Damage Detection for Truss Bridge Structure Using XGBoost

Abstract:

Structural health monitoring (SHM) is a burgeoning area of interest among modern research endeavors, motivated by the application of state-of-the-art machine learning models. During the last few years, many researchers have proposed techniques for the analysis of SHM datasets, particularly those corresponding to sequence data collected from sensors. Following the flow of this research, in this work, we introduce an effective approach utilizing eXtreme Gradient Boosting (XGBoost), a potent ensemble learning framework rooted in gradient boosting for damage detection. A dataset of damage cases from the Nam O bridge, a steel truss bridge for railways, is applied to assess damages. To evaluate the effectiveness of the method used, common DL models such as One-Dimensional Convolutional Neural Network (1DCNN) and Long Short-Term Memory (LSTM) are also considered. Moreover, the influence of the boosting round on the overall result will be analyzed. The results from the validation set and the test set both illustrate that XGBoost performs better in accuracy than 1DCNN and LSTM with 100% and 95.7%, respectively. Besides, XGBoost is the model that achieved the lowest mean square error (MSE) of only 4.3% in the test set. These results demonstrate the significant potential of utilizing the XGBoost model in SHM and truss bridge structures, especially through the utilization of time-series data.

• Periodical: Advances in Science and Technology (Volume 158)
• Pages: 65-74
• DOI: https://doi.org/10.4028/p-jDC4Vd
• Online since: January 2025
• Authors: Nguyen Huu Quyet, Tran Ngoc Hoa*, Ngoc Lan Nguyen, Bui Tien Thanh
• Keywords: Ensemble Learning, eXtreme Gradient Boosting (XGBoost), Structural Health Monitoring, Truss Bridge Structure

References

[1] Penfold RB, Zhang F. Use of Interrupted Time Series Analysis in Evaluating Health Care Quality Improvements. Academic Pediatrics 2013;13:S38–44.

DOI: 10.1016/j.acap.2013.08.002

[2] Lu M, Xu X. TRNN: An efficient time-series recurrent neural network for stock price prediction. Information Sciences 2024;657:119951.

DOI: 10.1016/j.ins.2023.119951

[3] Raza SA, Siddiqui AW. Exploring temporal demand patterns of refined petroleum products: Implications of the COVID-19 pandemic as a black swan event. The Extractive Industries and Society 2024;17:101388.

DOI: 10.1016/j.exis.2023.101388

[4] Nguyen QH, Le TX, Nguyen DLM, Bui TT, Nguyen NC, Tran HN. A Prospective Technique for Damage Detection in Truss Structures Using the Fusion of DNN with AVOA. KSCE J Civ Eng 2024.

DOI: 10.1007/s12205-024-1968-5

[5] Shu J, Zhang Z, Gonzalez I, Karoumi R. The application of a damage detection method using Artificial Neural Network and train-induced vibrations on a simplified railway bridge model. Engineering Structures 2013;52:408–21.

DOI: 10.1016/j.engstruct.2013.02.031

[6] Ishak S, Al-Deek H. Performance evaluation of short-term time-series traffic prediction model. Journal of Transportation Engineering 2002;128:490–8.

DOI: 10.1061/(asce)0733-947x(2002)128:6(490)

[7] Zhang Y, Yuen K-V. Review of artificial intelligence-based bridge damage detection. Advances in Mechanical Engineering 2022; 14: 16878132221122770. https://doi.org/10.1177/ 16878132221122770.

[8] Luleci F, Necati Catbas F, Avci O. CycleGAN for undamaged-to-damaged domain translation for structural health monitoring and damage detection. Mechanical Systems and Signal Processing 2023; 197:110370.

DOI: 10.1016/j.ymssp.2023.110370

[9] Nhung NTC, Vu LV, Nguyen HQ, Huyen DT, Nguyen DB, Quang MT. Development and Application of Linear Variable Differential Transformer (LVDT) Sensors for the Structural Health Monitoring of an Urban Railway Bridge in Vietnam. Engineering, Technology & Applied Science Research 2023;13:11622–7.

DOI: 10.48084/etasr.6192

[10] Liao Y, Wang Y, Zeng X, Wu M, Qing X. Multiscale 1-DCNN for Damage Localization and Quantification Using Guided Waves With Novel Data Fusion Technique and New Self-Attention Module. IEEE Transactions on Industrial Informatics 2024;20:492–502.

DOI: 10.1109/TII.2023.3268442

[11] Almutairi M, Nikitas N, Abdeljaber O, Avci O, Bocian M. A methodological approach towards evaluating structural damage severity using 1D CNNs. Structures 2021;34:4435–46.

DOI: 10.1016/j.istruc.2021.10.029

[12] Li Z, Lan Y, Lin W. Footbridge damage detection using smartphone-recorded responses of micromobility and convolutional neural networks. Automation in Construction 2024; 166: 105587.

DOI: 10.1016/j.autcon.2024.105587

[13] Viotti ID, Ribeiro RF, Gomes GF. Damage identification in sandwich structures using Convolutional Neural Networks. Mechanical Systems and Signal Processing 2024;220:111649.

DOI: 10.1016/j.ymssp.2024.111649

[14] Rautela M, Gopalakrishnan S. Ultrasonic guided wave based structural damage detection and localization using model assisted convolutional and recurrent neural networks. Expert Systems with Applications 2021;167:114189.

DOI: 10.1016/j.eswa.2020.114189

[15] Bui-Tien T, Bui-Ngoc D, Nguyen-Tran H, Nguyen-Ngoc L, Tran-Ngoc H, Tran-Viet H. Damage Detection in Structural Health Monitoring using Hybrid Convolution Neural Network and Recurrent Neural Network. Frattura Ed Integrità Strutturale 2022;16:461–70.

DOI: 10.3221/IGF-ESIS.59.30

[16] Sony S, Gamage S, Sadhu A, Samarabandu J. Vibration-based multiclass damage detection and localization using long short-term memory networks. Structures 2022;35:436–51.

DOI: 10.1016/j.istruc.2021.10.088

[17] Le-Xuan T, Bui-Tien T, Tran-Ngoc H. A novel approach model design for signal data using 1DCNN combing with LSTM and ResNet for damaged detection problem. Structures 2024;59:105784.

DOI: 10.1016/j.istruc.2023.105784

[18] Luo J, Zhang Z, Fu Y, Rao F. Time series prediction of COVID-19 transmission in America using LSTM and XGBoost algorithms. Results in Physics 2021;27:104462.

DOI: 10.1016/j.rinp.2021.104462

[19] Zhang L, Bian W, Qu W, Tuo L, Wang Y. Time series forecast of sales volume based on XGBoost. J Phys: Conf Ser 2021; 1873: 012067.

DOI: 10.1088/1742-6596/1873/1/012067

[20] Xian S, Chen K, Cheng Y. Improved seagull optimization algorithm of partition and XGBoost of prediction for fuzzy time series forecasting of COVID-19 daily confirmed. Advances in Engineering Software 2022;173:103212.

DOI: 10.1016/j.advengsoft.2022.103212

[21] Chakraborty D, Elzarka H. Early detection of faults in HVAC systems using an XGBoost model with a dynamic threshold. Energy and Buildings 2019; 185: 326–44.

DOI: 10.1016/j.enbuild.2018.12.032

[22] Ma J, Cheng JCP, Xu Z, Chen K, Lin C, Jiang F. Identification of the most influential areas for air pollution control using XGBoost and Grid Importance Rank. Journal of Cleaner Production 2020;274:122835.

DOI: 10.1016/j.jclepro.2020.122835

[23] Shi X, Wong YD, Li MZ-F, Palanisamy C, Chai C. A feature learning approach based on XGBoost for driving assessment and risk prediction. Accident Analysis & Prevention 2019;129:170–9.

DOI: 10.1016/j.aap.2019.05.005

[24] Song K, Yan F, Ding T, Gao L, Lu S. A steel property optimization model based on the XGBoost algorithm and improved PSO. Computational Materials Science 2020;174:109472.

DOI: 10.1016/j.commatsci.2019.109472

[25] Lim S, Chi S. Xgboost application on bridge management systems for proactive damage estimation. Advanced Engineering Informatics 2019;41:100922. https://doi.org/10.1016/j.aei. 2019.100922.

DOI: 10.1016/j.aei.2019.100922

[26] Dong W, Huang Y, Lehane B, Ma G. XGBoost algorithm-based prediction of concrete electrical resistivity for structural health monitoring. Automation in Construction 2020;114:103155.

DOI: 10.1016/j.autcon.2020.103155

[27] Chen T, Guestrin C. XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016, p.785–94.

DOI: 10.1145/2939672.2939785

[28] Friedman J, Hastie T, Tibshirani R. Additive logistic regression: a statistical view of boosting (With discussion and a rejoinder by the authors). The Annals of Statistics 2000;28:337–407.

DOI: 10.1214/aos/1016218223

[29] Friedman JH. Greedy Function Approximation: A Gradient Boosting Machine. The Annals of Statistics 2001;29:1189–232.

DOI: 10.1214/aos/1013203451

[30] Xiao F, Chen T, Zhang J, Zhang S. Water management fault diagnosis for proton-exchange membrane fuel cells based on deep learning methods. International Journal of Hydrogen Energy 2023;48:28163–73.

DOI: 10.1016/j.ijhydene.2023.03.097

[31] Tran-Ngoc H, Khatir S, De Roeck G, Bui-Tien T, Nguyen-Ngoc L, Abdel Wahab M. Model Updating for Nam O Bridge Using Particle Swarm Optimization Algorithm and Genetic Algorithm. Sensors 2018;18:4131.

DOI: 10.3390/s18124131

[32] François S, Schevenels M, Dooms D, Jansen M, Wambacq J, Lombaert G, et al. Stabil: An educational Matlab toolbox for static and dynamic structural analysis. Comp Applic In Engineering 2021;29:1372–89.

DOI: 10.1002/cae.22391

[33] Tran-Ngoc H, Khatir S, De Roeck G, Bui-Tien T, Nguyen-Ngoc L, Abdel Wahab M. Model updating for Nam O bridge using particle swarm optimization algorithm and genetic algorithm. Sensors 2018;18:4131.

DOI: 10.3390/s18124131