scholarly journals Intelligent Computing Based Formulas to Predict the Settlement of Shallow Foundations on Cohesionless Soils

2019 ◽  
Vol 13 (1) ◽  
pp. 1-9 ◽  
Author(s):  
Bashar Tarawneh ◽  
Wassel AL Bodour ◽  
Khaled Al Ajmi

Introduction: Although it is a regular duty of geotechnical engineers to evaluate how much shallow foundation settles in the granular soil, there is no well-approved formula for this task. The intent of this research is to develop a formula that is adequately simple to be used in routine geotechnical engineering work but complete enough to address the behavior of granular soil associated with the settlement issue. Methods: Cone penetration test and foundation load test data were used to generate a formula that can predict the settlement. Genetic Programming (GP) based Symbolic Regression (GP-SR) and artificial neural networks were used to develop an optimized formula. Settlements were also calculated using the finite method and compared to the results of the developed formula. Results and Conclusion: Two formulas were developed using SR, and several models were developed using ANN. ANN model 1 has the highest R2 value (0.93) and the lowest MSE (0.16) among all developed ANN and GP-SR models. FEM settlements were almost double the measured ones in some instances.

1986 ◽  
Vol 23 (4) ◽  
pp. 573-594 ◽  
Author(s):  
P. K. Robertson

The status of in situ testing and its application to foundation engineering are presented and discussed. The in situ test methods are discussed within the framework of three groups: logging, specific, and combined test methods. The major logging test methods discussed are standard penetration test (SPT), cone penetration test (CPT), and the flat plate dilatometer test (DMT). The major specific test methods discussed are the prebored pressuremeter test (PMT), the self-bored pressuremeter test (SBPMT), and the screw plate load test (SPLT). Discussion is also presented on recent tests that combine features of logging tests (using the CPT) and specific tests (e.g. the seismic, the electrical resistivity/dielectric, and the lateral stress sensing cone penetration tests). A brief discussion is also presented on the applicability, as perceived by the author, of existing in situ test methods and the future of in situ testing applied to foundation engineering. Key words: in situ testing, foundation engineering, penetration testing, pressuremeter.


1985 ◽  
Vol 22 (4) ◽  
pp. 518-527 ◽  
Author(s):  
P. K. Robertson ◽  
R. G. Campanella ◽  
P. T. Brown ◽  
I. Grof ◽  
J. M. O. Hughes

A 915 mm diameter steel pipe pile was driven and tested by the B.C. Ministry of Transportation and Highways as part of their foundation studies for the proposed Annacis channel crossing of the Fraser River. The pile was driven open ended to a maximum depth of 94 m. The pile was tested axially to failure when the pile tip was at depths of 67, 78, and 94 m below ground surface. Following the final axial load test, the pile was loaded laterally to a total deflection at the ground surface of 150 mm. A slope indicator casing was installed in the pile to monitor the deflected shape during lateral loading.Adjacent to the pile, a piezometer-friction cone penetration test (CPT) and a full-displacement pressuremeter profile were made. Results of the axial and lateral load tests are presented along with the data from the CPT and the full-displacement pressuremeter tests. Results of several analyses using the data from the CPT and pressuremeter tests to predict the axial and lateral performance of the pile are presented. A comparison and discussion is presented between the predicted and measured axial and lateral behaviour of the pile, for which excellent agreement was found. Key words: pile load test, cone penetration test, pressuremeter test.


2006 ◽  
Vol 43 (6) ◽  
pp. 626-637 ◽  
Author(s):  
Mohamed A Shahin ◽  
Mark B Jaksa

Marquees are temporary light structures that are connected to the ground by small anchors that act in tension and are designed to resist uplift forces. Due to the temporary nature of these structures, little, if any, attention is given to the pullout capacity of the anchors used to secure them. Failures of such structures are not rare and have resulted in deaths and tens of thousands of dollars of damage. This paper reports on a series of 119 in situ anchor pullout tests conducted on rough mild steel anchors of various lengths, cross-sectional shapes, and areas. Comparison tests are carried out to investigate the impact of the factors affecting the pullout capacity of small anchors. Six methods that determine the axial pile capacity directly from cone penetration test (CPT) data are presented and used to calculate the pullout capacity of small ground anchors. The capacities obtained from these CPT-based methods are compared with predictions from a recently developed artificial neural network (ANN) model. The actual pullout loads are compared with predictions from the CPT and ANN methods, and statistical analyses are carried out to evaluate and rank their performance. The results indicate that the ANN-based method provides superior predictions of the pullout capacity of small ground anchors, whereas the Schmertmann method provides the best performance of the CPT-based techniques examined.Key words: ground anchors, pullout capacity, cone penetration test, artificial neural networks.


2007 ◽  
Vol 34 (10) ◽  
pp. 1222-1236 ◽  
Author(s):  
J K.C Shih ◽  
J R Omer ◽  
R Delpak ◽  
R B Robinson ◽  
C D Jones

An interactive computer program GLAMPILE has been developed for predicting the static load capacity of single piles formed in any soil profile. A variety of well-known prediction methods have been incorporated into the program, including (i) soil mechanics based formulae; (ii) direct and indirect cone penetration test (CPT) based methods with and without accounting for scale effects of the cone on pile base capacity; and (iii) a new CPT-based method that considers the effects of “critical depth” and shaft resistance distribution, although the method has only been calibrated for relatively short piles. GLAMPILE can cope with different pile types installed with or without a permanent casing. The program has been applied to predict the axial capacities of 11 piles that were recently installed in sand and statically loaded to failure. Results from the soil mechanics procedures indicate increases, on the in situ value, of the earth pressure coefficient by up to 37%, which lies within the range 0%–100% recommended in the literature. The best CPT-based prediction method applied yields a mean (µ) and coefficient of variation (COV) of predicted to measured pile head capacity (Puh(p)/Puh(m)) of 0.83 and 0.12, respectively. Scale effects are shown to be nominal for the cases analysed. An improved method is recommended, which yields µ = 1.00 and COV = 0.10, implying higher accuracy and reliability compared with the other methods.Key words: piles, cone penetration test, static and dynamic load test, modular program.


2015 ◽  
Vol 72 (3) ◽  
Author(s):  
Ramli Nazir ◽  
Ehsan Momeni ◽  
Kadir Marsono ◽  
Harnedi Maizir

This study highlights the application of Back-Propagation (BP) feed forward Artificial Neural Network (ANN) as a tool for predicting bearing capacity of spread foundations in cohesionless soils. For network construction, a database of 75 recorded cases of full-scale axial compression load test on spread foundations in cohesionless soils was compiled from literatures. The database presents information about footing length (L), footing width (B), embedded depth of the footing (Df), average vertical effective stress of the soil at B/2 below footing (s΄), friction angle of the soil (f) and the ultimate axial bearing capacity (Qu). The last parameter was set as the desired output in the ANN model, while the rest were used as input of the ANN predictive model of bearing capacity. The prediction performance of ANN model was compared to that of Multi-Linear Regression analysis. Findings show that the proposed ANN model is a suitable tool for predicting bearing capacity of spread foundations. Coefficient of determination R2 equals to 0.98, strongly indicates that the ANN model exhibits a high degree of accuracy in predicting the axial bearing capacity of spread foundation. Using sensitivity analysis, it is concluded that the geometrical properties of the spread foundations (B and L) are the most influential parameters in the proposed predictive model of Qu.


2011 ◽  
Vol 243-249 ◽  
pp. 2435-2438
Author(s):  
Dong Hai Jiang ◽  
Zhang Li ◽  
Nai Jian Ji ◽  
Yuan Yuan Hu

Based on the end bearing capacity and friction capacity obtained from high strain dynamic test, an adjusted equation was provided to calculate the pile load capacity. The equation was corrected again by pile load test results. Therefore, a suggested equation was finally established. Practical experience showed that, the corrected equation of cone penetration test method to estimate the load capacity of single pile performed better than that in the national code.


2005 ◽  
Vol 42 (1) ◽  
pp. 91-109 ◽  
Author(s):  
Yung-Mook Na ◽  
Victor Choa ◽  
Cee-Ing Teh ◽  
Ming-Fang Chang

Sandfill at reclaimed sites is usually formed by more than one placement method. Reclaimed sandfill is often highly variable, and the cone penetration test is most commonly used for site characterization. Correlations among the cone resistance and geotechnical parameters for sand are influenced by the in situ stress level, and it is important to incorporate the stress-level effect. In this study, cone penetration tests were performed at several levels from the top of a 10 m high surcharge, which was later removed step by step, and in situ density was determined layer by layer at the Changi East reclamation site in Singapore. Different ways of normalizing the cone resistance by the corresponding in situ stress were investigated. Specialized in situ tests including the self-boring pressuremeter test, the cone pressure meter test, the seismic cone penetration test, and the plate load test were conducted to provide the reference deformation characteristics of sandfill. Results of the in situ tests indicate that the sand density and the cone resistance profiles vary between areas formed by different sand placement methods. Site-specific correlations developed based on comparison of normalized cone resistance with the reference data obtained from laboratory tests and other in situ tests are found to be suitable for the evaluation of relevant soil parameters.Key words: stress normalization, cone resistance, correlations, geotechnical parameter, in situ characterization, granular soil.


2018 ◽  
Vol 245 ◽  
pp. 01004
Author(s):  
Mohanad Sabri ◽  
Aleksandr Bugrov ◽  
Stanislav Panov ◽  
Viacheslav Davidenko

The paper describes an experiment conducted to study the effect of injection an expandablepolyurethane resin on the stabilization, settlement reduction and increasing the bearing capacity of the foundation’s soil. The experiment was carried out in sandy soil, and different types of soil investigations were carried out to investigate the effect of the resin on the soil properties beneath a concrete foundation. Results of Plate load test PLT and dynamic cone penetration test DCPT before and after the injection of the expandable resin are demonstrated and discussed in this paper.


2020 ◽  
Vol 35 (4) ◽  
pp. 1-14
Author(s):  
Nugroho Aji Satriyo ◽  
Eko Soebowo ◽  
Imam Achmad Sadisun

Area development deals with optimal land use and the reduction of the risk of geological disasters. The coastal area of South Bali is prone to land settlement hazards. In order to mitigate the risk, it is important to understand the depositional environment of the area related to its bearing capacity and geological hazard risks. The aim of this research is to understand the subsurface depositional environment and quantifying its bearing capacity. Quantitative modeling was carried out to obtain the sediment-bearing capacity of the Pendungan area in Bali, Indonesia. The methods used in this research were the observation of borehole cores, the identification of the cone penetration test (CPTu) curves pattern, the sediment index property test, the soil strength laboratory, and bearing capacity analysis. Based on lithologic association, the CPTu curve pattern, and grain size analysis, there are three facies developing in the study area with different bearing capacity values. Generally, beach ridge sand has a higher bearing capacity (N-SPT value of 8 – 52) for shallow foundation than fluvial clay. Meanwhile, floodplain facies has the lowest bearing capacity (N-SPT value of 2 – 20).


Sign in / Sign up

Export Citation Format

Share Document