Piles in Sandy Soil: A Numerical Study and Experimental Validation

Jebur, Ameer A.; Atherton, William; Alkhadar, Rafid M.; Loffill, Edward

doi:10.1016/j.proeng.2017.07.173

Cited by 12 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2 and 3, and as recommended by Alizadeh et al (2012). It should be stated that the existence of the transfer function in the hidden layer and output layer is essential in order to transform the weighted sum of all signals hitting on a neurons so as to select its "firing intensity" (Majdi and Beiki, 2010;Jebur et al, 2017b).…”

Section: Architecture and Ann Model Performancementioning

confidence: 99%

Settlement Prediction of Model Piles Embedded in Sandy Soil Using the Levenberg–Marquardt (LM) Training Algorithm

et al. 2018

Self Cite

View full text Add to dashboard Cite

This investigation aimed to examine the load carrying capacity of model piles embedded in sand soil and to develop a predictive model to simulate pile settlement using a new artificial neural network (ANN) approach. A series of experimental pile load tests were carried out on model concrete piles, comprised of three piles with slenderness ratios of 12, 17 and 25. This was to provide an initial dataset to establish the ANN model, in attempt at making current, in situ pile-load test methods unnecessary. Evolutionary Levenberg-Marquardt (LM) MATLAB algorithms, enhanced by T-tests and F-tests, were developed and applied in this process. The model piles were embedded in a calibration chamber in three densities of sand; loose, medium and dense. According to the statistical analysis and the relative importance study, pile lengths, applied load, pile flexural rigidity, pile aspects ratio, and sand-pile friction angle were found to play a key role in pile settlement at different contribution levels, following the order: P > δ > lc/d > lc > EA. The results revealed that the optimum model of the LM training algorithm can be used to characterize pile settlement with good degree of accuracy. There was also close agreement between the experimental and predicted data with a root mean square error, (RMSE) and correlation coefficient (R) of 0.0025192 and 0.988, respectively.

show abstract

Section: Architecture and Ann Model Performancementioning

confidence: 99%

Settlement Prediction of Model Piles Embedded in Sandy Soil Using the Levenberg–Marquardt (LM) Training Algorithm

et al. 2018

Self Cite

View full text Add to dashboard Cite

show abstract

“…Furthermore, there are several alternative predictive approaches are available to exactly estimate the pile load capacity and related settlement for examples, Shahin [50] provided state-of-the-art review of some selected Arti cial Intelligence (AI) techniques and their applications in pile foundations using cast in place real model of pile load tests by many factors and also discussed the strength and limitations of the selected AI techniques. Additionally, Jebura et al [24] were developed a novel approach of multi-layered arti cial neural networks (ANN) based on the Levenberg-Marquardt approach (LM) by conducting several experimental studies using three categories of steel open-ended pipe, steel closed-ended pipe and square concrete piles as tested models.…”

Section: Introductionmentioning

confidence: 99%

Model Study of a Single Pile With Varied Configuration in Sand

Sakr

Azzam

Kassim

2021

Preprint

View full text Add to dashboard Cite

In this experimental work, the influence of pile cross-section with varied configurations on the axial compression load capacity of a single pile and related settlement in sand are investigated. The influence of relative sand density (Dr), the pile length to diameter (L/D) ratios and the pile installation techniques are presented. A testing program comprising seven model steel piles with varied shapes of 20 mm width/diameter was conducted. The tests are performed on model piles with the pile length to diameter ratios of 10 and 30 installed in the three cases of sand modeling as loose, medium dense and dense sand. Results indicated that, the rectangular pile is the optimization cross-sectional under the same pile geometry and soil conditions. Also, the increase of the relative sand density has a significant influence on the ultimate compression pile load. Furthermore, the ultimate axial loads of flexible piles in the case of loose sand using the non-displacement method were found to be increased by 119%, 114%, 143%, 82% 139%, 89% and 100% comparing with the ultimate axial loads of rigid piles for the seven models of closed-ended pipe, open-ended pipe, conical base pipe, square closed-ended, square open-ended, tapered and rectangular piles respectively. While, these percentages were found to be increased by (49%, 37%, 26%, 78%, 35%, 71% and 91%) and (77%, 50%, 13%, 116%, 61%, 89% and 85%) in the cases of medium dense and dense sand respectively. The results also indicated that, piles installed in sand using jacking technique have more resistance compared with piles installed in sand using non-displacement technique.

show abstract

“…Therefore, most of the available methods fail to gain reliable success regarding precise prediction of the pile capacity and the corresponding settlement (Momeni et al, 2014;Loria et al, 2015;Jebur et al, 2017).…”

Section: Introductionmentioning

confidence: 99%