Modular Neural Networks for Predicting Settlements during Tunneling
Publication: Journal of Geotechnical and Geoenvironmental Engineering
Volume 124, Issue 5
Abstract
This paper discusses back-propagation neural networks (NN) for predicting the settlement during tunneling. Three settlement parameters and 11 major affecting factors have been identified from analyzing the general tunneling operations. A general neural network model is trained and tested using the actual collected data from the 6.5 km Brasilia Tunnel in Brazil. The general model generates an average error of 70 mm for the predicted settlements compared with the actual values. To improve the prediction accuracy, modular NN models are studied based on the concept of integrating multiple NN modules in one system with each module being constrained to operate at one specific situation of a complicated real world problem. The modular concept can make better use of neural computation algorithms to improve the convergence in the training process. It has been studied on modeling multiple output variables and discrete input variables. After applying modular models to the same Brasilia Tunnel, the average prediction error is reduced to 33.4 mm, which shows a significant improvement over the general NN model.
Get full access to this article
View all available purchase options and get full access to this article.
References
1.
Attewell, P. B. (1977). “Ground movements caused by tunnelling in soil.”Proc., Int. Conf. on Large Ground Movements and Struct., Pentech Press, London, England, 812–948.
2.
Attewell, P. B., and Woodman, J. P. (1982). “Predicting the dynamics of ground settlements and its derivatives caused by tunnelling in soil.”Ground Engrg., London, England, 15(8), 13–22, 36.
3.
Cording, E. J., and Hansmire, W. H. (1975). “Displacement around soft ground tunnels.”5th Pan Am. Conf. on SMFE, Buenos Aires, Vol. 4, 571–633.
4.
Mair, R. J., Taylor, R. N., and Bracegirdle, A.(1993). “Subsurface settlement profiles above tunnels in clays.”Géotechnique, London, England, 43(2), 315–320.
5.
Negro, A., and Kochen, R. (1996). “Numerical modelling of a tunnel in soft porous clay.”Proc. Symp. on Geotech. Aspects of Underground Constr. in Soft Ground, City University, London, Thomas Telford Ltd., London, England.
6.
O'Reilly, M. P., and New, B. M. (1982). “Settlements above tunnels in the United Kingdom—their magnitude and prediction.”Tunnelling '82, Institute of Mining and Metallurgy, London, England, 173–181.
7.
Ortigao, J. A. R., Cunha, R. P., and Alves, L. S.(1996a). “In situ tests in Brasilia porous clay.”Can. Geotech. J., Ottawa, Canada, 33, 189–198.
8.
Ortigao, J. A. R., Kochen, R., Farias, M. M., and Assis, A. A.(1996b). “Tunnelling in Brasilia porous clay.”Can. Geotech. J., Ottawa, Canada, 33, 565–573.
9.
Peck, R. B. (1969). “Deep excavations and tunneling in soft ground.”7th ICSMFE, state of the art report, México, 225–290.
10.
Rowe, R. K., and Lee, K. M.(1992). “An evaluation of simplified techniques for three-dimensional undrained ground movements due to tunnelling in soft soils.”Can. Geotech. J., Ottawa, Canada, 29, 39–52.
11.
Rumelhart, D. E., and McClelland, J. L. (1986). Parallel distributed processing, Vol. 1, MIT Press, Cambridge, Mass.
12.
Uriel, A. O., and Sagaseta, C. (1989). “Selection of design parameters for underground construction.”General Report, Proc., 12th ICSMFE, Rio de Janeiro, Brazil, A. A. Balkema, Rotterdam, The Netherlands, Vol. 4, 2521–2551.
Information & Authors
Information
Published In
Copyright
Copyright © 1998 American Society of Civil Engineers.
History
Published online: May 1, 1998
Published in print: May 1998
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.