Keywords: Fondation ; Mur de soutenement ; Pieux ; Capacite portante ; Ancrage ; Dimensionnement Reference Record created on 2004-09-07, modified on 2016-08-08

In recent years artificial neural networks (ANNs) have been applied to many geotechnical engineering problems with some degree of success. With respect to the design of pile foundations, accurate prediction of pile settlement is necessary to ensure appropriate structural and serviceability performance. In this paper, an ANN model is developed for predicting pile settlement based on the results of cone penetration test (CPT) data. Approximately, 300 data sets, obtained from the published literature, are used to develop the ANN model. In addition, the paper discusses the choice of input and internal network parameters which were examined to obtain the optimum model. Finally, the paper compares the predictions obtained by the ANN with those given by a number of traditional methods. It is demonstrated that the ANN model outperforms the traditional methods and provides accurate pile settlement predictions.

Foundation analysis and design

Prediction of Pile Settlement Using Artificial Neural Networks Based on Cone Penetration Test Data

Assessment of lateral excess pressure attributable to train live load on the backfill embankment is one of the main subjects in railway bridge abutment and retaining wall design. Relevant design codes usually define a uniform infinite surcharge on the surface of the embankment to evaluate the lateral live load–induced pressure on the bridge abutments. This simplified method does not consider the actual pattern of operational live load and its induced pressure distribution on the width and height of the wall. In the current study, the operational railway live load pattern LM71 was applied to accurately calculate the laterally induced pressure on the abutment. In this regard, the elasticity-based equations of the laterally induced pressure caused by rectangular area and strip loads were utilized to evaluate the lateral pressure distribution on the abutment attributable to the railway live load. For evaluating the resultant lateral force and moment on the wall, a numerical integration was conducted o...

Effect of Train Live Load on Railway Bridge Abutments

Artificial neural networks have been widely used over the past two decades to successfully develop empirical models for a variety of geotechnical problems. In this paper, an empirical model based on the product-unit neural network (PUNN) is developed to predict the load-deformation behaviour of piles based SPT values of the supporting soil. Other parameters used as inputs include particle grading, pile geometry, method of installation as well as the elastic modulus of the pile material. The model is trained using full-scale pile loading tests data retrieved from FHWA deep foundations database. From the results obtained, it is observed that the proposed model gives a better simulation of pile load-deformation curves compared to the Fleming’s hyperbolic model and t-z approach.

ANN-based empirical modelling of pile behaviour under static compressive loading

The modulus of subgrade reaction is not a unique fundamental soil property that can be readily measured, and its magnitude is an outcome from a soil-structure interaction. But it is required by structural engineers for the structural design of a tunnel. The adoption of an appropriate magnitude for the modulus of subgrade reaction is crucial to ensure that the structural design of the tunnel will be adequate. Some engineers inappropriately rely on the plate load test to determine the magnitude of the modulus of subgrade reaction of the underlying stratum for the structural design of the tunnel. This paper will discuss an appropriate approach to estimate the magnitude of the modulus of subgrade reaction of weak sandstones and siltstones underlying a 2-km tunnel. This tunnel was completed and extensive cracks were noted prior to the opening of the tunnel. This prompted an investigation that included a design review that identified the important issue of an appropriate method for determining the magnitude of the modulus of subgrade reaction for the tunnel design. Typical values for the moduli and Poisson’s ratios of weak sandstones and siltstones required for the soil-structure interaction analysis will be discussed based on a review of the existing literature and the results of plate load tests, pressuremeter tests, and unconfined compression strength tests of the soil investigation report for the tunnel project.

Tunnel Design and Modulus of Subgrade Reaction

/pdf/design-and-field-testing-of-jointless-bridges-235tv1ln7i.pdf

Foundation analysis and design

Citations

Prediction of Pile Settlement Using Artificial Neural Networks Based on Cone Penetration Test Data

Effect of Train Live Load on Railway Bridge Abutments

ANN-based empirical modelling of pile behaviour under static compressive loading

Tunnel Design and Modulus of Subgrade Reaction

Design and field testing of jointless bridges

Related Papers (5)

Soil mechanics in engineering practice

Theoretical Soil Mechanics

Pile Foundation Analysis and Design

Principles of Foundation Engineering

Analysis of Ultimate Loads of Shallow Foundations