Predicting Culvert Deterioration Using Physical and Environmental Time-Independent Variables
Publication: Journal of Pipeline Systems Engineering and Practice
Volume 10, Issue 4
Abstract
Given a vast inventory of culverts with different physical and environmental characteristics, the task of condition assessment can become difficult or impossible. Using a database of approximately 8,000 culverts in South Carolina with varying sizes, types, and configurations, a model was produced to predict the condition of these culverts. This model combined only the physical culvert information given in the database with mapped environmental characteristics including historical temperature, precipitation, pH, and estimated runoff coefficient. The resulting model used the combination of inputs that produced the model with the best performance measures, primarily the area under a receiver operating characteristic curve. A separate model was created for each of the 6 culvert types commonly found in South Carolina and the 10 condition categories given to each culvert in the database: cracking, separation, corrosion, alignment, scour, sedimentation, vegetation, erosion, blockage, and piping. Both a logistic regression model and an artificial neural network model were used to combine the input variables into a prediction of the desired output variables. The models produced were shown to have a coefficient of determination of between 0.25 for poorly correlated models and 0.80 for better correlated models when comparing the predicted culvert score with the actual culvert score. With the ability to predict culvert health without inspection or any idea of the age of the culvert, the culverts in need of assessment can be prioritized without comprehensive inspections or more detailed information about the culverts.
Get full access to this article
View all available purchase options and get full access to this article.
Acknowledgments
This project was sponsored by the South Carolina Department of Transportation (Grant No. SPR 718). The authors would like to thank the SCDOT for their support and guidance throughout the project.
References
Aimin, Y., L. Jintao, J. Bohai, and M. Haifeng. 2011. “Study on damage identification for a simply supported reinforced concrete beam based on the LMBP neural network.” In Design, Construction, Rehabilitation, and Maintenance of Bridges, Geotechnical Special Publication 219. Reston, VA: ASCE. https://doi.org/10.1061/47630(409)9.
Al-Gburi, M. A., J.-E. Jonasson, and M. Nilsson. 2015. “Using artificial neural networks to predict the restraint in concrete culverts at early age.” Struct. Eng. Int. 25 (3): 258–265.
Ariaratnam, S. T., A. El-Assaly, and Y. Yang. 2001. “Assessment of infrastructure inspection needs using logistic models.” J. Infrastruct. Syst. 7 (4): 160–165. https://doi.org/10.1061/(ASCE)1076-0342(2001)7:4(160).
Colorado Urrea, G. J. 2014. “Service life of concrete and metal culverts located in Ohio Department of Transportation Districts 9 and 10.” Ph.D. dissertation, Civil Engineering Dept., Ohio Univ.
Fawcett, T. 2006. “An introduction to ROC analysis.” Patt. Recognit. Lett. 27 (8): 861–874. https://doi.org/10.1016/j.patrec.2005.10.010.
Gassman, S. L., I. Sasanakul, C. E. Pierce, E. Gheibi, R. Starcher, W. Ovalle, and M. Rahman. 2017. “Failures of pipe culverts from a 1000-year rainfall event in South Carolina.” In Geotechnical Frontiers 2017: Transportation Facilities, Structures, and Site Investigation, Geotechnical Special Publication 277, edited by T. L. Brandon and R. J. Valentine. Reston, VA: ASCE. https://doi.org/10.1061/9780784480441.013.
Gnana Sheela, K., and S. N. Deepa. 2013. “Review on methods to fix number of hidden neurons in neural networks.” Math. Prob. Eng. 2013: 1–11. https://doi.org/10.1155/2013/425740.
Jin, H. 2016. “Decision-making guidance for selecting culvert renewal techniques.” Ph.D. dissertation, Clemson Univ. https://tigerprints.clemson.edu/all_dissertations/1726.
Marquardt, D. W. 1963. “An algorithm for least-squares estimation of nonlinear parameters.” J. Soc. Ind. Appl. Math. 11 (2): 431–441.
Meegoda, J. N., and T. M. Juliano. 2009. Corrugated steel culvert pipe deterioration. Trenton, NJ: New Jersey DOT.
Najafi, M., and G. Kulandaivel. 2005. “Pipeline condition prediction using neural network models.” In Pipelines 2005: Optimizing Pipeline Design, Operations, and Maintenance in Today’s Economy. Reston, VA: ASCE. https://doi.org/10.1061/40800(180)61.
Salem, O., B. Salman, and M. Najafi. 2012. “Culvert asset management practices and deterioration modeling.” Transp. Res. Rec. 2285 (1): 1–7.
SCDOT (South Carolina DOT). 2009. Requirements for hydraulic design studies. Columbia, SC: SCDOT.
SCDOT (South Carolina DOT). 2011a. Field inventory and inspection guidelines. Columbia, SC: SCDOT.
SCDOT (South Carolina DOT). 2011b. Pipe & culvert inventory and assessment guidelines. Columbia, SC: SCDOT.
South Carolina Alliance to Fix Our Roads. 2015. “Highway facts.” Accessed October 21, 2015. https://www.scfor.org/.
Tatari, O., S. M. Sargand, T. Masada, and B. Tarawneh. 2013. “Neural network approach to condition assessment of highway culverts: Case study in Ohio.” J. Infrastruct. Syst. 19 (4): 409–414. https://doi.org/10.1061/(ASCE)IS.1943-555X.0000139.
Thompson, P. D., K. M. Ford, M. H. R. Arman, S. Labi, K. C. Sinha, and A. M. Shirole. 2012. Estimating life expectancies of highway assets. Washington, DC: Transportation Research Board.
Tran, D. H., A. W. M. Ng, B. J. C. Perera, S. Burn, and P. Davis. 2006. “Application of probabilistic neural networks in modelling structural deterioration of stormwater pipes.” Urban Water J. 3 (3): 175–184. https://doi.org/10.1080/15730620600961684.
Tran, H. D., B. J. C. Perera, and A. W. M. Ng. 2009. “Predicting structural deterioration condition of individual storm-water pipes using probabilistic neural networks and multiple logistic regression models.” J. Water Resour. Plann. Manage. 135 (6): 553–557. https://doi.org/10.1061/(ASCE)0733-9496(2009)135:6(553).
Information & Authors
Information
Published In
Copyright
©2019 American Society of Civil Engineers.
History
Received: Jun 22, 2018
Accepted: Mar 26, 2019
Published online: Sep 11, 2019
Published in print: Nov 1, 2019
Discussion open until: Feb 11, 2020
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.