Application of Neural Network Model to Forecast Short-Term Pavement Crack Condition: Florida Case Study
Publication: Journal of Infrastructure Systems
Volume 7, Issue 4
Abstract
Certain highway agencies such as the Florida Department of Transportation use the crack index (CI) to enumerate pavement cracking and determine the rehabilitation priorities. Thus, accurate forecasting of CI is essential for pavement rehabilitation budgeting. Currently, mechanistic-empirical and purely empirical models are popular tools for forecasting pavement cracking. However, with a large data dimension, it is difficult to select appropriate mathematical function forms for the above models. This paper summarizes the results obtained from a case study in which single-year and multiyear back-propagation neural network (BPNN) models were developed to forecast accurately the short-term time variation of CIs of Florida's highway network. The BPNN models exhibited a remarkable ability of learning the historical crack progression trend from the CI database and accurately forecasting future CI values. Then, the BPNN model was validated by comparing the forecasted CIs with measured CI data for the year 1998. Finally, the BPNN model results were compared to those of a commonly used autoregressive model and the BPNN model was seen to be certainly more accurate than the autoregressive model. Hence the BPNN models can be expected to make a significant impact on the efficiency of rehabilitation budget planning in particular and pavement management systems in general.
Get full access to this article
View all available purchase options and get full access to this article.
References
1.
Attoh-Okine, N. O. ( 1994). “Predicting roughness progression in flexible pavements using artificial neural networks.” Proc., 3rd Int. Conf. on Managing Pavements, Vol. 1, Transportation Research Board, San Antonio, Tex., 55–62.
2.
Bandara, N., and Gunaratne, M. (2001). “Current and future pavement maintenance prioritization based on rapid visual condition evaluation.”J. Transp. Engrg., ASCE, 127(2), 116–123.
3.
Horici, K. ( 1994). “Pavement performance model and its application to pavement management system.” J. Mat., Concrete Struct. and Pavements, 99–102.
4.
Hornik, K., Strathcombe, M., and White, H. ( 1989). “Multilayer feedforward networks are universal approximators.” Neural networks 2, Pergamon, 2(4), 359–366.
5.
Jackson, N. C., Deighton, R., and Huft, D. L. ( 1996). “Development of pavement performance curves for individual distress indexes in South Dakota based on expert opinion.” Transp. Res. Rec. 1524, Transportation Research Board, Washington, D.C., 130–136.
6.
Lawrence, J., and Fredrickson, J. ( 1993). BrainMaker user's guide and reference manual, 7th Ed., California Scientific Software, Nevada City, Calif.
7.
Lu, J., Bertrand, C., Hudson, W. R., and Mccullough, B. F. ( 1993). “Adaptive filter forecasting system for pavement roughness.” Transp. Res. Rec. 1344, Transportation Research Board, Washington, D.C., 124–129.
8.
Owusu-Ababio, S. ( 1995). “Modeling skid resistance for flexible pavements: A comparison between regression and neural network models.” Transp. Res. Rec. 1501, Transportation Research Board, Washington, D.C., 60–71.
9.
Queiroz, C. ( 1983). “A mechanistic analysis of asphalt pavement performance in Brazil.” J. Assn. of Asphalt Paving Technol., 52, 474–488.
10.
Rumelhart, D., and McClelland, J. ( 1986). Parallel distributed processing, Vol. 1 and 2, MIP Press, Cambridge, Mass.
11.
Sood, V. K., Sharma, B. M., Kanchan, P. K., and Sitaramanjaneyulu, K. ( 1994). “Pavement deterioration modeling in India.” Proc., 3rd Int. Conf. on Managing Pavements, Transportation Research Board, San Antonio, Tex., 1, 47–54.
12.
Wang, K. C. P., Zaniewski, J., and Way, G. (1994). “Probabilistic behavior of pavements.”J. Transp. Engrg., ASCE, 120(3), 358–375.
Information & Authors
Information
Published In
History
Received: Apr 13, 2000
Published online: Dec 1, 2001
Published in print: Dec 2001
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.