Computational & Technology Resources
an online resource for computational,
engineering & technology publications
COMPUTATIONAL ENGINEERING USING METAPHORS FROM NATURE
Edited by: B.H.V. Topping
Neural Network Predictive Tools for Settlement Responses Due to Long-Term Dewatering Activities
A.W. Sadek, F. El-Nahhas and A. El-Shenawy
Engineering Division, Kuwait Institute for Scientific Research, Safat, Kuwait
A.W. Sadek, F. El-Nahhas, A. El-Shenawy, "Neural Network Predictive Tools for Settlement Responses Due to Long-Term Dewatering Activities", in B.H.V. Topping, (Editor), "Computational Engineering using Metaphors from Nature", Civil-Comp Press, Edinburgh, UK, pp 65-70, 2000. doi:10.4203/ccp.64.1.10
The present paper reports an application of the neural network technique to predict ground settlement as occasioned by dewatering activities of a long-term large-scale drainage project. For this purpose, neural networks to estimate settlement values in the vicinity of the pumping wells are developed. The effect of soil characteristics on settlement responses is considered by including the average standard penetration test number SPTN in the input nodes of the network. A long-term index is synthesized and included in the input nodes to account for time-dependent factors such as leaching potential, clay content and consolidation.
Two alternative approaches are proposed for the drawdown-settlement network application. The present cited application of neural network to predict ground settlement has proven invaluable in view of the complex relationship between drawndowns and settlements.
purchase the full-text of this paper (price £20)