Feature Selection and Deep Learning for Deterioration Prediction of the Bridges
Publication: Journal of Performance of Constructed Facilities
Volume 35, Issue 6
Abstract
Bridge deterioration is inevitable in service, and the inspection and maintenance of bridges are needed to ensure structural integrity. To make cost-effective inspection plans, bridge management departments need degradation models to predict future condition ratings of bridges. Although there have been studies on bridge degradation, the input features of models are selected mostly based on engineering experience, and no effective method has been proposed. Meanwhile, most models based on machine learning (ML) and deep learning (DL) only predict the degradation of bridges in a single year and cannot cover a complete inspection cycle (usually 2 years), providing limited decision support for the transportation departments. Besides, more accurate models are needed to predict the degradation trend of bridges. In response to these problems, an improved ReliefF algorithm is proposed to select features of bridges in the paper. Meanwhile, a new degradation model combining recurrent neural network (RNN) and convolutional neural network (CNN) is established. Historical data of bridges in the US state of Texas from 1992 to 2019 are employed to verify the proposed methods. The result shows that the improved ReliefF algorithm selects the appropriate feature set as the input of the prediction model, and the model accurately predicts the future condition ratings of bridges in the next 3–4 years. The research is beneficial to infrastructure management departments in allocating bridge inspection and maintenance resources reasonably.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some or all data, models, or code that support the findings of this study are available from the corresponding author upon reasonable request.
Acknowledgments
The author would like to acknowledge members of the Key Laboratory of Coast Civil Structure Safety (Ministry of Education) and the research group of bridges at Tianjin University for their endless support. The paper uses the NBI data from the Federal Highway Administration (FHWA) of the US Department of Transportation. The authors greatly appreciate the engineering professionals of FHWA who collected bridge information. This work presented here was supported by the National Key R&D Program of China (2018YFB1600300 and 2018YFB1600301), the National Science Foundation of China (52078333), and the Tianjin Transportation Science and Technology Development Plan Project (G2018-29). Any opinions, findings, and conclusions, or recommendations expressed in this paper are those of the authors and do not necessarily reflect those of the sponsor.
References
Barros, R. C., M. P. Basgalupp, A. C. P. L. F. d. Carvalho, and A. A. Freitas. 2012. “A hyper-heuristic evolutionarya algorithm for automatically designing decision-tree algorithms.” In Proc., GECCO 2012 Workshop on Genetic and Evolutionary Computation, 1237–1244. New York: Association for Computing Machinery.
Bolukbasi, M., J. Mohammadi, and D. Arditi. 2004. “Estimating the future condition of highway bridge components using national bridge inventory data.” Pract. Periodical Struct. Des. Constr. 9 (1): 16–25. https://doi.org/10.1061/(ASCE)1084-0680(2004)9:1(16).
Cesare, M. A., C. Santamarina, C. Turkstra, and E. H. Vanmarcke. 1992. “Modeling bridge deterioration with Markov chains.” J. Transp. Eng. 118 (6): 820–833. https://doi.org/10.1061/(ASCE)0733-947X(1992)118:6(820).
Creary, P. A., and F. C. Fang. 2014. “Forecasting long-term bridge deterioration conditions using artificial intelligence techniques.” Int. J. Intell. Syst. Tech. Appl. 13 (4): 280–293. https://doi.org/10.1504/IJISTA.2014.068830.
Dorafshan, S., R. J. Thomas, and M. Maguire. 2018. “Comparison of deep convolutional neural networks and edge detectors for image-based crack detection in concrete.” Constr. Build. Mater. 186 (Oct): 1031–1045. https://doi.org/10.1016/j.conbuildmat.2018.08.011.
FHWA (Federal Highway Administration). 1995. Recording and coding guide for the structure inventory and appraisal of the nation’s bridges. FHWA-PD-96-01. Washington, DC: FHWA.
FHWA (Federal Highway Administration). 2012. Bridge inspector’s reference manual (BIRM). Washington, DC: FHWA.
FHWA (Federal Highway Administration). 2017. Assessing pavement condition for the National Highway Performance Program and bridge condition for the National Highway Performance Program, 5886–5970. Washington, DC: FHWA.
Frangopol, D., M.-J. Kallen, and J. M. V. Noortwijk. 2004. “Probabilistic models for life-cycle performance of deteriorating structures: review and future directions.” Prog. Struct. Eng. Mater. 6 (4): 197–212. https://doi.org/10.1002/pse.180.
Guyon, I., and A. Elisseeff. 2003. “An introduction to variable and feature selection.” J. Mach. Learn. Res. 3 (Mar): 1157–1182.
He, K., X. Zhang, S. Ren, and J. Sun. 2016. “Deep residual learning for image recognition.” In Proc., CVPR 2016 Workshop on Computer Vision and Pattern Recognition, 770–778. New York: IEEE.
Huang, Y. 2010. “Artificial neural network model of bridge deterioration.” J. Perform. Constr. Facil. 24 (6): 597–602. https://doi.org/10.1061/(ASCE)CF.1943-5509.0000124.
Ilbeigi, M., and M. E. Meimand. 2020. “Statistical forecasting of bridge deterioration conditions.” J. Perform. Constr. Facil. 34 (1): 04019104. https://doi.org/10.1061/(ASCE)CF.1943-5509.0001347.
Kawamura, K., A. Miyamoto, M. F. Dan, and K. Ryuichi. 2003. “Performance evaluation of concrete slabs of existing bridges using neural networks.” Eng. Struct. 25 (12): 1455–1477. https://doi.org/10.1016/S0141-0296(03)00112-3.
Kim, Y. J., and D. K. Yoon. 2010. “Identifying critical sources of bridge deterioration in cold regions through the constructed bridges in North Dakota.” J. Bridge Eng. 15 (5): 542–552. https://doi.org/10.1061/(ASCE)BE.1943-5592.0000087.
Kingma, D. P., and L. J. Ba. 2015. “Adam: A method for stochastic optimization.” Preprint, submitted December 22, 2014. http://arxiv.org/abs/1412.
Lei, T., Y. Zhang, S. I. Wang, H. Dai, and Y. O. Artzi. 2018. “Simple recurrent units for highly parallelizable recurrence.” In Proc., EMNLP 2018 Workshop on Empirical Methods in Natural Language, 4470–4481. Brussels, Belgium: Association for Computational Linguistics.
Liang, X. 2018. “Image-based post-disaster inspection of reinforced concrete bridge systems using deep learning with Bayesian optimization” Comput-Aided. Civ. Inf. 34 (5): 415–430. https://doi.org/10.1111/mice.12425.
Liu, H., and Y. Zhang. 2020. “Bridge condition rating data modeling using deep learning algorithm.” Struct. Infrastruct. Eng. 16 (10): 1447–1460. https://doi.org/10.1080/15732479.2020.1712610.
Liu, K., and N. El-Gohary. 2020. “Fusing data extracted from bridge inspection reports for enhanced data-driven bridge deterioration prediction: A hybrid data fusion method.” J. Comput. Civ. Eng. 34 (6): 04020047. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000921.
Martinez, P., E. Mohamed, O. Mohsen, and Y. Mohamed. 2020. “Comparative study of data mining models for prediction of bridge future conditions.” J. Perform. Constr. Facil. 34 (1): 04019108. https://doi.org/10.1061/(ASCE)CF.1943-5509.0001395.
Morcous, G. 2006. “Performance prediction of bridge deck systems using Markov chains.” J. Perform. Constr. Facil. 20 (2): 146–155. https://doi.org/10.1061/(ASCE)0887-3828(2006)20:2(146).
Nasrollahi, M., and G. Washer. 2015. “Estimating inspection intervals for bridges based on statistical analysis of national bridge inventory data.” J. Bridge Eng. 20 (9): 04014104. https://doi.org/10.1061/(ASCE)BE.1943-5592.0000710.
Palma-Mendoza, R. J., D. Rodriguez, and L. De-Marcos. 2018. “Distributed relief based feature selection in Spark.” Knowl. Inf. Syst. 57 (1): 1–20. https://doi.org/10.1007/s10115-017-1145-y.
Rafiei, M. H., and H. Adeli. 2018. “A novel unsupervised deep learning model for global and local health condition assessment of structures.” Eng. Struct. 156 (Feb): 598–607. https://doi.org/10.1016/j.engstruct.2017.10.070.
Ranjith, S., S. Setunge, R. Gravina, and S. Venkatesan. 2013. “Deterioration prediction of timber bridge elements using the Markov chain.” J. Perform. Constr. Facil. 27 (3): 319–325. https://doi.org/10.1061/(ASCE)CF.1943-5509.0000311.
Reshef, D. N., Y. A. Reshef, H. K. Finucane, S. R. Grossman, G. McVean, P. J. Turnbaugh, E. S. Lander, M. Mitzenmacher, and P. C. Sabeti. 2011. “Detecting novel associations in large data sets.” Science 334 (6062): 1518–1524. https://doi.org/10.1126/science.1205438.
Shi, X., Z. Chen, H. Wang, D.-Y. Yeung, W.-K. Wong, and W.-C. Woo. 2015. “Convolutional LSTM network: A machine learning approach for precipitation nowcasting.” In Proc., NIPS 2015 Workshop on Neural Information Processing Systems, 802–810. Cambridge, MA: MIT Press.
Shibani, S., T. Dimitris, I. Andrew, and A. Madry. 2018. “How does batch normalization help optimization?” In Proc., 32nd Int. Conf. Neural Information Processing Systems, 2483–2493. Cambridge, MA: MIT Press.
Song, Y., W. Si, F. Dai, and G. Yang. 2020. “Weighted RELIEFF with threshold constraints of feature selection for imbalanced data classification.” Concurr. Comput. 32 (14): e5691. https://doi.org/10.1002/cpe.5691.
Spolaor, N., E. A. Cherman, M. C. Monard, and H. D. Lee. 2013. “ReliefF for multi-label feature selection.” In Proc., BRACIS 2013 Brazilian Conf. on Intelligent Systems, 6–11. New York: IEEE.
Srivastava, N., G. Hinton, A. Krizhevsky, and I. Sutskever. 2014. “Dropout: A simple way to prevent neural networks from overfitting.” J. Mach. Learn. Res. 15 (1): 1929–1958.
USDOT. 2017. “Transportation performance management: Pavement and bridge condition performance measures final rule.” Accessed January 15, 2021. https://www.fhwa.dot.gov/tpm/rule.cfm.
USDOT. 2019. “FHWA: National bridge inventory.” Accessed January 15, 2021. https://www.fhwa.dot.gov/bridge/nbi.cfm.
Wang, Y., L. Jiang, M.-H. Yang, L.-J. Li, M. Long, and L. Fei-Fei. 2019. “Eidetic 3D LSTM: A model for video prediction and beyond.” In Proc., ICLR 2019 Workshop on Learning Representations. London: DeepMand.
Wang, Y., M. Long, J. Wang, Z. Gao, and P. S. Yu. 2017. “PredRNN: Recurrent neural networks for predictive learning using spatiotemporal LSTMs.” In Proc., NIPS 2017 Workshop on Neural Information Processing Systems, 879–888. Cambridge, MA: MIT Press.
Washer, G., R. Connor, M. Nasrollahi, and J. Provines. 2016. “New framework for risk-based inspection of highway bridges.” J. Bridge Eng. 21 (4): 04015077.04015071–04015077. 04015078. https://doi.org/10.1061/(ASCE)BE.1943-5592.0000818.
Yu, B., H. Yin, and Z. Zhu. 2018. “Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting.” In Proc., IJCAI 2017 Workshop on Artificial Intelligence, 3634–3640. San Francisco: Margan Kaufmann.
Zhu, J., C. Zhang, H. Qi, and Z. Lu. 2019. “Vision-based defects detection for bridges using transfer learning and convolutional neural networks.” Struct. Infrastruct. Eng. 16 (7): 1037–1049.
Information & Authors
Information
Published In
Journal of Performance of Constructed Facilities
Volume 35 • Issue 6 • December 2021
Copyright
© 2021 American Society of Civil Engineers.
History
Received: Apr 19, 2021
Accepted: Jul 8, 2021
Published online: Aug 30, 2021
Published in print: Dec 1, 2021
Discussion open until: Jan 30, 2022
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.
Cited by
- Mohammadreza Mahmoudkelayeh, Behnam Adhami, Behzad Saeedi Razavi, Continuous Health Assessment of Bridges under Sudden Environmental Variability by Local Unsupervised Learning, Journal of Performance of Constructed Facilities, 10.1061/JPCFEV.CFENG-4323, 38, 5, (2024).
- Yoon-Soo Shin, Junhee Kim, Sensor Data Reconstruction for Dynamic Responses of Structures Using External Feedback of Recurrent Neural Network, Sensors, 10.3390/s23052737, 23, 5, (2737), (2023).
- Xi Hu, Kaijian Liu, Structural Deterioration Knowledge Ontology towards Physics-Informed Machine Learning for Enhanced Bridge Deterioration Prediction, Journal of Computing in Civil Engineering, 10.1061/(ASCE)CP.1943-5487.0001066, 37, 1, (2023).
- Yanlei Wang, Jinsong Zhu, Yongbin Guo, Cong Wang, Early shrinkage experiment of concrete and the development law of its temperature and humidity field in natural environment, Journal of Building Engineering, 10.1016/j.jobe.2022.105528, 63, (105528), (2023).
- Renda Zhao, Kaifeng Zheng, Xing Wei, Hongyu Jia, Xiaozhen Li, Qinghua Zhang, Guoji Xu, Yulin Zhan, Ruili Shen, Fang Zhang, Qianhui Pu, Hongye Gou, Chuanjin Yu, State-of-the-art and annual progress of bridge engineering in 2021, Advances in Bridge Engineering, 10.1186/s43251-022-00070-1, 3, 1, (2022).
- Gaowei Xu, Fae Azhari, Data-driven optimization of repair schemes and inspection intervals for highway bridges, Reliability Engineering & System Safety, 10.1016/j.ress.2022.108779, 228, (108779), (2022).
- Jingliu Lai, Hongmei Chen, Weiyi Li, Tianrui Li, Jihong Wan, Semi-supervised feature selection via adaptive structure learning and constrained graph learning, Knowledge-Based Systems, 10.1016/j.knosys.2022.109243, 251, (109243), (2022).
- Xiaoming Lei, Ye Xia, Seyedmilad Komarizadehasl, Limin Sun, Condition level deteriorations modeling of RC beam bridges with U-Net convolutional neural networks, Structures, 10.1016/j.istruc.2022.06.013, 42, (333-342), (2022).
- Xiaoming Lei, Ye Xia, You Dong, Limin Sun, Multi-level time-variant vulnerability assessment of deteriorating bridge networks with structural condition records, Engineering Structures, 10.1016/j.engstruct.2022.114581, 266, (114581), (2022).