Evaluating and Predicting Deterioration of Bridges Using Machine Learning Applications
Publication: Structures Congress 2023
ABSTRACT
Condition of bridge infrastructure is critical to the operation of transportation networks. Out of more than 617,000 bridges across the US about 7.5% are considered to have structurally “poor” condition. The objective of this study is to develop a data-driven approach to evaluate conditions of small and medium span bridges and propose new prediction models based on the existing Federal Highway Administration bridge inspection data. Using Maryland’s more than 5,000 bridges, Structure Inventory and Appraisal (SI&A) and National Oceanic and Atmospheric Administration data from 2010 to 2021 were employed, and inconsistent or missing data were identified, cleaned, and processed. The processed data was used to carry out a preliminary analysis to identify the most influential variables on deteriorating a bridge. Several machine learning models were examined to find the most suitable prediction model with the highest accuracy for bridge deterioration. This can help decision-makers to accurately predict bridge condition and effectively allocate funds for bridge management.
Get full access to this article
View all available purchase options and get full access to this chapter.
REFERENCES
AASHTO. (June 2013). Transportation Asset Management Guide: A Foucs on Implementation. FHWA. Retrieved from https://www.fhwa.dot.gov/asseet/
Abduljabbar, R. a. (2019). Applications of Artificial Intelligence in Transport: An Overview. Sustainability, 11.
Abu-Tair, A., McParland, C., Lyness, J., & Nadjai, A. (March 2022). Predictive models of deterioration rates of bridges uisng the factor method based on historic inspection data. Proceedings of the 9th International Conference on Durability of Building Materials and Components (DBMC). Brisbane, Australia.
Adhikari, R. S., Moselhi, O., & Bagchi, A. (2014). Image-based retrieval of concrete crack properties for bridge inspection. Automation in Construction, Vol. 39, pp. 180–194.
Agatonovic-Kustrin, S. a. (2000). Basic concepts of artificial neural network (ANN) modeling and its application in pharmaceutical research. Journal of Pharmaceutical and Biomedical Analysis, 22(5), 717–727.
Agrawal, A. K., Kawaguchi, A., & Chen, Z. (2010). Deterioration rates of typcal bridge elements in New York. Journal of Bridge Engineering, Vol. 15(No. 4), pp. 419-429.
Ajay Kulkarni, F. A. (2020). Foundations of data imbalance and solutions for a data democracy. Data Democracy.
Al-Hussein, A. (2017). Estimating bridge deterioration age using artificial neural networks. The British University in Dubai. Dubai: Doctoral Dissertation. Retrieved from https://bspace.buid.ac.ae/handle/1234/1128
Al-Hussein, A. (2017). Estimating bridge deterioration age using arificial neural networks. Dubai: Doctoral Dissertation, The British University in Dubai.
ASCE. (2021). Infrastructure Report Card. ASCE. Retrieved from https://infrastructurereportcard.org/cat-item/bridges/https://www.fhwa.dot.gove/asset/
Busa, G., Ben-Akiva, M., & Buyukozturk, O. (1985). Medeling Concrete Deck Deterioration. Massachusetts Institute of Technology, Department of Civil Engineering, Cambridge, MA, USA.
Cook, W. (2014). Bridge failure rates, consequences, and predictive trends. Doctoral Dissertation.
Das, S., Dey, A., Pal, A., & Roy, N. (2015). Applications of Artificial Intelligence in Machine Learning: Review and Prospect. International Journal of Computer Applications, 115.
FHWA (1996). Recording and Coding Guide for the Structure Inventory and Appraisal of the Nation's Bridges. FHWA. Retrieved from https://www.fhwa.dot.gov/bridge/mtguide.pdf
Hodhod, O. A., & Ahmed, H. I. (2013). Developing an artificial neural network model toevaluate chloride diffusivity in high performance concrete. HBRC Journal, Vol. 9(No. 1), pp. 15-21.
Huang, Y.-H. (2010). Artificial neural network model of bridge deterioration. Journal of Performance of Constructed Facilities, Vol. 24(No. 6), pp. 597-602.
Hyman, W., Hughes, D., & Dobson, T. (1983). The least cost mix of birdge replacement and repair work on Winsconsin's state highways over time-a computer simulation. Madison, WI, USA: WisDOT.
Jeong, Y., Kim, W., & Lee, I. (2017). Bridge service life estimation considering inspection reliabilty. KSCE Journal of Civil Engineering, Vol. 15(No. 4), pp. 1882-1893.
Kim, J., Gucunski, N., & Dinh, K. (2019). Deterioration and predictive condition modeling of concrete bridge decks based on data from periodic NDE surveys. Journal of Infrastructure Methodologys, Vol. 25(No. 2).
Korstanje, J. (2021). The F1 score. Retrieved from Towards Data Science : https://towardsdatascience.com/the-f1-score-bec2bbc38aa6
Kulkarni, A., Chong, D., & Bataresh, F. (2020). Foundations of data imbalance and solutions for a data democracy. In Foundations of data imbalance and solutions for a data democracy.
Kwok, K. Y. (2009). Assessment of bridge inspection and maintenance in the United States. Doctoral Dissertation.
Lee, L. S. (2011). Rehabilitation and service life estimation of bridge superstructures. Cambridge, England: Woodhead Publishing.
Li, L., Sun, L., & Ning, G. (2014). Deterioration prediction of urban bridges on network level uisng Markov-chain model. Mathematical Problems in Engineering, Vol. 2014.
Lim, S., & Chi, S. (2019). Bridge damage prediction using deep neural network. Reston, VA: ASCE.
Mauch, M., & Madanat, S. (2001). Semiprametric hazard rate models of reinforced concrete bridge deck deterioration. Journal of Infrastructure Systems, Vol. 7(No. 2), pp. 49-57.
McDonald, C. (2014, February 1). A bridge too far: Repairing America's aging infrastructure. Risk Mangement Magazine. Retrieved from http://www.rmmagazine.com
Miguel-Hurtado, O. G. (2016). Comparing Machine Learning Classifiers and Linear/Logistic Regression to Explore the Relationship between Hand Dimensions and Demographic Characteristics. PLOS ONE, 11(11).
Mikami, I., Tanaka, S., & Kurachi, A. (1994). Expert system with learning ability for retrofitting steel bridges. Journal of Computing in Civil Engineering, Vol. 8(No. 1), pp. 88-102.
Minnesota DOT. (2019). Transporation Asset Management Plan. Retrieved from https://www.dot.state.mn.us/assetmanagement/pdf/tamp/tamp.pdf
Mozaffarian, D. e. (2015). Heart disease and stroke statistics—2015 update: a report from the American Heart Association. Heart disease and stroke statistics, 131(4), 29–322.
New Yort State DOT. (2019). Transportation Asset Management Plan. Retrieved from https://www.dot.ny.gov/programs/capital-plan/repository/Final%20TAMP%20June2028%202019.pdf
New Zealand Transportation Agency. (2011). State Highway Asset Management Plan 2012-15. Retrieved from https://tamptemplate.org/wp-content/uploads/tamps/009_newzealand.pdf
Ng, A., & Jordan, M. (2002). On Discriminative vs. Generative Classifiers: A comparison of logistic regression and naive Bayes. Adv. Neural Inf. Process. Sys, 2.
Nishadi, A. S. (2019). Predicting Heart Diseases in Logistic Regression of Machine Learning Algorithms by Python Jupyterlab. International Journal of Advance Research and Publication, 3(8), 69–74.
Pan, N.-F., Lin, T.-C., & Pan, N.-H. (2009). Estimating bridge performance based on a matrix-driven fuzzy linear regression model. Automation in Construction, Vol. 18(No. 5), pp. 578-586.
Park, H. A. (2013). An introduction to logistic regression: from basic concepts to interpretation with particular attention to nursing domain. Journal of Korean Academy of Nursing, 43(2), 154–164.
Rangan, K. (2021, June 24). What is Asset Management? ITR's necessary for business success. Retrieved from https://www.fhwa.dot.gov/bride/nbis/pubs/nhi12049.pdf
Sabellano, R., & Shokouhian, M. (July 2022). Development of a decision-making tool. Toronto, Ontario, Canada.
Sathya, R., & Abraham, A. (2013). Comparison of Supervised and Unsupervised Learning Algorithms for Pattern Classification. Advanced Research in Artificial Intelligence(IJARAI), 2(2).
Sobanjo, J. O. (1997). A neural network approach to medeling bridge deterioration. Reston, VA: ASCE.
Strecht, P., Cruz, L., Soares, C., Mendes-Moreira, J., & Abreu, R. (2015). A Comparative Study of Classification and Regression Algorithms for Modelling Students' Academic Performance. International Conference on Educational Data Mining (EDM). Madrid, Spain.
Transportation Research Board. (2009). NCHRP Report 632 - An Asset-Management Framework for the Interstate System. TRB. Retrieved from file:///C:/Usersrsabellano/Downloads/14233.pdf
TRB, T. P. (2021). Renewing the National Commitment to the Interstate Highway System: A Foundation for the Future. Washington, DC: Consensus Study report.
USDOT FHWA. (2017, May 15). Asset Management. Retrieved from https://www.fhwa.dot.gov/asset/
Wellalage, N. W., Zhang, T., & Dwight, R. (2015). Calibrating Markov chain-based deterioration models for predicting future conditions of railway bridge elements. Journal of Bridge Engineering, Vol. 20(No. 2).
WYOMING DOT. (2018). Transportation Asset Management Plan. Retrieved from https://www.dot.state.wy.us/files/live/sites/wydot/files/shared/Planning/Transportation-Plans/TAMP_WYDOT%20SubmissionPublic_FINAL_2.pdf
Information & Authors
Information
Published In
Structures Congress 2023
Pages: 150 - 163
History
Published online: May 1, 2023
ASCE Technical Topics:
- Architectural engineering
- Artificial intelligence and machine learning
- Bridge engineering
- Bridge management
- Bridge tests
- Bridges
- Bridges (by type)
- Building management
- Computer programming
- Computing in civil engineering
- Deterioration
- Engineering fundamentals
- Field tests
- Highway bridges
- Maintenance and operation
- Materials characterization
- Materials engineering
- Model accuracy
- Models (by type)
- Structural engineering
- Tests (by type)
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.