Evaluation of the Change in Undrained Shear Strength in Cohesive Soils due to Principal Stress Rotation Using an Artificial Neural Network

Wrzesiński, Grzegorz; Sulewska, Maria Jolanta; Lechowicz, Zbigniew

doi:10.3390/app8050781

Cited by 11 publications

(8 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To determine the change of soil shear strength parameters depending on the principal stress rotation α, there are many empirical equations [32][33][34][35][36]. However, the use of these equations requires the prior determination of many physical properties of the investigated soil and is therefore rarely used.…”

Section: Discussionmentioning

confidence: 99%

Archives of Civil Engineering

Wrzesiński

2021

View full text Add to dashboard Cite

The paper presents the phenomenon of principal stress rotation in cohesive subsoil resulting from its loading or unloading and the impact of this phenomenon on the values of soil shear strength parameters: undrained shear strength τfu, effective cohesion c', effective angle of internal friction φ'. For this purpose, tests in a triaxial apparatus and torsional shear hollow cylinder apparatus on selected undisturbed cohesive soils: sasiCl, saclSi, clSi, Cl, characterized by different index properties were carried out. Soil shear strength parameters were determined at angle of principal stress rotation α equal to 0° and 90° in tests in triaxial apparatus and α equal to 0°, 15°, 30°, 45°, 60°, 75°, 90° in tests in torsional shear hollow cylinder apparatus. The results of laboratory tests allow to assess the influence of the principal stress rotation on the shear strength parameters that should be used to determine the bearing capacity of the subsoil.

show abstract

Section: Discussionmentioning

confidence: 99%

Archives of Civil Engineering

Wrzesiński

2021

View full text Add to dashboard Cite

show abstract

“…[12] appraised a similar relationship for refilled soils using relative compaction and moisture content. Wrzesiński et al (2018) appraised the shear strength evaluation of fine-grained cohesive soils using artificial neural networks [13]. A Risk model for the prediction of subsidence along railway lines based on Artificial Neural Networks (ANN) employing Multi-Layer Perceptron (MLP) and support vector machine (SVM) has been developed by Le and Oh (2018) [14].…”

Section: Literature Reviewmentioning

confidence: 99%

Knowledge Based Prediction of Standard Penetration Resistance of Soil Using Geotechnical Database

Arshid

2021

Civ Eng J

View full text Add to dashboard Cite

The current study aimed at predicting standard penetration resistance (N) of soil using particle sizes and Atterberg's limits. The geotechnical database was created subsequent to the field and laboratory testing. The sample collection points were distributed in a mesh grid pattern to have uniform sampling consistency. Artificial Neural Networks (ANN) were trained on the database to build a knowledge-based understanding of the interrelation of the given soil parameters. To check the efficacy of the model, the validation was carried out by predicting standard penetration resistance (N) for another 30 samples which were not included in the training data (444 samples). The trained ANN model has been found to predict N values in close agreement with the N values measured in the field. The novelty of the research work is the standard penetration prediction employing basic physical properties of soil. This proves the efficacy of the proposed model for the target civil engineering application. Doi: 10.28991/CEJ-SP2021-07-01 Full Text: PDF

show abstract

“…Several related studies such as in determining foundation behavior like prediction of shallow foundation reliability [11], pile raft foundation [12], axial capacity of pile foundation [13], shaft resistance [14], elastic settlement [15], settlement shallow foundation [16] and loading-unloading pile static load [17]. Other related research such as predicting soil physical and mechanical properties like prediction of CBR value [18], uniaxial compressive strength [19], undrained shear strength [20]- [21], bearing capacity [22]- [23], unit weight [24], compression index & compression ratio [25], classification [26], compression coefficient [27], liquefaction [28], and electrical resistivity of soil [29]. ANN is also used in prediction of dynamic compaction [30] and slope stability [31].…”

Section: Table 1 Summarize Of Literature Reviewmentioning

confidence: 99%

Prediction of standard penetration test value on cohesive soil using artificial neural networks

Nugroho¹,

Fernando²,

Suryanita³

2021

Jurnal Informatika

View full text Add to dashboard Cite

Soil investigation is the main key in starting a construction. Standard Penetration Test (SPT) and Cone Penetration Test (CPT) are field tests that are often used in estimating soil parameters for foundation design purposes. The SPT value shows a correlation with the CPT value and other soil parameters. At present, there have been many conventional correlations examining these correlations, but the nonlinear nature of the soil due to very complex soil formations means that this correlation cannot be used in all situations. Artificial neural networks (ANN) are often used to estimate a complex and nonlinear value. In this study, that will predict the value of SPT on cohesive soil based on CPT test data and soil physical properties using artificial neural network capabilities using the Backpropagation algorithm and the activation function is bipolar sigmoid. This study uses 284 data from several places in Sumatra Island, Indonesia with data input are tip resistance (qc), shaft resistance (fs), effective overburden pressure (σ'0), percentage of liquid limit, plastic limit, sand, silt and clay. This study shows that the artificial neural network is able and effective in predicting the N-SPT value with a small error value and a strong regression equation. In this study, RMSE 3,441, MAE 2,318 and R 2 0,9451 for training data and RMSE 2,785, MAE 2,085, R 2 0,9792 for test data. This model is hereinafter referred to as NN_Nspt(C).

show abstract

Evaluation of the Change in Undrained Shear Strength in Cohesive Soils due to Principal Stress Rotation Using an Artificial Neural Network

Cited by 11 publications

References 35 publications

Archives of Civil Engineering

Archives of Civil Engineering

Knowledge Based Prediction of Standard Penetration Resistance of Soil Using Geotechnical Database

Prediction of standard penetration test value on cohesive soil using artificial neural networks

Contact Info

Product

Resources

About