Artificial Neural Network Model for Time-Dependent Vertical Bearing Capacity of Preformed Concrete Pile

Tian Xia; Wei Wang; Xiao Ni Wang

doi:10.4028/www.scientific.net/AMM.29-32.226

Paper Titles

Vibration Measurement and Data Analysis of a Spinning Shaft Using a Camera-Based Motion Analysis System
p.203

The Reliability Study of LRB Continuous Girder Bridges Subject to Seismic Excitation
p.209

Experimental Study on Cutting Force of Pocket Corner in HSM
p.215

Modified Analytical Expression of Damping Constant in the Hertz Contact Model with Non-Linear Damping for Structural Pounding
p.220

Artificial Neural Network Model for Time-Dependent Vertical Bearing Capacity of Preformed Concrete Pile
p.226

Study of a Bistable Stochastic Resonance-Based Children Activities Monitoring System Using Wireless Sensor Network
p.233

Application of the LMI Approach in the Robust Force Control of Servo-Hydraulic Actuator with Parametric Uncertainties
p.240

An Improved Synchronization Mechanism of SERCOS III in Strong EMI Environment
p.246

Keyhole Modeling during Laser Deep Penetration Welding
p.252

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 29-32Artificial Neural Network Model for Time-Dependent...

Artificial Neural Network Model for Time-Dependent Vertical Bearing Capacity of Preformed Concrete Pile

Abstract:

Mechanism of time effect on vertical ultimate bearing capacity (VUBC) of preformed concrete pile is analyzed. The effect strongly depends on seven parameters of pile engineering. Pile length, area of pile section, soil friction angle, soil consolidation coefficient, soil elastic module and time after pile installation and pile type are them. Considering time effect and soil consolidation, artificial neural network model to predict this time-dependent VUBC is established. Input layer includes seven parameters discussed above. Conjugate gradient method is adopted to train the net. Based on calculation of practical piles, results of the model are found to be in good agreement with field tests, and the efficiency of the present model is signalized.

You might also be interested in these eBooks

Applied Mechanics And Mechanical Engineering

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 29-32)

Pages:

226-230

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.29-32.226

Citation:

Cite this paper

Online since:

August 2010

Authors:

Tian Xia, Wei Wang, Xiao Ni Wang

Keywords:

Artificial Neural Network (ANN), Preformed Concrete Pile, Time-Effect, Ultimate Bearing Capacity

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] M. A. Abu Kiefa: J. Geotech. & Geoenv. Vol. 124 (1998), p.1177.

Google Scholar

[2] X. Li, J. Liu: Chinese Journal of Geotechnical Engineering, Vol. 14 (1992), p.9.

Google Scholar

[3] Z. Li: China Harbor Engineering, Vol. 5(2002), p.36.

Google Scholar

[4] T. Xia, W. Wang, in: Study on evaluating methods for time-dependent ultimate bearing capacity of single driven pile, edited by J. R. Zhu, International Conference on Engineering Computation, IEEE CPS Publishers (2009).

DOI: 10.1109/icec.2009.56

Google Scholar

[5] S.J. Li, Y.X. Liu and X. He: Chinese J. Rock Mechanics and Engineering, Vol. 22 (2003), p.1870.

Google Scholar

[6] Z. L. Feng, H. T. Sun and S. J. Wang: Tongji University J. Vol. 27 (1999), p.397.

Google Scholar

[7] C. H. Wang, W. T. Zhang: Rock and Soil Mechanics. Vol. 23 (2002), p.173.

Google Scholar

[8] W. G. K. Fleming, W. K. Elson: Pile Engineering (John and Sons, 2nd edition, UK1992).

Google Scholar