Prediction of Lateral Load Capacity of Pile in Clay Using Multivariate Adaptive Regression Spline and Functional Network

Das, Sarat Kumar; Suman, Shakti

doi:10.1007/s13369-015-1624-y

Cited by 30 publications

(6 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Equations ( 9) and (10) were used to determine the theoretical UBC of a single pile. The details about these calculations can be found in Das (2015).…”

Section: Comparison Of Best Model and Theoretical Methodsmentioning

confidence: 99%

“…Determining the UBC of piles requires an exact experimental apparatus and is very expensive. The geotechnical properties of the basic soil, loading conditions and pile dimensions all have an effect on the UBC of the piles (Das 2015). The inherent variability and uncertainty of these factors complicates the estimation of the UBC of the piles.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Estimation of ultimate bearing capacity of driven piles in c-φ soil using MLP-GWO and ANFIS-GWO models: a comparative study

et al. 2020

View full text Add to dashboard Cite

A new forecast method is proposed in order to improve the estimation accuracy of the ultimate bearing capacity (UBC) of single driven piles. The performance of the adaptive neuro-fuzzy inference system (ANFIS) and multilayer perceptron (MLP) models have been boosted using gray wolf optimization (GWO). To train the models, data were used from 100 driven piles in c-u soil in different locations. The input parameters were pile area (m 2 ), pile length (m), flap number, average cohesion (kN/m 2 ) and friction angle (°), average soil specific weight (kN/m 2 ) and average pile-soil friction angle (°), and the output was UBC. The results showed that both the MLP and ANFIS methods had good abilities to predict the UBC of the piles; however, the MLP-GWO model with a topology of 7 9 10 9 10 9 1 provided better results. The performance indices of this model were a RMSE of 1.86 kN and R 2 of 0.991 for the test data. The validity of the MLP-GWO model was tested using a new experimental dataset, and the difference between actual and estimated UBC was very low (about 2%) and confirmed the high accuracy of the model. It was observed that the theoretical methods underestimated the UBC significantly, while the proposed model estimated the UBC with high accuracy. Sensitivity analysis confirmed that the pile area and length were the most effective factors for estimation of UBC.Keywords Piles Á ANFIS Á Gray wolf optimization Á Ultimate bearing capacity Á Sandy soil Á Clay soil Communicated by V. Loia.

show abstract

“…Equations ( 9) and (10) were used to determine the theoretical UBC of a single pile. The details about these calculations can be found in Das (2015).…”

Section: Comparison Of Best Model and Theoretical Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Estimation of ultimate bearing capacity of driven piles in c-φ soil using MLP-GWO and ANFIS-GWO models: a comparative study

et al. 2020

View full text Add to dashboard Cite

show abstract

“…As the use of FN [24,25], and MARS [25][26][27] is limited in geotechnical, these are described briefly in the following sections.…”

Section: Methodsmentioning

confidence: 99%

“…The FN introduced by Castillo [28,29], Castillo and Ruiz-Cobo [30] and Castillo et al [31,32] is a powerful extension of the ANNs and is advantageous to ANNs. Owing to their advantages over ANNs, FNs have been successfully used in various fields such as petroleum engineering [33], signal processing, pattern recognition, function's approximations [34] real-time flood forecasting, science, bioinformatics, medicine [35] structural engineering [36], transportation engineering [37] and geotechnical engineering [24,25].…”

Section: Functional Networkmentioning

confidence: 99%

Prediction of Maximum Dry Density and Unconfined Compressive Strength of Cement Stabilised Soil Using Artificial Intelligence Techniques

Suman

Mahamaya

Das

2016

Int. J. of Geosynth. and Ground Eng.

Self Cite

View full text Add to dashboard Cite

The soft soil that has not enough in situ bearing capacity needs proper stabilization before any construction can be done on this soil. Cement stabilization has been found to be an effective method to improve the soil properties by many researchers. The strength development in a cement stabilized mix depends on a number of factors such as the soil properties, the water-cement ratio and the percentage of cement in the mix. In the present study an attempt is made to develop prediction model to determine the maximum dry density (MDD) and the unconfined compressive strength (UCS) of cement stabilized soil with the use of two recently developed artificial intelligence (AI) techniques; functional networks (FN) and multivariate adaptive regression splines (MARS). Database previously available in the literature was used to develop the prediction models. Based on different statistical performance criteria, it was found that the FN and MARS techniques, are better at prediction of MDD and UCS as compared to previously used AI techniques, artificial neural network and support vector machine. The prediction model presented here is more comprehensive and can be used by professional engineers.

show abstract

“…In order to evaluate the relative efficacy of the CRIM and BHS model in prediction of concentration of suspensions, a ranking system reliant on several statistical parameters through three criteria [70] has been used. In this method, each model is assigned a numeric respectively [72]. Based on the above concept, the model having µ and SD value close to 1.0 and 0, respectively, is ranked higher than the other one.…”

Section: Ranking Of Modelsmentioning

confidence: 99%

Dielectric spectroscopy measurements on kaolin suspensions for sediment concentration monitoring

et al. 2018

View full text Add to dashboard Cite

Sedimentation along with consolidation processes dictate the in situ engineering and hydraulic behavior of a particulate system such as soil. With this in view, the present investigation discusses about the application of dielectric measurements in relation to sediment concentration measurements for fine grained soils. An in-house set up comprising of open ended coaxial probes and vector network analyzer has been used to measure the dielectric behavior of kaolin suspensions in tap and deionized water. These have been further analyzed to furnish suspended sediment concentration, pore water conductivity and shape factors utilizing Complex Refractive Index Model (CRIM) and Bruggeman-Hanai-Sen (BHS) model, through the implementation of an optimization scheme. Furthermore, measured and estimated suspended sediment concentrations showed good agreement with each other in terms of statistical parameters, and a ranking of models approach reliant on three statistical criteria revealed that, CRIM outperforms BHS model for estimating sediment concentrations.

show abstract

Prediction of Lateral Load Capacity of Pile in Clay Using Multivariate Adaptive Regression Spline and Functional Network

Cited by 30 publications

References 32 publications

Estimation of ultimate bearing capacity of driven piles in c-φ soil using MLP-GWO and ANFIS-GWO models: a comparative study

Estimation of ultimate bearing capacity of driven piles in c-φ soil using MLP-GWO and ANFIS-GWO models: a comparative study

Prediction of Maximum Dry Density and Unconfined Compressive Strength of Cement Stabilised Soil Using Artificial Intelligence Techniques

Dielectric spectroscopy measurements on kaolin suspensions for sediment concentration monitoring

Contact Info

Product

Resources

About