Prediction of Pile Capacity Using Neural Networks
- 1 April 1997
- journal article
- Published by American Society of Civil Engineers (ASCE) in Journal of Computing in Civil Engineering
- Vol. 11 (2), 129-138
- https://doi.org/10.1061/(asce)0887-3801(1997)11:2(129)
Abstract
A back-propagation neural network model for estimating static pile capacity from dynamic stress-wave data is proposed. The training and testing of the network were based on a database of 37 precast reinforced concrete (RC) piles from 21 different sites. The CAPWAP-predicted soil parameters were used as the desired output in training. Three different network models were used to study the ability of the neural network to predict the desired output to increasing degree of detail. The study showed that the neural network model predicted the total capacity reasonably well. The neural-network-predicted soil resistance along the pile was also in general agreement with the CAPWAP solution. The capability of the network to generalize from limited training examples was verified by its performance against dynamic test data obtained from non-RC piles.Keywords
This publication has 8 references indexed in Scilit:
- A new approach to the analysis of high-strain dynamic pile test dataCanadian Geotechnical Journal, 1994
- Working with neural networksIEEE Spectrum, 1993
- Rational Wave Equation Model for Pile‐Driving AnalysisJournal of Geotechnical Engineering, 1988
- Parallel Distributed ProcessingPublished by MIT Press ,1986
- Learning Internal Representations by Error PropagationPublished by Defense Technical Information Center (DTIC) ,1985
- Dynamic Determination of Pile CapacityJournal of Geotechnical Engineering, 1985
- Soil Resistance Predictions from Pile DynamicsJournal of the Soil Mechanics and Foundations Division, 1972
- Pile-Driving Analysis by the Wave EquationJournal of the Soil Mechanics and Foundations Division, 1960