Bridge Infrastructure Management System: Autoencoder Approach for Predicting Bridge Condition Ratings
Publication: Journal of Infrastructure Systems
Volume 29, Issue 1
Abstract
Being an essential component of our economy, bridges play a vital role in facilitating transportation of people and goods all over the world. Bridge infrastructure systems help in developing an effective way to monitor and protect structures in all aspects. However, the bridges are exposed to various kinds of damages due to aging, heavy load of traffic, quality of construction, and so on. Hence, determining the condition of such bridges through a proper infrastructure management system is important for understanding the potential loss in the longevity of the structures. This research paper presents the development and evaluation of an autoencoder-random forest (AE-RF) model to predict the condition rating of bridges using the National Bridge Inventory (NBI) database. To demonstrate the proposed model, a case study using bridges present in the US state of Florida has been performed using historical NBI data (2011–2020). Through this research, it was identified that when one of the deep learning models, named autoencoder, is combined with random forest (RF), it results in an efficient model for determining the condition ratings of the bridge components with fewer input parameters. The developed model was about 90% accurate in predicting the bridge’s deck condition by using other rating values as input variables and about 79% accurate without the use of any other rating factors, thereby addressing the existing research gap in determining the condition rating without the use of historic condition rating. On the other hand, the model was 78% and 77% accurate in determining the condition ratings for superstructure and substructure without using historic ratings and evaluation parameters. Hence, the proposed model would be more reliable in the evaluation of condition of existing bridges across the nation.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
The developed code and generated models during the study are proprietary or confidential in nature and may only be provided with restrictions. The NBI data set used is publicly available on Federal Highway Administration (FHWA) website and can be accessed using https://www.fhwa.dot.gov/bridge/nbi/ascii.cfm.
Acknowledgments
The authors would like to thank the Federal Highway Administration (FHWA) for providing the periodic bridge inspection records from 1992 to 2021, in the National Bridge Inventory (NBI) database. These bridge data are available for free on their website along with the coding guide. In addition, the facilities and support provided by the Department of Civil, Environmental, and Geomatics Engineering at Florida Atlantic University to carry out the research is much appreciable.
References
ASCE. 2017. “ASCE’s 2021 infrastructure report card.” Accessed March 3, 2021. https://www.infrastructurereportcard.org/.
Assaad, R., and I. H. El-Adaway. 2020. “Bridge infrastructure asset management system: Comparative computational machine learning approach for evaluating and predicting deck deterioration conditions.” J. Infrastruct. Syst. 26 (3): 04020032. https://doi.org/10.1061/(ASCE)IS.1943-555X.0000572.
Bergstra, J., D. Yamins, and D. D. Cox. 2013. “Hyperopt: A python library for optimizing the hyperparameters of machine learning algorithms.” In Vol. 13 of Proc., 12th Python in Science Conf., 20. Austin, TX: SciPy.
Cao, Y., B. Ashuri, and M. Baek. 2018. “Prediction of unit price bids of resurfacing highway projects through ensemble machine learning.” J. Comput. Civ. Eng. 32 (5): 04018043. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000788.
Christodoulou, A., and P. Christidis. 2020. “Bridges across borders: A clustering approach to support EU regional policy.” J. Transp. Geogr. 83 (Feb): 102666. https://doi.org/10.1016/j.jtrangeo.2020.102666.
Coffer, B., M. Kubacki, Y. Wen, T. Zhang, C. A. Barajas, and M. K. Gobbert. 2021. “Machine learning with feature importance analysis for tornado prediction from environmental sounding data.” Proc. Appl. Math. Mech. 20 (1): e202000112. https://doi.org/10.1002/pamm.202000112.
Cook, W., and P. J. Barr. 2017. “Observations and trends among collapsed bridges in New York state.” J. Perform. Constr. Facil. 31 (4): 04017011. https://doi.org/10.1061/(ASCE)CF.1943-5509.0000996.
Datacamp. 2022. “Sklearn random forest classifiers in Python tutorial.” Accessed April 12, 2021. https://www.datacamp.com/community/tutorials/random-forests-classifier-python/.
Fereshtehnejad, E., A. Shafieezadeh, and J. Hur. 2022. “Optimal budget allocation for bridge portfolios with element-level inspection data: A constrained integer linear programming formulation.” Struct. Infrastruct. Eng. 18 (6): 864–878. https://doi.org/10.1080/15732479.2021.1875489.
FHWA (Federal Highway Administration). 1995. “Recording and coding guide for the structure inventory and appraisal of the Nation'S bridges.” Accessed February 14, 2021. https://www.fhwa.dot.gov/bridge/mtguide.pdf.
FHWA (Federal Highway Administration). 2020. “National bridge inventory.” Accessed May 1, 2021. https://www.fhwa.dot.gov/bridge/nbi/ascii.cfm.
FHWA (Federal Highway Administration). 2021a. “Download NBI ASCII files—National bridge inventory—Bridge inspection—Safety—Bridges & structures.” Accessed May 1, 2021. https://www.fhwa.dot.gov/bridge/nbi/ascii.cfm.
FHWA (Federal Highway Administration). 2021b. “National bridge inventory—Bridge inspection—Safety—Bridges & structures.” Accessed May 1, 2021. https://www.fhwa.dot.gov/bridge/nbi.cfm.
Frangopol, D. M., J. S. Kong, and E. S. Gharaibeh. 2001. “Reliability-based life-cycle management of highway bridges.” J. Comput. Civ. Eng. 15 (1): 27–34. https://doi.org/10.1061/(ASCE)0887-3801(2001)15:1(27).
Goutte, C., and E. Gaussier. 2005. “A probabilistic interpretation of precision, recall and -score, with implication for evaluation.” In Proc., European Conf. on Information Retrieval, Lecture Notes in Computer Science, 345–359. Berlin: Springer. https://doi.org/10.1007/978-3-540-31865-1_25.
Huang, Y.-H. 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.
Jordan, J. 2018. “Introduction to autoencoders.” Accessed June 6, 2021. https://www.jeremyjordan.me/autoencoders/.
Joseph, D., A. Lai, S. Silverstein, R. Ramchandran, and E. A. Bernal. 2021. Using machine learning to classify Schizophrenia based on retinal images. New York: Cold Spring Harbor Laboratory. https://doi.org/10.1101/2021.04.04.21254893.
Kanstrén, T. 2020. “A look at precision, recall, and -score.” Medium. Accessed June 12, 2021. https://towardsdatascience.com/a-look-at-precision-recall-and-f1-score-36b5fd0dd3ec.
Kaushik, S. 2016. “Introduction to feature selection methods with an example (or how to select the right variables?).” Accessed May 2, 2021. https://www.analyticsvidhya.com/blog/2016/12/introduction-to-feature-selection-methods-with-an-example-or-how-to-select-the-right-variables/.
Kosgodagan-Dalla Torre, A., T. G. Yeung, O. Morales-Nápoles, B. Castanier, J. Maljaars, and W. Courage. 2017. “A two-dimension dynamic Bayesian network for large-scale degradation modeling with an application to a bridges network.” Comput.-Aided Civ. Infrastruct. Eng. 32 (8): 641–656. https://doi.org/10.1111/mice.12286.
Kumar, R., J. L. Matias de Oliveira, A. Schultz, and M. Marasteanu. 2018. “Remaining service life asset measure, Phase 1.” Accessed June 21, 2021. https://conservancy.umn.edu/handle/11299/200642.
Lee, J., J. B. Son, H. Guan, M. Blumenstein, and Y.-C. Loo. 2009. “Generating complete historical condition ratings using a new set of non-bridge factors for Queensland bridges in the backward prediction model (BPM).” In Proc., 7th Austroads Bridge Conf., 2009. Washington, DC: Transport Research Board.
Lee, J. H., H. Guan, Y. C. Loo, M. Blumenstein, and X. P. Wang. 2011. “Modelling long-term bridge deterioration at structural member level using artificial intelligence techniques.” Appl. Mech. Mater. 99–100 (Sep): 444–453. https://doi.org/10.4028/www.scientific.net/AMM.99-100.444.
Lichtenstein, A. G. 1993. “The silver bridge collapse recounted.” J. Perform. Constr. Facil. 7 (4): 249–261. https://doi.org/10.1061/(ASCE)0887-3828(1993)7:4(249).
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.
Madanat, S., R. Mishalani, and W. H. Wan Ibrahim. 1995. “Estimation of infrastructure transition probabilities from condition rating data.” J. Infrastruct. Syst. 1 (2): 120–125. https://doi.org/10.1061/(ASCE)1076-0342(1995)1:2(120).
Morcous, G., H. Rivard, and A. M. Hanna. 2002. “Modeling bridge deterioration using case-based reasoning.” J. Infrastruct. Syst. 8 (3): 86–95. https://doi.org/10.1061/(ASCE)1076-0342(2002)8:3(86).
Nargesian, F., H. Samulowitz, U. Khurana, E. B. Khalil, and D. Turaga. 2017. “Learning feature engineering for classification.” In Proc., 26th Int. Joint Conf. on Artificial Intelligence. Red Hook, NY: Curran Associates. https://doi.org/10.24963/ijcai.2017/352.
Pedregosa, F., et al. 2011. “Scikit-learn: Machine learning in Python.” J. Mach. Learn. Res. 12 (Nov): 2825–2830.
Rafiq, M. I., M. K. Chryssanthopoulos, and S. Sathananthan. 2014. “Bridge condition modelling and prediction using dynamic Bayesian belief networks.” Struct. Infrastruct. Eng. 11 (1): 38–50. https://doi.org/10.1080/15732479.2013.879319.
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.
Scikit-Learn. 2011. “Metrics and scoring: Quantifying the quality of predictions—Scikit-learn 0.22.1 documentation.” Accessed June 17, 2021. https://scikit-learn.org/stable/modules/model_evaluation.html.
Scikitlearn.org. 2022. “Random forest classifier model.” Accessed February 6, 2022. https://scikitlearn.org/stable/modules/generated/sklearn.ensemble.RandomForestClassifier.html.
Sewani, H., and R. Kashef. 2020. “An autoencoder-based deep learning classifier for efficient diagnosis of autism.” Children 7 (10): 182. https://doi.org/10.3390/children7100182.
Sokolova, M., N. Japkowicz, and S. Szpakowicz. 2006. “Beyond accuracy, -score and ROC: A family of discriminant measures for performance evaluation.” In Proc., Australasian Joint Conf. on Artificial Intelligence, Lecture Notes in Computer Science, 1015–1021. Berlin: Springer. https://doi.org/10.1007/11941439_114.
Straub, D. 2009. “Stochastic modeling of deterioration processes through dynamic Bayesian networks.” J. Eng. Mech. 135 (10): 1089–1099. https://doi.org/10.1061/(ASCE)em.1943-7889.0000024.
Veshosky, D., C. R. Beidleman, G. W. Buetow, and M. Demir. 1994. “Comparative analysis of bridge superstructure deterioration.” J. Struct. Eng. 120 (7): 2123–2136. https://doi.org/10.1061/(ASCE)0733-9445(1994)120:7(2123).
Wang, Y., H. Yao, and S. Zhao. 2016. “Auto-encoder based dimensionality reduction.” Neurocomputing 184 (Apr): 232–242. https://doi.org/10.1016/j.neucom.2015.08.104.
Yang, D. Y., and D. M. Frangopol. 2018. “Probabilistic optimization framework for inspection/repair planning of fatigue-critical details using dynamic Bayesian networks.” Comput. Struct. 198 (Mar): 40–50. https://doi.org/10.1016/j.compstruc.2018.01.006.
Information & Authors
Information
Published In
Journal of Infrastructure Systems
Volume 29 • Issue 1 • March 2023
Copyright
© 2022 American Society of Civil Engineers.
History
Received: Nov 30, 2021
Accepted: Sep 14, 2022
Published online: Nov 12, 2022
Published in print: Mar 1, 2023
Discussion open until: Apr 12, 2023
ASCE Technical Topics:
- Architectural engineering
- Bridge components
- Bridge engineering
- Bridge management
- Building management
- Business management
- Ecosystems
- Engineering fundamentals
- Environmental engineering
- Forests
- Infrastructure
- Maintenance and operation
- Management methods
- Model accuracy
- Models (by type)
- Practice and Profession
- Ratings
- Structural engineering
- Systems engineering
- Systems management
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.