Limitation of the Artificial Neural Networks Methodology for Predicting the Vertical Swelling Percentage of Expansive Clays
Publication: Journal of Materials in Civil Engineering
Volume 25, Issue 11
Abstract
The general swelling model has recently been updated in Israel by applying the Excel-solver command (ESC) analysis to new local test results from 897 undisturbed specimens. In this analysis, the goodness-of-fit statistics obtained classify the category of their associated regression only as fair. Thus, it seems necessary to explore the possibility of enhancing the outputs of this regression analysis by applying the artificial neural networks (ANN) methodology to the same 897 undisturbed specimens. However, it is shown that the use of the ANN outputs should be accompanied by an additional check to ensure that they follow the expected physical swelling behavior, as characterized by the index properties of the soil. The ANN methodology applied in this paper is similar to previous studies in geotechnical engineering. Different models were tested using the same database (i.e., the same 897 undisturbed specimens). The statistical fit of the ANN models were clearly found to be superior to the ESC models. However, in the sense of the required physical behavior, as characterized by the index properties of the soil, the ANN models did not predict swelling values as well as ESC models did, in particular values ranging near (or outside) the data set boundaries. Thus, the former ESC models still remain preferable.
Get full access to this article
View all available purchase options and get full access to this article.
Acknowledgments
The paper is based on engineering studies conducted for various Israeli governmental departments and authorities, and thanks are therefore due to them. The helpful assistance provided by Professor Yacoub Najjar of the Department of Civil Engineering of Kansas State University contributed to the development of the paper, and thanks are therefore due to him.
References
Caudill, M. (1988). “Neural networks primer, part III.” AI Expert, 3(6), 53–59.
Ceylan, H., Schwartz, C. W., Kim, S., and Gopalakrishnan, K. (2009). “Accuracy of predictive models for dynamic modulus of hot-mix asphalt.” J. Mater. Civ. Eng., 21(6), 286–293.
Demuth, H., Beale, M., and Hagan, M. (2006). Neural network toolbox user’s guide, Math Works, Natick, MA.
Dongré, R., Leslie, M., D’Angelo, J., Paugh, C., and Gudimettla, J. (2005). “Field evaluation of Witczak and Hirsch models for predicting dynamic modulus of hot-mix asphalt.” J. Assoc. Asphalt Paving Technol., 74, 381–442.
Ersin, Y., and Güneş, N. (2011). “The prediction of swell percent and swell pressure by using neural networks.” Math. Comput. Appl., 16(2), 425–436.
Flood, I., and Kartam, N. (1994). “Neural networks in civil engineering. I: Principles and understanding.” J. Comput. Civ. Eng., 8(2), 31–148.
Foster, C. R. (1962). “Analyses of road test data using procedures developed in the U.S. Army Corps of Engineers accelerated traffic tests.” Proc., 1st Int. Conf. on the Structural Design of Asphalt Pavements, Univ. of Michigan, Ann Arbor, MI, 358–364.
Kassiff, G., Livneh, M., and Wiseman, G. (1969). Pavements on expansive clays, Jerusalem Academic Press, Jerusalem.
Komornik, A., and David, D. (1969). “Prediction of swelling pressure of clays.” J. Soil Mech. Found. Div., 95(1), 209–225.
Livneh, M. (2012a). “An alternative analysis for developing the swelling model for expansive clays.” Proc., 2nd Int. Conf. on Road and Rail Infrastructure, CETRA, Dubrovnik, Croatia.
Livneh, M. (2012b). “Updating predictive models for vertical swell percentage of expansive clays.” Int. J. GEOMATE, 40(2), 205–212.
Livneh, M., and Livneh, A. N. (2012). “On swelling potential of remolded clays as compared with that of undisturbed clays.” Paper submitted to the 25th Conf. of the Australian Road Research Board (ARRB), Shaping the Future, ARRB Group, Perth, Western Australia.
Najjar, Y. M., Basheer, I. A., Ali, H. A., and McReynolds, R. L. (2000). “Swelling potential of Kansas soils, modeling and validation using artificial neural network reliability approach.” Transportation Research Record 1736, Transportation Research Board, Washington, DC, 141–147.
Shahin, M. A., Jaksa, M. B., and Maier, H. R. (2008). “State of the art of artificial neural networks in geotechnical engineering.” Electron. J. Geotech. Eng., 8, 1–26.
Tokar, S. A., and Johnson, P. A. (1999). “Rainfall-runoff modeling using artificial neural networks.” J. Hydrol. Eng., 4(3), 232–239.
Wiseman, G., Komornik, A., and Greenstein, J. (1985). “Experience with roads and buildings on expansive clays.” Transportation Research Record 1023, Transportation Research Board, Washington, DC, 60–67.
Information & Authors
Information
Published In
Copyright
© 2013 American Society of Civil Engineers.
History
Received: Apr 30, 2012
Accepted: Oct 19, 2012
Published online: Oct 20, 2012
Discussion open until: Mar 20, 2013
Published in print: Nov 1, 2013
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.