Machine Learning Framework for SHM Alarm Log Triage under Alarm Flood and Limited Labeled Data: A Case Study on a Tropical Cable-Stayed Bridge
DOI:
https://doi.org/10.62411/jcta.17014Keywords:
Alarm flood, Alarm log classification, Alarm triage, Cable-stayed bridge, Label scarcity, Interpretable machine learning, Structural health monitoring, Weakly supervised learningAbstract
Structural Health Monitoring (SHM) systems on long-span bridges routinely generate alarm volumes exceeding operators' manual review capacity, a condition known as alarm flood, so that genuine structural anomalies risk being buried among far more numerous instrumentation faults. The problem is acute in developing-country settings, where monitoring falls to small operational teams rather than dedicated staff. This study proposes an alarm-log triage framework that classifies events directly from tabular database records and static sensor metadata, requiring no raw sensor time-series, offering an alternative to the raw-signal paradigm dominating bridge SHM. The dataset comprises 63,934 alarm records logged over 2.5 years on a 641.8-m tropical cable-stayed bridge: labeling collapses as volume rises, leaving only 401 usable labeled records from the pre-flood period, a weakly-supervised task under severe label scarcity. The pipeline integrates alarm-log attributes, causally-ordered temporal window features, and as-built sensor metadata, with fold-internal resampling and recall-oriented operating-point selection. Seven classifiers were benchmarked under identical stratified 5-fold cross-validation, including TabNet alongside linear, kernel-based, tree-ensemble, and neural baselines. Gradient-boosted tree ensembles separate clearly from all other families (F1-Macro 0.7991–0.8860 outside the tree family versus 0.9354–0.9432 within it; McNemar and DeLong tests confirm the separation, p < 0.05). Differences among the tree ensembles themselves are not consistently significant, so LightGBM is reported as the selected deployment model on consistent top-tier performance (F1-Macro 0.9432, AUC-ROC 0.9885 at the default threshold) rather than as demonstrably superior. A two-part ablation shows temporal alarm-rate features supply most of the discriminative power, while explicit imbalance handling yields no measurable benefit at the observed ratio, indicating that such mechanisms should be calibrated to imbalance severity rather than applied by default. The results establish operational alarm logs as a viable, lightweight input for structural event triage and document alarm flood quantitatively in a real bridge SHMS.References
L. Sun, Z. Shang, Y. Xia, S. Bhowmick, and S. Nagarajaiah, “Review of Bridge Structural Health Monitoring Aided by Big Data and Artificial Intelligence: From Condition Assessment to Damage Detection,” J. Struct. Eng., vol. 146, no. 5, p. 4020073, May 2020, doi: 10.1061/(ASCE)ST.1943-541X.0002535.
C. R. Farrar and K. Worden, “An introduction to structural health monitoring,” Philos. Trans. R. Soc. A Math. Phys. Eng. Sci., vol. 365, no. 1851, pp. 303–315, Feb. 2007, doi: 10.1098/rsta.2006.1928.
J. Jia and Y. Li, “Deep Learning for Structural Health Monitoring: Data, Algorithms, Applications, Challenges, and Trends,” Sensors, vol. 23, no. 21, p. 8824, Oct. 2023, doi: 10.3390/s23218824.
Z. He, W. Li, H. Salehi, H. Zhang, H. Zhou, and P. Jiao, “Integrated structural health monitoring in bridge engineering,” Autom. Constr., vol. 136, p. 104168, Apr. 2022, doi: 10.1016/j.autcon.2022.104168.
R. Zinno, S. S. Haghshenas, G. Guido, and A. Vitale, “Artificial Intelligence and Structural Health Monitoring of Bridges: A Review of the State-of-the-Art,” IEEE Access, vol. 10, pp. 88058–88078, 2022, doi: 10.1109/ACCESS.2022.3199443.
The International Society of Automation [ISA], Management of Alarm Systems for the Process Industries. North Carolina: ANSI (American National Standards Institute), 2016.
M. R. Parvez, W. Hu, and T. Chen, “Real-time pattern matching and ranking for early prediction of industrial alarm floods,” Control Eng. Pract., vol. 120, p. 105004, Mar. 2022, doi: 10.1016/j.conengprac.2021.105004.
R. Kaced, A. Kouadri, K. Baiche, and A. Bensmail, “Multivariate nuisance alarm management in chemical processes,” J. Loss Prev. Process Ind., vol. 72, p. 104548, Sep. 2021, doi: 10.1016/j.jlp.2021.104548.
S. Sekiou, A. Behloul, R. Nait-Said, and Z. Chiremsel, “Alarms prediction and classification in industrial processes using supervised machine learning techniques: A case study in an Algerian gas plant,” Comput. Chem. Eng., vol. 204, p. 109378, Jan. 2026, doi: 10.1016/j.compchemeng.2025.109378.
M. R. Parvez, M. H. Roohi, Z. Guo, and F. Xu, “Proactive management of industrial alarm floods: A reinforcement learning framework for early prediction and operator support,” Control Eng. Pract., vol. 161, p. 106341, Aug. 2025, doi: 10.1016/j.conengprac.2025.106341.
S. D. Puspitasari, S. Harahap, and P. Astuti, “A Critical Review of Bridge Management System in Indonesia,” in Proceedings of the 5th International Conference on Rehabilitation and Maintenance in Civil Engineering, vol. 225, S. A. Kristiawan, B. S. Gan, M. Shahin, and A. Sharma, Eds. Singapore: Springer Nature Singapore, 2023, pp. 381–389. doi: 10.1007/978-981-16-9348-9_33.
S. Samudra, M. Barbosh, and A. Sadhu, “Machine Learning-Assisted Improved Anomaly Detection for Structural Health Monitoring,” Sensors, vol. 23, no. 7, p. 3365, Mar. 2023, doi: 10.3390/s23073365.
S.-Y. Kim and M. Mukhiddinov, “Data Anomaly Detection for Structural Health Monitoring Based on a Convolutional Neural Network,” Sensors, vol. 23, no. 20, p. 8525, Oct. 2023, doi: 10.3390/s23208525.
D. Hu, Y. Lin, S. Li, J. Wu, and H. Ma, “Hierarchical Attention Transformer-Based Sensor Anomaly Detection in Structural Health Monitoring,” Sensors, vol. 25, no. 16, p. 4959, Aug. 2025, doi: 10.3390/s25164959.
J. Zhang, J. Zhang, and Z. Wu, “Long-Short Term Memory Network-Based Monitoring Data Anomaly Detection of a Long-Span Suspension Bridge,” Sensors, vol. 22, no. 16, p. 6045, Aug. 2022, doi: 10.3390/s22166045.
A. M. Mart’inez-Heredia and S. Ventura, “Weak Supervision: A Survey on Predictive Maintenance,” WIREs Data Min. Knowl. Discov., vol. 15, no. 2, p. e70022, Jun. 2025, doi: 10.1002/widm.70022.
J. Nesackon Abraham, M. Q. Tran, J. S. Jayaraj, J. C. Matos, M. R. Valluzzi, and S. N. Dang, “Unsupervised Learning-Based Anomaly Detection for Bridge Structural Health Monitoring: Identifying Deviations from Normal Structural Behaviour,” Sensors, vol. 26, no. 2, p. 561, Jan. 2026, doi: 10.3390/s26020561.
Q. Zhu, W. Li, X. Wang, Q. Zhang, and Y. Du, “Anomaly detection in bridge structural health monitoring via 1D-LBP and statistical feature fusion,” Structures, vol. 70, p. 107734, Dec. 2024, doi: 10.1016/j.istruc.2024.107734.
L. Wang et al., “Online diagnosis for bridge monitoring data via a machine learning-based anomaly detection method,” Measurement, vol. 245, p. 116587, Mar. 2025, doi: 10.1016/j.measurement.2024.116587.
N. Javanbakht, A. Neshastegaran, and I. Izadi, “Alarm-Based Root Cause Analysis in Industrial Processes Using Deep Learning,” arXiv, 2022, doi: 10.48550/arXiv.2203.11321.
N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, “SMOTE: Synthetic Minority Over-sampling Technique,” J. Artif. Intell. Res., vol. 16, no. February 2017, pp. 321–357, Jun. 2002, doi: 10.1613/jair.953.
M. Imani, A. Beikmohammadi, and H. R. Arabnia, “Comprehensive Analysis of Random Forest and XGBoost Performance with SMOTE, ADASYN, and GNUS Under Varying Imbalance Levels,” Technologies, vol. 13, no. 3, p. 88, Feb. 2025, doi: 10.3390/technologies13030088.
Y. Han, Z. Wei, and G. Huang, “An imbalance data quality monitoring based on SMOTE-XGBOOST supported by edge computing,” Sci. Rep., vol. 14, no. 1, p. 10151, May 2024, doi: 10.1038/s41598-024-60600-x.
P. Zhang, Y. Jia, and Y. Shang, “Research and application of XGBoost in imbalanced data,” Int. J. Distrib. Sens. Networks, vol. 18, no. 6, p. 155013292211069, Jun. 2022, doi: 10.1177/15501329221106935.
L. Bonde and A. K. Bichanga, “Improving Credit Card Fraud Detection with Ensemble Deep Learning-Based Models: A Hybrid Approach Using SMOTE-ENN,” J. Comput. Theor. Appl., vol. 2, no. 3, pp. 383–394, Feb. 2025, doi: 10.62411/jcta.12021.
J. P. Ntayagabiri, Y. Bentaleb, J. Ndikumagenge, and H. El Makhtoum, “A Comparative Analysis of Supervised Machine Learning Algorithms for IoT Attack Detection and Classification,” J. Comput. Theor. Appl., vol. 2, no. 3, pp. 395–409, Feb. 2025, doi: 10.62411/jcta.11901.
T. Chen and C. Guestrin, “XGBoost: A Scalable Tree Boosting System,” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Aug. 2016, pp. 785–794. doi: 10.1145/2939672.2939785.
G. Ke et al., “LightGBM: A Highly Efficient Gradient Boosting Decision Tree,” Adv. Neural Inf. Process. Syst., vol. 30, 2017.
V. Borisov, T. Leemann, K. Seßler, J. Haug, M. Pawelczyk, and G. Kasneci, “Deep Neural Networks and Tabular Data: A Survey,” IEEE Trans. Neural Networks Learn. Syst., vol. 35, no. 6, pp. 7499–7519, Jun. 2024, doi: 10.1109/TNNLS.2022.3229161.
L. Breiman, “Random Forests,” Mach. Learn., vol. 45, no. 1, pp. 5–32, Oct. 2001, doi: 10.1023/A:1010933404324.
C. Deng, J. Song, C. Chen, T. Wang, and L. Cheng, “Semi-Supervised Informer for the Compound Fault Diagnosis of Industrial Robots,” Sensors, vol. 24, no. 12, p. 3732, Jun. 2024, doi: 10.3390/s24123732.
K. M. Sujon, R. Hassan, K. Choi, and M. A. Samad, “Accuracy, precision, recall, f1-score, or MCC? empirical evidence from advanced statistics, ML, and XAI for evaluating business predictive models,” J. Big Data, vol. 12, no. 1, p. 268, Dec. 2025, doi: 10.1186/s40537-025-01313-4.
T. Fawcett, “An introduction to ROC analysis,” Pattern Recognit. Lett., vol. 27, no. 8, pp. 861–874, Jun. 2006, doi: 10.1016/j.patrec.2005.10.010.
Y. Ding, X. W. Ye, and Y. Guo, “Data set from wind, temperature, humidity and cable acceleration monitoring of the Jiashao bridge,” J. Civ. Struct. Heal. Monit., vol. 13, no. 2--3, pp. 579–589, Mar. 2023, doi: 10.1007/s13349-022-00662-5.
E. Figueiredo, N. Peres, I. Moldovan, and A. Nasr, “Impact of climate change on long-term damage detection for structural health monitoring of bridges,” Struct. Heal. Monit., vol. 24, no. 4, pp. 2252–2270, Jul. 2025, doi: 10.1177/14759217231224254.
J. Li, X. Meng, L. Hu, and Y. Bao, “Quantifying the Impact of Environment Loads on Displacements in a Suspension Bridge with a Data-Driven Approach,” Sensors, vol. 24, no. 6, p. 1877, Mar. 2024, doi: 10.3390/s24061877.
X. He, G. Tan, W. Chu, S. Zhang, and X. Wei, “Reliability Assessment Method for Simply Supported Bridge Based on Structural Health Monitoring of Frequency with Temperature and Humidity Effect Eliminated,” Sustainability, vol. 14, no. 15, p. 9600, Aug. 2022, doi: 10.3390/su14159600.
J. Kang et al., “Effective alerting for bridge monitoring via a machine learning-based anomaly detection method,” Struct. Heal. Monit., vol. 24, no. 6, pp. 3327–3343, Nov. 2025, doi: 10.1177/14759217241265286.
X. Jian, H. Zhong, Y. Xia, and L. Sun, “Faulty data detection and classification for bridge structural health monitoring via statistical and deep-learning approach,” Struct. Control Heal. Monit., vol. 28, no. 11, p. e2824, Nov. 2021, doi: 10.1002/stc.2824.
Ministry of Public Works and Housing of the Republic of Indonesia, “Regulation No. 10 of 2022 on the Implementation of Road Bridge and Tunnel Safety.” Jakarta, Indonesia, 2022.
Directorate General of Highways, Ministry of Public Works and Housing, Republic of Indonesia, “Guideline for the Design and Installation of Bridge Structural Health Monitoring Systems.” Jakarta, Indonesia, 2025.
Directorate General of Highways, Ministry of Public Works and Housing, Republic of Indonesia, “Guideline for the Maintenance of Bridge Structural Health Monitoring Systems.” Jakarta, Indonesia, 2025.
Y. Yilmaz, O. C. Bayrak, and A. Soycan, “Evaluation of Machine Learning Algorithms for Classification of Infrastructure Elements in Complex Structures,” KSCE J. Civ. Eng., vol. 28, no. 8, pp. 3489–3505, 2024, doi: 10.1007/s12205-024-2062-8.
D. W. Hosmer, S. Lemeshow, and R. X. Sturdivant, Applied Logistic Regression. Wiley, 2013. doi: 10.1002/9781118548387.
C. Cortes and V. Vapnik, “Support-vector networks,” Mach. Learn., vol. 20, no. 3, pp. 273–297, Sep. 1995, doi: 10.1007/BF00994018.
S. Ö. Arik and T. Pfister, “TabNet: Attentive Interpretable Tabular Learning,” Proc. AAAI Conf. Artif. Intell., vol. 35, no. 8, pp. 6679–6687, May 2021, doi: 10.1609/aaai.v35i8.16826.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Aris Haris Rismayana, Gatot Sukmara, Nana Rachmana Syambas, Drees Andriyanto Martono, Acep Purqon
This work is licensed under a Creative Commons Attribution 4.0 International License.
