A new genetic programming model for predicting settlement of shallow foundations

2007 ◽  
Vol 44 (12) ◽  
pp. 1462-1473 ◽  
Author(s):  
Mohammad Rezania ◽  
Akbar A. Javadi
Keyword(s):  
Genetic Programming ◽  
Programming Model ◽  
Standard Penetration Test ◽  
Shallow Foundations ◽  
Penetration Test ◽  
Case Histories ◽  
Contributing Factors ◽  
Artificial Neural Network Ann ◽  
Gp Model ◽  
Very High

In this paper, a new genetic programming (GP) approach for predicting settlement of shallow foundations is presented. The GP model is developed and verified using a large database of standard penetration test (SPT) based case histories that involve measured settlements of shallow foundations. The results of the developed GP model are compared with those of a number of commonly used traditional methods and artificial neural network (ANN) based models. It is shown that the GP model is able to learn, with a very high accuracy, the complex relationship between foundation settlement and its contributing factors, and render this knowledge in the form of a function. The attained function can be used to generalize the learning and apply it to predict settlement of foundations for new cases not used in the development of the model. The advantages of the proposed GP model over the conventional and ANN based models are highlighted.

scholarly journals Optimization of Windspeed Prediction Using an Artificial Neural Network Compared With a Genetic Programming Model

2021 ◽  
pp. 116-147
Author(s):  
Ravinesh C. Deo ◽  
Sujan Ghimire ◽  
Nathan J. Downs ◽  
Nawin Raj
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Genetic Programming ◽  
Programming Model ◽  
Power Prediction ◽  
Energy Forecasting ◽  
Precise Prediction ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Gp Model

The precise prediction of windspeed is essential in order to improve and optimize wind power prediction. However, due to the sporadic and inherent complexity of weather parameters, the prediction of windspeed data using different patterns is difficult. Machine learning (ML) is a powerful tool to deal with uncertainty and has been widely discussed and applied in renewable energy forecasting. In this chapter, the authors present and compare an artificial neural network (ANN) and genetic programming (GP) model as a tool to predict windspeed of 15 locations in Queensland, Australia. After performing feature selection using neighborhood component analysis (NCA) from 11 different metrological parameters, seven of the most important predictor variables were chosen for 85 Queensland locations, 60 of which were used for training the model, 10 locations for model validation, and 15 locations for the model testing. For all 15 target sites, the testing performance of ANN was significantly superior to the GP model.

scholarly journals Optimization of Windspeed Prediction Using an Artificial Neural Network Compared With a Genetic Programming Model

2018 ◽  
pp. 328-359 ◽  
Author(s):  
Ravinesh C. Deo ◽  
Sujan Ghimire ◽  
Nathan J. Downs ◽  
Nawin Raj
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Genetic Programming ◽  
Programming Model ◽  
Power Prediction ◽  
Energy Forecasting ◽  
Precise Prediction ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Gp Model

The precise prediction of windspeed is essential in order to improve and optimize wind power prediction. However, due to the sporadic and inherent complexity of weather parameters, the prediction of windspeed data using different patterns is difficult. Machine learning (ML) is a powerful tool to deal with uncertainty and has been widely discussed and applied in renewable energy forecasting. In this chapter, the authors present and compare an artificial neural network (ANN) and genetic programming (GP) model as a tool to predict windspeed of 15 locations in Queensland, Australia. After performing feature selection using neighborhood component analysis (NCA) from 11 different metrological parameters, seven of the most important predictor variables were chosen for 85 Queensland locations, 60 of which were used for training the model, 10 locations for model validation, and 15 locations for the model testing. For all 15 target sites, the testing performance of ANN was significantly superior to the GP model.

Reconsideration of case histories for estimating undrained shear strength in sandy soils

1999 ◽  
Vol 36 (5) ◽  
pp. 907-933 ◽  
Author(s):  
C E (Fear) Wride ◽  
E C McRoberts ◽  
P K Robertson
Keyword(s):  
Shear Strength ◽  
Sandy Soils ◽  
Standard Penetration Test ◽  
Undrained Shear Strength ◽  
Soil Liquefaction ◽  
Penetration Test ◽  
Case Histories ◽  
Original Case ◽  
Undrained Strength ◽  
Undrained Shear

When sandy soils respond in a strain-softening manner to undrained loading, an estimation of the resulting undrained shear strength (Su) is required to determine the potential for flow liquefaction at a given site. One of the most commonly used methods for estimating the undrained strength of liquefied sand is an empirical standard penetration test (SPT) based chart (originally proposed by H.B. Seed), which was developed using a number of case histories. The original interpretations of these case histories are viewed by many workers and regulatory agencies as the most authoritative measure of the liquefied strength of sand. Consequently, in comparison, other less conservative methods are generally held in an unfavourable light. This paper reexamines the original database of case histories in view of some more recent concepts regarding soil liquefaction. The objectives of this paper are to explore and reassess the issues involved in the original assessment and to offer alternative views of the case records. The conclusions presented here indicate that alternative explanations of the liquefied strength of sand are not inconsistent with the original case histories. Key words: sandy soils, soil liquefaction, undrained strength, standard penetration test (SPT).

Liquefied strength ratio from liquefaction flow failure case histories

2002 ◽  
Vol 39 (3) ◽  
pp. 629-647 ◽  
Author(s):  
Scott M Olson ◽  
Timothy D Stark
Keyword(s):  
Shear Strength ◽  
Back Analysis ◽  
Penetration Resistance ◽  
Standard Penetration Test ◽  
Strength Ratio ◽  
Penetration Test ◽  
Case Histories ◽  
Tip Resistance ◽  
Flow Failure ◽  
Vertical Effective Stress

The shear strength of liquefied soil, su(LIQ), mobilized during a liquefaction flow failure is normalized with respect to the vertical effective stress (σ 'vo) prior to failure to evaluate the liquefied strength ratio, su(LIQ)/σ 'vo. Liquefied strength ratios mobilized during 33 cases of liquefaction flow failure are estimated using a procedure developed to directly back-analyze the liquefied strength ratio. In ten cases, sufficient data regarding the flow slide are available to incorporate the kinetics, i.e., momentum, of failure in the back-analysis. Using liquefied strength ratios back-calculated from case histories, relationships between liquefied strength ratio and normalized standard penetration test blowcount and cone penetration test tip resistance are proposed. These relationships indicate approximately linear correlations between liquefied strength ratio and penetration resistance up to values of qc1 and (N1)60 of 6.5 MPa and 12 blows/ft (i.e., blows/0.3 m), respectively.Key words: liquefaction, flow failure, liquefied shear strength, stability analysis, kinetics, penetration resistance.

SPT-Based Probabilistic Method for Evaluation of Liquefaction Potential of Soil Using Multi-Gene Genetic Programming

2013 ◽  
Vol 4 (1) ◽  
pp. 42-60 ◽  
Author(s):  
Pradyut Kumar Muduli ◽  
Sarat Kumar Das
Keyword(s):  
Genetic Programming ◽  
Probabilistic Method ◽  
Limit State ◽  
Mapping Function ◽  
Standard Penetration Test ◽  
State Function ◽  
Liquefaction Potential ◽  
Successful Prediction ◽  
Bayesian Mapping ◽  
Artificial Neural Network Ann

The present study discusses about evaluation of liquefaction potential of soil within a probabilistic framework based on the standard penetration test (SPT) dataset using evolutionary artificial intelligence technique, multi-gene genetic programming (MGGP). Based on the developed limit state function, a relationship is given between probability of liquefaction and factor of safety against liquefaction using Bayesian theory. This Bayesian mapping function is further used to develop a probabiliy based design chart for evaluation of liquefaction potential of soil. Using an independent database the efficacy of present MGGP based probabilistic model is compared with the available artificial neural network (ANN) and statistical models in terms of rate of successful prediction of liquefaction and non-liquefaction cases. The proposed MGGP based model is found to be more accurate compared to other models.

Genetic programming model for forecast of short and noisy data

2007 ◽  
Vol 21 (2) ◽  
pp. 266-272 ◽  
Author(s):  
C. Sivapragasam ◽  
P. Vincent ◽  
G. Vasudevan
Keyword(s):  
Genetic Programming ◽  
Programming Model ◽  
Noisy Data

Comportement de pieux d'essais instrumentés sous charge horizontale

1993 ◽  
Vol 30 (1) ◽  
pp. 1-11
Author(s):  
R. Frank ◽  
H. Zervogiannis ◽  
S. Christoulas ◽  
V. Papadopoulos ◽  
N. Kalteziotis
Keyword(s):  
Pile Foundation ◽  
Bending Moment ◽  
Standard Penetration Test ◽  
American Petroleum Institute ◽  
Full Scale ◽  
Test Method ◽  
Cohesionless Soil ◽  
Penetration Test ◽  
Cohesionless Soils ◽  
Final Design

This paper describes the behaviour of two test piles (one bored and postgrouted and one simply bored, both 31.7 m long and 0.75 m in diameter) subjected to horizontal loads. These full-scale pile tests were carried out for the actual design of the pile foundation of a pier of the Evripos cable-stayed bridge. This bridge will link the Euboea Island to mainland Greece. The two piles have already been subjected to bearing capacity tests under axial loadings. The inclinometer measurements, taken during the present tests, yielded, in particular, the deformed shape of the piles as well as the bending moments. Conclusions could be drawn for the final design of the pile foundation with respect to horizontal loadings. Furthermore, various calculation methods using p–y reaction curves for cohesionless soils have been checked: the Ménard pressuremeter method, the method of the American Petroleum Institute recommendations, and the Standard penetration test method of Christoulas. These pile tests show that simple measurements, taken on construction sites, can yield interesting results on the actual behaviour of horizontally loaded piles. Key words : pile, horizontal loading, full-scale test, horizontal loads, bending moment, subgrade reaction modulus, p–y curve, cohesionless soil, Standard penetration test, pressuremeter test.

Assessment of the range of variation of Nγ from 60 estimation methods for footings on sand

2013 ◽  
Vol 50 (7) ◽  
pp. 793-800 ◽  
Author(s):  
Edgar Giovanny Diaz-Segura
Keyword(s):  
Friction Angle ◽  
Standard Penetration Test ◽  
Estimation Methods ◽  
Penetration Test ◽  
In Situ Tests ◽  
Vertical Loading ◽  
Simplified Method ◽  
Bearing Capacity Factor ◽  
Range Of Variation

The range of variation of the bearing capacity factor, Nγ, was assessed using 60 estimation methods for rough footings on sand subjected to static vertical loading. The influence on the Nγ values of the use of correlations for the estimation of the friction angle, [Formula: see text], derived from in situ tests was also assessed. The analysis shows a marked dependency on the methods used to determine Nγ, showing differences for the same [Formula: see text] values of up to 267% between estimated values. Uncertainty in the estimation of [Formula: see text], due to the use of correlations with in situ tests, leads to a range of variation for Nγ higher than that seen using the 60 estimation methods. Finally, given the regular use of the in situ standard penetration test (SPT) on sands, and based on a series of analyses using finite elements, a simplified method in terms of the SPT N-values is proposed for estimation of Nγ in footings on sands.

Sign in / Sign up

Export Citation Format

Share Document