An Integrated Expert System for Prioritizing Concrete Railway Bridges Maintenance: A Hybrid Fuzzy Delphi - Fuzzy TOPSIS - MLP Framework
Keywords:
Expert system, Railway concrete bridge maintenance, Multi-criteria decision-making (MCDM), Fuzzy TOPSIS, MLP neural network, Maintenance prioritizationAbstract
Maintenance prioritization of railway bridges is a critical challenge due to limited financial resources and the direct impact of bridge failures on transportation network safety. Traditional approaches relying on individual expert judgment are inadequate for managing the complexity of maintaining precast concrete railway bridges, particularly in environmentally aggressive corridors. This study presents an integrated three-stage expert system (hybrid decision-support framework) for maintenance prioritization of 85 precast box-girder concrete bridges along the BonekuhGorgan railway corridor (Northern Iran). The proposed framework combines: (1) Fuzzy Delphi for extracting, screening, and weighting maintenance criteria through the judgment of 15 domain experts; (2) Fuzzy TOPSIS for quantitative prioritization and computation of the Intervention Priority Index (Cl+) across three inspection periods (2020, 2022, and 2024); and (3) Multilayer Perceptron (MLP) neural network for predicting the future trend of the Cl+ index and supporting preventive maintenance planning. In the Fuzzy Delphi stage, 12 key criteria were identified from 20 initial candidates; expansion joints (C5) and guardrails (C12) received the highest weights (w = 0.096). Kendall's concordance coefficient (W = 0.69) and Cronbach's alpha (α = 0.847) confirmed satisfactory consensus and reliability among experts. Fuzzy TOPSIS results showed that bridge B1, with Cl+ = 0.826, had the most critical condition requiring immediate intervention, while bridge B48, with Cl+ = 0.214, exhibited the lowest deterioration level. The MLP model with a 13-64-1 architecture and Walk-Forward Validation predicted the Cl+ index with R² = 0.931 and RMSE = 0.0214, demonstrating high generalizability. The results indicate that the proposed framework can serve as a practical Decision Support System (DSS) for railway bridge maintenance management, supporting optimal allocation of limited resources with scientific precision and transparency.
References
Alshibani, A., Saa, A. S. A., Hassanian, M. A., Bubshait, A., & Shash, A. (2023). Decision support model for allocating maintenance budgets for bridges. Applied Sciences, 13(17), 9679. https://doi.org/10.3390/app13179679
Bocchini, P., & Frangopol, D. M. (2012). Resilience as optimization criterion for the rehabilitation of bridges belonging to a transportation network subject to earthquake. Structures Congress 2011,
Box, G. E. P., Jenkins, G. M., Reinsel, G. C., & Ljung, G. M. (2015). Time Series Analysis: Forecasting and Control (5th ed.). John Wiley & Sons.
Doshi-Velez, F., & Kim, B. (2017). Towards a rigorous science of interpretable machine learning. ArXiv. https://arxiv.org/abs/1702.08608
Frangopol, D. M. (2011). Life-cycle performance, management, and optimisation of structural systems under uncertainty: Accomplishments and challenges. Structure and Infrastructure Engineering, 7(6), 389-413. https://doi.org/10.1080/15732471003594427
Gal, Y., & Ghahramani, Z. (2016). Dropout as a Bayesian approximation: Representing model uncertainty in deep learning. Proceedings of the 33rd International Conference on Machine Learning,
Gao, W., Li, Q., & Zhang, Y. (2023). Integrating AHP and MLP for predictive maintenance of railway bridges. Expert Systems with Applications, 215, 119431. https://doi.org/10.1016/j.eswa.2022.119431
Ghafoori, M., Abdallah, M., & Ozbek, M. E. (2024). Machine learning-based bridge maintenance optimization model for maximizing performance within available annual budgets. Journal of Bridge Engineering, 29(4), 04024011. https://doi.org/10.1061/JBENF2.BEENG-6436
Glorot, X., & Bengio, Y. (2010). Understanding the difficulty of training deep feedforward neural networks. Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics,
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press. http://www.deeplearningbook.org
Hastie, T., Tibshirani, R., & Friedman, J. (2009). The Elements of Statistical Learning: Data Mining, Inference, and Prediction (2nd ed.). Springer. https://doi.org/10.1007/978-0-387-84858-7
Haykin, S. (2007). Neural Networks and Learning Machines (3rd ed.). Prentice-Hall. https://dl.acm.org/doi/book/10.5555/1213811
Hyndman, R. J., & Athanasopoulos, G. (2021). Forecasting: Principles and Practice (3rd ed.). OTexts. https://doi.org/10.1007/978-3-030-39091-4
Kahraman, C. (2008). Fuzzy Multi-Criteria Decision Making: Theory and Applications with Recent Developments. Springer. https://doi.org/10.1007/978-0-387-76813-7
Li, Y., Deng, J., Wang, Y., Liu, H., Peng, L., Zhang, H., Liang, Y., & Feng, Q. (2025). The condition evaluation of bridges based on fuzzy BWM and fuzzy comprehensive evaluation. Applied Sciences, 15(6), 2904. https://doi.org/10.3390/app15062904
Mehta, P. K., & Monteiro, P. J. M. (2014). Concrete: Microstructure, Properties, and Materials (4th ed.). McGraw-Hill Education. https://www.researchgate.net/publication/258848178_Concrete_Structure_Properties_and_Materials
Qu, B., Lin, S., & Huang, H. (2025). A modified fuzzy TOPSIS approach for the condition assessment of existing bridges. Nonlinear Engineering, 14(1). https://doi.org/10.1515/nleng-2025-0106
Rashidi-Nasab, A. R., & Elzarka, H. (2023). Optimizing machine learning algorithms for improving prediction of bridge deck deterioration: A case study of Ohio bridges. Buildings, 13(6), 1517. https://doi.org/10.3390/buildings13061517
Rogulj, K., Pamukovic, J. K., & Jajac, N. (2021). Knowledge-based fuzzy expert system to the condition assessment of historic road bridges. Applied Soft Computing, 11(3), 1021. https://doi.org/10.3390/app11031021
Ryall, M. (2009). Bridge Management (2nd ed.). CRC Press. https://doi.org/10.1201/b12866
Saltelli, A., Chan, K., & Scott, E. M. (2009). Sensitivity Analysis. John Wiley & Sons.
Wang, Y., Yeo, G. T., & Ng, A. K. Y. (2014). Choosing optimal bunkering ports for liner shipping companies: A hybrid fuzzy-Delphi-TOPSIS approach. Transport Policy, 35, 358-365. https://doi.org/10.1016/j.tranpol.2014.04.009
Wang, Y. M., & Elhag, T. M. S. (2006). Fuzzy TOPSIS method based on alpha level sets with an application to bridge risk assessment. Expert Systems with Applications, 31(2), 309-319. https://doi.org/10.1016/j.eswa.2005.09.040
Downloads
Published
Submitted
Revised
Accepted
Issue
Section
License
Copyright (c) 2026 Hossein Farshad (Author); Nader Abdoli Yazdi; Ehsan Eshtehardian (Author)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
