Neural Network Modeling of Resilient Modulus Using Routine Subgrade Soil Properties
Publication: International Journal of Geomechanics
Volume 10, Issue 1
Abstract
Artificial neural network (ANN) models are developed in this study to correlate resilient modulus with routine properties of subgrade soils and state of stress for pavement design application. A database is developed containing grain size distribution, Atterberg limits, standard Proctor, unconfined compression, and resilient modulus results for 97 soils from 16 different counties in Oklahoma. Of these, 63 soils (development data set) are used in training, and the remaining 34 soils (evaluation data set) from two different counties are used in the evaluation of the developed models. A commercial software, STATISTICA 7.1, is used to develop four different feedforward-type ANN models: linear network, general regression neural network, radial basis function network, and multilayer perceptrons network (MLPN). In each of these models, the input layer consists of seven nodes, one node for each of the independent variables, namely moisture content , dry density , plasticity index (PI), percent passing sieve No. 200 , unconfined compressive strength , deviatoric stress , and bulk stress . The output layer consists of only one node—resilient modulus . After the architecture is set, the development data set is fed into the model for training. The strengths and weaknesses of the developed models are examined by comparing the predicted values with the experimental values with respect to the values. Overall, the MLPN model with two hidden layers was found to be the best model for the present development and evaluation data sets. This model as well as the other models could be refined using an enriched database.
Get full access to this article
View all available purchase options and get full access to this article.
Acknowledgments
The writers are thankful to Burgess Engineering and Testing, Inc. for assistance in laboratory testing of this study. The Oklahoma DOT provided some of the evaluation data. The writers are also thankful to StatSoft for providing helpful tips that improved the quality of this study. They are also thankful to their colleagues, Gerald Miller, Kianoosh Hatami, and Joakim Laguros for their technical comments.
References
AASHTO. (1986). Standard specifications for transportation materials and methods of sampling and testing, AASHTO, Washington, D.C.
AASHTO. (2002). AASHTO guide for design of pavement structures, AASHTO, Washington, D.C.
AASHTO. (2004). Standard specifications for transportation materials and methods of sampling and testing, AASHTO, Washington, D.C.
Bishop, C. (1995). Neural networks for pattern recognition, Oxford University Press, New York.
Bors, A. G. (2001). “Introduction of the radial basis function (RBF) networks.” Online Symp. for Electronics Engineers, DSP Algorithms: Multimedia, ⟨http://www.osee.net/⟩, 1(1), 1–7.
Dai, S., and Zollars, J. (2002). “Resilient modulus of Minnesota road research project subgrade soil.” Transp. Res. Rec., 1786, 20–28.
Dunlap, W. S. (1963). “A report on a mathematical model describing the deformation characteristics of granular materials.” Technical Rep. No. 1, Project 2-8-62-27, TTI, Texas A&M Univ., College Station, Tex.
Ebrahimi, A. (2006). “Regression and neural network modeling of resilient modulus based on routine soil properties and stress states.” Ph.D. dissertation, Univ. of Oklahoma, Norman, Okla.
Far, M. S. S., Underwood, B. S., Ranjithan, S. R., Kim, Y. R., and Jackson, N. (2009). “The application of artificial neural networks for estimating the dynamic modulus of asphalt concrete.” Proc., Transportation Research Board 88th Annual Meeting (CD-ROM), Transportation Research Board, Washington, D.C.
Farrar, M. J., and Turner, J. P. (1991). “Resilient modulus of Wyoming subgrade soils.” Mountain Plains Consortium Rep. No. 91-1, The Univ. of Wyoming, Laramie, Wyo.
Fausett, L. V. (1994). Fundamentals neural networks: Architecture, algorithms, and applications, Prentice-Hall, Englewood Cliffs, N.J.
FHWA. (2002). “Study of LTPP laboratory resilient modulus test data and response characteristics.” Final Rep. No. FHWA-RD-02-051, Office of Engineering Research and Development, McLean, Va.
Haykin, W. L. (1994). Neural networks: A comprehensive foundation, Macmillan, New York.
Hill, T., and Lewicki, P. (2006). STATISTICS methods and applications, StatSoft, Tulsa, Okla.
Hopkins, T. C., Beckham, T. L., Sun, L., and Pfalzer, B. (2004). “Kentucky geotechnical database.” Research Rep. No. KTC-03-06/SPR-177-98-1F, Univ. of Kentucky Transportation Center, College of Engineering, Lexington, Ky.
Khazanovich, L., Celauro, B., Chabourn, B., and Zollars, J. (2006). “Evaluation of subgrade resilient modulus predictive model for use in mechanistic-empirical pavement design guide.” Transp. Res. Rec., 1947, 155–166.
Kohonen, T. (1989). Self-organization and associative memory, 3rd Ed., Springer, Berlin.
Malla, R. B., and Joshi, S. (2008). “Subgrade resilient modulus prediction models for coarse and fine-grained soils based on long-term pavement performance data.” Int. J. Pavement Eng., 9(6), 431–444.
Mehrotra, K., Mohan, C. K., and Ranka, S. (1996). Elements of artificial neural networks, MIT Press, Cambridge, Mass.
Meier, R. W., Alexander, D. R., and Freeman, R. B. (1997). “Using artificial neural networks as a forward approach to backcalculation.” Transp. Res. Rec., 1570, 126–133.
Montgomery, D. C., Peck, E. A., and Vining, G. G. (2006). Introduction to linear regression analyses, Wiley, New York.
Moossazadeh, J. M., and Witczak, M. W. (1981). “Prediction of subgrade moduli for soil that exhibits nonlinear behavior.” Transp. Res. Rec., 810, 9–17.
Najjar, Y. M., Basheer, I. A., Ali, H. E., and McReynolds, R. L. (2000). “Swelling potential of Kansas soils: Modeling and validation using artificial neural network reliability approach.” Transp. Res. Rec., 1736, 141–147.
Narayan, S. (2002). “Using genetic algorithms to adapt neuron functional forms.” Proc., Artificial Intelligence and Soft Computing, ACTA, Banff, Canada.
NCHRP. (2004). “Guide for mechanistic-empirical design of new and rehabilitated pavement structures.” Final Rep. No. 1-37A, NCHRP, Transportation Research Board, Washington, D.C.
ODOT. (2000). Standards and specifications, DOT, Oklahoma City.
Park, H. I., Kweon, G. C., and Lee, S. R. (2009). “Prediction of resilient modulus of granular subgrade soils and subbase materials using an artificial neural network.” Road Mater. Pavement Des., 10(3), 647–665.
Patterson, D. (1996). Artificial neural networks, Prentice-Hall, N.J.
Rahim, A. M., and George, J. P. (2004). “Subgrade soil index properties to estimate resilient modulus.” Proc., 83rd Annual Meeting of Transportation Research Board, Transportation Research Board, Washington, D.C.
Rankine, R. M., and Sivakugan, N. (2005). “Prediction of paste backfill performance using artificial neural networks.” Proc., 16th ISSMGE, Vol. 2, A. A. Balkema, The Netherlands, 1107–1110.
Ripley, B. D. (1996). Pattern recognition and neural networks, Cambridge University Press, Cambridge, U.K.
Rumelhart, D. E., and McClelland, J. (1986). Parallel distributed processing, Vol. 1, MIT Press, Cambridge, Mass.
Shahin, M. A., Jaksa, M. B., and Maier, H. R. (2001). “Artificial neural network applications in geotechnical engineer.” Austral. Geomech. J., 36(1), 49–62.
Shahin, M. A., Maier, H. R., and Jaksa, M. B. (2004). “Data division for developing neural networks applied to geotechnical engineering.” J. Comput. Civ. Eng., 18(2), 105–114.
Sharma, S., and Das, A. (2008). “Backcalculation of pavement layer moduli from falling weight deflectometer data using an artificial neural network.” Can. J. Civ. Eng., 35(1), 57–66.
Skapura, D. M. (1996). Building neural networks, ACM, New York.
Specht, D. F. (1991). “A generalized regression neural network.” IEEE Trans. Neural Netw., 2(6), 568–576.
Tarefder, R. A., White, L., and Zaman, M. (2005). “Neural network model for asphalt concrete permeability.” J. Mater. Civ. Eng., 17(1), 19–27.
Thompson, M. R., and Robnett, Q. L. (1976). “Resilient properties of subgrade soils.” Final Rep. No. FHWA-IL-UI-160, Univ. of Illinois, Urbana, Ill.
TRB. (1999). “Use of artificial neural networks in geomechanical and pavement systems.” Transportation Research Circular No. E-C012, Transportation Research Board, National Research Council, Washington, D.C.
Uzan, J. (1985). “Characterization of granular material.” Transp. Res. Rec., 1022, 52–59.
Yau, A., and Von Quintus, H. L. (2002). “Study of LTPP laboratory resilient modulus test data and response characteristics.” Final Rep. No. FHWA-RD-02-051, FHWA, Washington, D.C.
Yildirim, T., and Ozyilmaz, L. (2002). “Dimensionality reduction in conic section function neural network.” Sadhana: Proc., Indian Acad. Sci., 27(6), 675–683.
Zurada, J. M. (1992). Introduction to artificial neural systems, West, St. Paul, Minn.
Information & Authors
Information
Published In
International Journal of Geomechanics
Volume 10 • Issue 1 • February 2010
Pages: 1 - 12
Copyright
© 2010 ASCE.
History
Received: Dec 29, 2006
Accepted: Aug 28, 2009
Published online: Jan 15, 2010
Published in print: Feb 2010
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.