ASSESSMENT OF STRUCTURAL CONDITION FOR BRIDGE  BASED ON UNSUPERVISED LEARNING ALGORITHM

Hồ Thanh Phong; Lê Hoàng Sơn; Võ Nhật Luân; Đỗ Việt Dũng

doi:10.34238/tnu-jst.11711

ASSESSMENT OF STRUCTURAL CONDITION FOR BRIDGE BASED ON UNSUPERVISED LEARNING ALGORITHM

About this article

Received: 16/12/24 Revised: 22/01/25 Published: 22/01/25

Authors

1. Ho Thanh Phong, ACC245 Joint Stock Company
2. Le Hoang Son, Kien Giang University
3. Vo Nhat Luan, Van Hien University
4. Do Viet Dung , Ho Chi Minh City University of Transport

Abstract

Along with the rapid development of trade, the number and load of vehicles crossing the bridges have increased significantly. As a result, these structures deteriorate quickly and are at a high risk of damage, posing safety hazards for both people and vehicles. This paper proposes a solution for assessing the structural condition of bridges by analyzing structural displacement data sets using the K-means unsupervised learning algorithm. The bridge states were monitored through a sensor network that measured vibration amplitude, acceleration, and flexing. The monitoring sample sets were analyzed using a danger threshold determination method and clustering structure condition data with the K-means algorithm. The results of the structural condition assessment, based on the silhouette coefficient, were divided into three optimal data clusters that correspond to healthy, normal, and abnormal structural conditions. These feasible results validate the effectiveness of the proposed solution, forming a solid foundation for practical implementation.

Keywords

Unsupervised learning; Multi-sensors network; K-means; Structure health monitoring; Data clustering

Full Text:

PDF (Tiếng Việt)

References

[1] A. Aeran, S. Vantadori, A. Carpinteri, S. Siriwardane, and D. Scorza, "Novel non-linear relationship to evaluate the critical plane orientation," Int. J. Fatigue, vol. 124, pp. 537-543, 2019, doi: 10.1016/j.ijfatigue.2019.02.012.

[2] T. Q. Nguyen, T. T. D. Nguyen, X. H. Nguyen, and N. K. Ngo, "A correlation coefficient approach for evaluation of stiffness degradation of beams under moving load," Computers, Materials and Continua, vol. 61, pp. 27-53, 2019, doi: 10.32604/cmc.2019.07756.

[3] M. Kim and J. Song, "Near-Real-Time Identification of Seismic Damage Using Unsupervised Deep Neural Network," J. Eng. Mech., vol. 148, 2022, Art. no. 04022006, doi: 10.1061/(asce)em.1943-7889.0002066.

[4] O. Bouzas, B. Conde, J. C. Matos, M. Solla, and M. Cabaleiro, "Reliability-based structural assessment of historical masonry arch bridges: The case study of Cernadela bridge," Case Stud. Constr. Mater., vol. 18, 2023, Art. no. e02003, doi: 10.1016/j.cscm.2023.e02003.

[5] Z. Xiang, Z. Zhu, and X. Lei, "Fatigue assessment and crack propagation of floorbeam cutout in orthotropic bridge decks," Mater. Des., vol. 226, 2023, Art. no. 111676, doi: 10.1016/j.matdes.2023.111676.

[6] D. P. McCrum, S. Wang, and E. J. OBrien, “Monitoring the health of bridges using accelerations from a fleet of vehicles without knowing individual axle weights,” J. Struct. Integrity Maint., vol. 8, no. 4, pp. 249-259, 2023, doi: 10.1080/24705314.2023.2193779.

[7] A. Santos, R. Santos, M. Silva, E. Figueiredo, C. Sales, and J. C. W. A. Costa, "A Global Expectation–Maximization Approach Based on Memetic Algorithm for Vibration-Based Structural Damage Detection," IEEE Trans. Instrum. Meas., vol. 66, no. 4, pp. 661-670, 2017, doi: 10.1109/TIM.2017.2663478.

[8] Y. Li, N. Zhang, Q. Sun, C. Cai, and K. Li, “Neural Network-Based Anomaly Data Classification and Localization in Bridge Structural Health Monitoring,” Int. J. Struct. Stab. Dyn., vol. 24, no. 16, 2024, Art. no. 2450184, doi: 10.1142/S0219455424501840.

[9] S. Muin, C. Chern, and K. M. Mosalam, “Human–Machine Collaboration Framework for Bridge Health Monitoring,” J. Bridge Eng., vol. 29, no. 7, 2024, Art. no. 4024041, doi: 10.1061/JBENF2.BEENG-6587.

[10] A. Diez, N. L. D. Khoa, M. M. Alamdari, Y. Wang, F. Chen, and P. Runcie, “A clustering approach for structural health monitoring on bridges," J. Civ. Struct. Health Monit., vol. 6, pp. 429-445, 2016, doi: 10.1007/s13349-016-0160-0.

[11] J. Xiong, L. Shu, Q. Wang, W. Xu, and C. Zhu, “A Scheme on Indoor Tracking of Ship Dynamic Positioning Based on Distributed Multi-Sensor Data Fusion," IEEE Access, vol. 5, pp. 379-392, 2017, doi: 10.1109/ACCESS.2016.2607232.

[12] N. A. Cao, V. V. Vu, and T. T. H. Phung, “K-Means* Clustering Algorithm,” TNU Journal of Science and Technology, vol. 169, no. 9, pp. 159-164, 2017.

[13] Vietnam Ministry of Science and Technology, “TCVN 7378: 2004: Vibration and shock - Vibration of buildings - Limits of vibration levels and method for evaluation,” October 29, 2004.

[14] X. K. Dang, J. M. Corchado, V. V. Le, and V. D. Do, “Non-parametric Vibration-based Structural Damage Detection for Coastal Structures: Multi-Dimension to Single Input Convolutional Neural Network Approach,” Advances in Electrical and Computer Engineering, vol. 24, no. 4, pp. 3-18, 2024, doi: 10.4316/AECE.2024.04001.

[15] M. T. Nguyen and N. Rahnavard, “Cluster-Based Energy-Efficient Data Collection in Wireless Sensor Networks Utilizing Compressive Sensing,” 2013 IEEE Military Communications Conference, CA, USA, 2013, pp. 1708-1713, doi: 10.1109/MILCOM.2013.289.

[16] M. T. Nguyen, “Energy-Efficient Data Collection Method In Clustered Wireless Sensor Networks,” TNU Journal of Science and Technology, vol. 166, no. 6, pp. 121-124, 2017.

[17] R. Gu, Z. Yang, and Y. Ji, "Machine learning for intelligent optical networks: A comprehensive survey," J. Network Comput. Appl., vol. 157, pp. 102576-102618, 2020, doi: 10.1016/j.jnca.2020.102576.

[18] V. V. Vu, “An efficient semi-supervised graph based clustering,” Intell. Data Anal., vol. 22, no. 2, pp. 297-307, 2018, doi: 10.3233/IDA-163296.

[19] T. A. Pham, X. K. Dang, and N. S. Vo, “Optimising Maritime Big Data by K-means Clustering with Mapreduce Model,” Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, vol. 157, pp. 136-151, 2022, doi: 10.1007/978-3-031-08878-0_10.

[20] P. J. Rousseeuw, “Silhouettes: A graphical aid to the interpretation and validation of cluster analysis,” J. Comput. Appl. Math., vol. 20, pp. 53-65, 1987, doi: 10.1016/0377-0427(87)90125-7.

[21] M. B. Baylon, F. A. A. Uy, K. M. S. Montes, and K. A. D. Embalzado, "Threshold Determination Using Bi-hazard Fragility Curves for the Evaluation of Structural Health Monitoring of USHER Technology," IOP Conf. Ser.: Mater. Sci. Eng., vol. 739, 2020, Art. no. 012002, doi: 10.1088/1757-899X/739/1/012002.

DOI: https://doi.org/10.34238/tnu-jst.11711

Refbacks

There are currently no refbacks.



Remember me