Data Fault Detection of Structural Health Monitoring System (SHMS)

Jaehwan Kim; Wook Kim; Heesoo Son; Hojin Kim

doi:10.21729/ksds.2025.18.4.41

All Issue

2025 Vol.18, Issue 4 Preview Page Next Page

Original Article

Data Fault Detection of Structural Health Monitoring System (SHMS) 구조 건전성 모니터링 데이터의 결함 검출 기법 고찰

31 December 2025. pp. 41-50

PDF XML

Abstract

In recent years, the application of Structural Health Monitoring (SHM) technology has rapidly expanded to enhance the long-term safety and maintenance efficiency of civil infrastructure. The large-scale data collected from sensor networks in such monitoring systems may contain various types of faults—such as sensor malfunction, signal drift, data loss, and noise contamination—which can significantly degrade the reliability of structural condition assessments. This study comprehensively investigates both data-driven and model-based approaches for the early detection of data faults acquired from Structural Health Monitoring Systems (SHMS). Statistical anomaly detection methods, frequency-domain analyses, machine learning algorithms, and hybrid fault detection techniques were examined to compare their strengths and limitations. The comparative evaluation also assessed the practical applicability of these methods to bridge monitoring systems and digital sensing networks.

Keywords

Structural Health Monitoring (SHM)

Data fault detection

Hybrid algorithm

Kalman filter

Autoencoder

CAN-BUS sensor network

최근 구조물의 장기 안전성 활보와 유지관리 효율향상을 위해 구조 건전성 모니터링(Structural Health Monitoring) 기술의 적용이 급격히 확대되고 있다. 해당 모니터링 시스템의 센서 네트워크로부터 수집되는 대용량 데이터에는 센서의 기능이상, 신호 디르프, 데이터 손실, 노이즈 혼입 등 다양한 결함(Fault)이 존재할 수 있으며, 이는 구조 상태 진단 결과의 신뢰성을 심각하게 저하시킬 수 있다. 본 연구는 구조 건전성 모니터링 시스템(SHMS)으로부터 취득된 데이터 결함을 조기 검출하기 위한 데이터 중심(Data-driven) 및 시스템 중심(Model-based)기법을 종합적으로 검토하였고 통계적 이상치 검출, 주파스 분석, 머신러닝 및 하이브리드 결함 검출 알고리즘을 고찰하여 그 장, 단점을 비교분석하여 교량 및 디지털 센싱, 네트워크 적용에 대한 실효성을 분석하였다.

키워드

구조 건전성 모니터링

데이터 결함 검출

하이브리드 알고리즘

칼만 필터

오토인코더

CAN-BUS 센서 네트워크

References

Chandola, V., A. Banerjee, and V. Kumar. (2009). Anomaly Detection: A Survey. ACM Computing Surveys. 41(3): 1-58.

10.1145/1541880.1541882

Farrar, C. R. and K. Worden. (2012). Structural Health Monitoring: A Machine Learning Perspective. John Wiley & Sons.

10.1002/9781118443118

Feng, Q., A. Mita, and H. Li. (2014). Data-Driven Anomaly Detection in Bridges Using PCA and Machine Learning. Journal of Civil Structural Health Monitoring. 4(3): 157-167.

Ghorbel, M., M. Najar, and L. Saidi. (2015). Statistical Fault Detection for Bridge Monitoring Systems. Engineering Structures. 91: 26-35.

ISO 13374. (2019). Condition Monitoring and Diagnostics of Machines – Data Processing, Communication and Presentation – Part 1: General Guidelines. International Organization for Standardization.

Jin, X., Y. Zhang, and Y. Xu. (2015). Application of Autoencoder in Structural Health Monitoring. Mechanical Systems and Signal Processing. 60-61: 351-366.

Kim, Wook. (2021). Anomaly Detection of Structural Health Monitoring System. Master Thesis. Sejong University. 13-18.

Mohri, T., T. Kobayashi, and M. Nishio. (2012). Hybrid Sensor Fusion for Fault Detection in Structural Health Monitoring. Sensors and Actuators A: Physical. 188: 240-249.

Muhammed, T. and R. A. Shaikh. (2017). An Analysis of Fault Detection Strategies in Wireless Sensor Networks. Journal of Network and Computer Applications. 78: 267-287.

10.1016/j.jnca.2016.10.019

Korean References Translated from the English

김욱 (2021). 구조건전성 모니터링 시스템의 이상징후 검지. 석사학위논문. 세종대학교 대학원. 13-18.

Information

Publisher :Korean Society of Disaster and Security
Publisher(Ko) :한국방재안전학회
Journal Title :Journal of Korean Society of Disaster and Security
Journal Title(Ko) :한국방재안전학회 논문집
Volume : 18
No :4
Pages :41-50
Received Date : 2025-10-15
Revised Date : 2025-11-10
Accepted Date : 2025-11-11
DOI :https://doi.org/10.21729/ksds.2025.18.4.41

Journal of Korean Society of Disaster and Security ISSN:2466-1147(Print) 2508-285X(Online) 한국방재안전학회 논문집

All Issue

Korean References Translated from the English