pages :183-189
Received Date : 2021-05-13
Revised Date : 2021-06-17
Accepted Date : 2021-07-08
DOI :https://doi.org/10.7734/COSEIK.2021.34.4.183

Journal of the Computational Structural Engineering Institute of Korea ISSN:1229-3059(Print) 2287-2302(Online) 한국전산구조공학회 논문집

All Issue