Application of Machine Learning Algorithms in Civil Structural Health Monitoring

DOI: https://doi.org/10.62517/jcte.202506303

Author(s)

Qin Yujian1, Wang Yuhong2,*

Affiliation(s)

1School of Civil Engineering, Inner Mongolia University of Science & Technology, Baotou, Inner Mongolia, China 2College of Information and Electrical Engineering ,China Agricultural University, Beijing, China *Corresponding author

Abstract

Civil Structural Health Monitoring (SHM) faces challenges such as complex, multi-source, noisy data, and the difficulty of traditional methods in achieving efficient, real-time damage identification. This study explores and validates the effectiveness of machine learning algorithms applied in SHM. Firstly, multi-source sensor data including acceleration and strain from bridge structures are collected, and Wavelet Packet Transform (WPT) is used for denoising and feature extraction. Secondly, Principal Component Analysis (PCA) is employed for dimensionality reduction to obtain key features. Subsequently, machine learning algorithms such as Support Vector Machine (SVM) and Random Forest (RF) are utilized for structural health state classification and damage localization. Experiments using monitoring data from an actual bridge demonstrate that the Random Forest method achieves damage localization errors within 1.4 meters and elevates the average confidence level for damage level classification to 92%, while SVM exhibits higher damage detection sensitivity under small-sample scenarios. The SHM approach based on multi-source feature fusion and machine learning algorithms significantly enhances the accuracy and real-time capability of damage identification in civil structures, providing robust technical support for structural safety management.

Keywords

Civil Structural Health Monitoring; Machine Learning; Feature Extraction; Damage Localization; Data Fusion

References

[1]Long Wujian, Shu Yuqing, Mei Liu, Kou Shicong, Luo Qiling. A review of the application of intelligent structural health monitoring in civil engineering[J]. Structural Engineer, 2024, 40(3): 203-216 [2] Wang Na. Application and exploration of digital technology in structural health monitoring[J]. Engineering Quality, 2024, 42(8): 5-8 [3] He Min, Yuan Zetong, Tian Jing, Zhang Mingzhong, Hou Runkun, Hou Gangling. Talent training for nuclear power plant structural health monitoring from a multidisciplinary perspective[J]. Journal of Higher Education, 2024 ,10(20):167-170 [4]Weng Shun, Zhang Zhiyue, Gao Ke, Zhu Hongping. Research progress of flexible piezoresistive strain sensing technology in the field of structural health monitoring[J]. Journal of Building Structures,2024,45(7):242-261 [5]Du Houyi, He Yuxin, Huang Lieran, Gao Ziang, Zhang Ruilin, Liu Hu, Liu Chuntai. Research status of fiber reinforced polymer matrix composites with structural health monitoring function[J]. New Chemical Materials,2025,53(1):9-14 [6]Flah M, Nunez I, Ben Chaabene W, et al. Machine learning algorithms in civil structural health monitoring: A systematic review[J]. Archives of computational methods in engineering, 2021, 28(4): 2621-2643. [7]Gharehbaghi V R, Noroozinejad Farsangi E, Noori M, et al. A critical review on structural health monitoring: Definitions, methods, and perspectives[J]. Archives of computational methods in engineering, 2022, 29(4): 2209-2235. [8]Han Q, Ma Q, Xu J, et al. Structural health monitoring research under varying temperature condition: A review[J]. Journal of Civil Structural Health Monitoring, 2021, 11(1): 149-173. [9]Dong C Z, Catbas F N. A review of computer vision–based structural health monitoring at local and global levels[J]. Structural Health Monitoring, 2021, 20(2): 692-743. [10]Bao Y, Li H. Machine learning paradigm for structural health monitoring[J]. Structural health monitoring, 2021, 20(4): 1353-1372.