Prediction Of Unconfined Compressive Strength Research Articles

Prediction of Unconfined Compressive Strength of Stabilized Sand Using Machine Learning Methods

Prediction of Unconfined Compressive Strength of Stabilized Sand Using Machine Learning Methods

Prediction of unconfined compressive strength of lime treated soils

ABSTRACT Robust models based on Artificial Neural Network and simplified linear regression were proposed to predict the Unconfined Compressive Strength (UCS) of Lime Treated Soils (LTS). In total, an experimental database using 1120 test specimens was created. Critical examination of the collected experimental data suggested that there are eight key parameters that govern the attained strength gain. These input parameters are liquid limit, plastic limit, dry unit weight, water content, fine content, lime content, curing temperature and curing time whereas the only output dependent parameter is the UCS. The parameters of the proposed model including weights, biases and transfer functions were successfully converted to an explicit mathematical model relating the UCS with the key input parameters. Based on the results of the statistical evaluation, it was shown that a three-layered Artificial-Neural-Network model with 19 hidden neurons was capable to predict the UCS of (LTS) with a high degree of accuracy that was better than that achieved by the developed regression model. A coupling effect of the input parameters and weights analysis were conducted for the developed Artificial-Neural-Network-model to assess the importance of the key parameters. Analysis of weights of the model showed that curing time was the most significant factor affecting strength gain.

Prediction of unconfined compressive strength of cement–lime stabilized soil using artificial neural network

Prediction of unconfined compressive strength of cement–lime stabilized soil using artificial neural network

Prediction of unconfined compressive strength of cement–fly ash stabilized soil using support vector machines

Prediction of unconfined compressive strength of cement–fly ash stabilized soil using support vector machines

Estimation of unconfined compressive strength of marine clay modified with recycled tiles using hybridized extreme gradient boosting method

An accurate evaluation of the clay's properties when mixed with recyclable materials is the end objective of many geotechnical experimental efforts. However, experimental studies need time, cost, and laborious efforts, which could be eliminated using alternative methods. This study concentrated on the prediction of unconfined compressive strength (UCS) of marine clay (MC) amended with recycled tiles (RT). For this aim, four novel hybridized models were developed for estimating UCS of MC modified with RT, with the integration of Adaptive neuro-fuzzy inference system (ANFIS), support vector regression (SVR), random forest (RF), and extreme gradient boosting (XGB) with Aquila optimizer (AO) algorithm. The results illustrate that all four models contain reliable precision in UCS prediction procedure. Between all models, AO-XGB model has the smallest values of scatter index (SI) than others (Excellent performance), with SITrain=0.0247 and SITest=0.02483. It was clear that the AO-XGB model contains the least uncertainty, with 9.735 and 1.44 for the testing and training dataset, which depicts its greater generalization capability compared to others. All in all, by considering the explanations of results and comparison with published literature, the hybridized AO-XGB model could outperform other models to be practiced in practical usage.

Machine Learning-Based Prediction of Unconfined Compressive Strength of Sands Treated by Microbially-Induced Calcite Precipitation (MICP): A Gradient Boosting Approach and Correlation Analysis

The current study applies a soft-computing approach based on the gradient boosting method to predict the unconfined compressive strength (UCS) of sands treated with microbially-induced calcite precipitation (MICP). A 10-fold cross-validation method and hyperparameter tuning are performed to find the optimal architecture of the gradient boosting algorithm. A total of 402 data of unconfined compression tests performed on biocemented sands are utilized in this study. The dataset includes eight input parameters: median sand particle size, uniformity coefficient of sand, initial void ratio, calcium chloride concentration, urea concentration, urease activity, optical density of bacteria, and calcite content. The finding demonstrates that the gradient boosting method outperformed five commonly used machine learning algorithms (artificial neural networks, random forests, k-nearest neighbors, support vector regression, and decision trees) in predicting the UCS of biocemented sands. Using the gradient boosting, the predicted UCS has a strong correlation with the actual values (R2 = 0.95). Moreover, a series of correlation and feature importance analyses are carried out over the dataset. The relationships between unconfined compressive strength, calcite content, and initial void ratio are discussed within the article. Furthermore, some guidelines are provided for assessing the effect of environmental factors on the UCS of biocemented sands. For further study, the limitations of this study regarding the insufficiency of data for correlation and environmental modification are addressed.

Closed-Form Equation for Estimating Unconfined Compressive Strength of Granite from Three Non-destructive Tests Using Soft Computing Models

The use of three artificial neural network (ANN)-based models for the prediction of unconfined compressive strength (UCS) of granite using three non-destructive test indicators, namely pulse velocity, Schmidt hammer rebound number, and effective porosity, has been investigated in this study. For this purpose, a sum of 274 datasets was compiled and used to train and validate three ANN models including ANN constructed using Levenberg–Marquardt algorithm (ANN-LM), a combination of ANN and particle swarm optimization (ANN-PSO), and a combination of ANN and imperialist competitive algorithm (ANN-ICA). The constructed ANN-LM model was proven to be the most accurate based on experimental findings. In the validation phase, the ANN-LM model has achieved the best predictive performance with R = 0.9607 and RMSE = 14.8272. Experimental results show that the developed ANN-LM outperforms a number of existing models available in the literature. Furthermore, a Graphical User Interface (GUI) has been developed which can be readily used to estimate the UCS of granite through the ANN-LM model. The developed GUI is made available as a supplementary material.

Estimating unconfined compressive strength and Young’s modulus of carbonate rocks from petrophysical properties

Geomechanical studies in carbonate rocks often require the use of log relations to obtain mechanical properties when laboratory measurements are not available. This study presents a new set of equations to predict the unconfined compressive strength (UCS) and Young’s modulus (E) for three carbonate lithologies: limestone, dolomite, and chalk. The equations are developed based on more than 700 mechanical-physical tests of carbonate rocks across different geological settings and geographical locations. The obtained results confirmed that petrophysical properties are consistent in determining the carbonate mechanical properties. The relations are developed based on either a single parameter or multiple parameters where coefficient of determination was improved for the multiple parameter relations. Scattering in the prediction of UCS and E is expected due to the carbonate heterogeneity in mineralogy, porosity, fabric as well as testing conditions. Thus, the applicable range of each relation is investigated. To test whether improved fits are achieved in this study, the relations are compared with the literature, and they showed a higher coefficient of determination. The proposed relations can be generally used as a starting point for UCS and E estimate when carbonate mechanical properties from laboratory tests are not available.

Hybrid gradient boosting with meta-heuristic algorithms prediction of unconfined compressive strength of stabilized soil based on initial soil properties, mix design and effective compaction

In the investigation, hybrid Gradient Boosting (GB) with four optimization techniques named Simulated Annealing (SA), Random Restart Hill Climbing (RRHC), Particle Swarm Optimization (PSO) and Evolution Strategy Optimization (ESO) are used to develop machine learning models for predicting unconfined compressive strength (UCS) of stabilized soils based on initial soil properties, mix design and effective compaction. The results show that the hybrid model GB_PSO can successfully predict the UCS of stabilized soils with high performance R2 = 0.9655, RMSE = 0.1633 MPa for testing part. The feature importance analyses are performed with using GB_PSO based Permutation Importance of Sklearn library and Shapley Additive Explanations (SHAP value), which reveal that maximum dry density (MDD), linear shrinkage (LS), and Gravel content are the most important characteristics in the UCS prediction performance of the GB_PSO model. The partial dependence plot (PDP) analysis consisting of PDP 1D and PDP 2D show respectively the impact way of each feature on the UCS and the interactions between initial soil properties, mix design and effective compaction in the UCS improvement of stabilized soil. The PDP analysis show that (i) the LS is the most important criterion in determining the success of improving the UCS of stabilized soil, (ii) the predominance of effective compaction over other conditions on the improvement of UCS. The present investigation can be considered to be new insights for better understanding process of stabilized soil and UCS improvement.

Prediction of unconfined compressive strength and California bearing capacity of cement- or lime-pozzolan-stabilised soil admixed with crushed stone waste

ABSTRACT So far, a limited number of studies have been published on utilisation of crushed stone waste, cement, lime and pozzolan as stabilisers for soil stabilisation. The research conducts soil engineering properties and strength test for various contents of crushed stone waste, cement, lime and pozzolan under various curing times. Increasing the pozzolan or cement content resulted in an increase in UCS; however, the UCS increased as the lime content increased from 0% to 5% and then decreased as lime content violated from 5%. An increase in the granite crushed stone content from 0% to 10% resulted in an increase in the UCS value. The unsoaked CBR and UCS values are almost 1.37 and 1.24 times more than the corresponding soaked ones for all cases, respectively. The CBR value increased with the increase in the pozzolan, lime or cement content. The cement content has more important influence on the increase in CBR value than the lime or pozzolan content. The multi-layer perceptron (MLP) neural network and non-linear regression (NLR) techniques are employed to develop models to predict the CBR and UCS values of the stabilised specimens.

Feasibility of lime and biopolymer treatment for soft clay improvement: a comparative and complementary approach

Highway pavement infrastructure projects which involve soil improvement should be executed, ensuring environmental sustainability. In the present study, guar gum (GG) and lime were assessed for the purpose of soft clay stabilization. The experimental program for the soil stabilization employed a two-stage process. The initial stage involves treatment of the soil with various percentages of lime (3, 5, 7, and 9%) and GG (0.6, 1.0, 1.4, and 1.8%), maintaining the same material acquisition cost and considering curing (0, 7, 14, and 28 days) for the unconfined compressive strength (UCS). In the second experimental stage, a complementary approach in which 3% lime was combined with GG at various percentages (0.1, 0.2, and 0.3%) was employed. The tests conducted include UCS, California bearing ratio (CBR), and strength loss resistance (SLR). Results show that the sole use of lime and GG resulted in significant improvement in the UCS, albeit lime was better. While UCS improved with curing time for the lime-stabilized soil, UCS gain for GG occurred only for up to 7 days curing because biodegradation of GG by microbes in the soil ensues on further curing. Lime-GG stabilization resulted in better UCS and CBR improvement with curing than lime stabilization; however, lime stabilization yielded better SLR. The optimum additive content for strength improvement was obtained at 3% lime + 0.3% GG. Microstructural analysis indicated cementation in the stabilized soil. Predictive models for the UCS were developed based on regression methods. Model evaluation revealed that Gaussian process model provided the best UCS prediction.

Prediction of undrained shear strength and correlation in between soil parameters

Correlation of soil parameters has undeniable benefit in the determination of engineering properties of soil to solve problems in geotechnical Engineering area. The tests were conducted within geotechnical laboratory. These tested soil parameters, used in the correlation analysis are unconfined compressive strength, bulk unit weight and dry unit weight. The aim of this study is proposing a relationship in between the strength parameter with some of the index properties of soils using statistical regression analysis. The linear regression analyses have been done for prediction of unconfined compressive strength (qu ) from bulk and dry unit weight as model-1 and model-2 respectively. And dry unit weight was predicted from bulk unit weight as model-3. Model-4 represents the multiple linear regression analysis to predict qu . The health of developed models is measured by coefficient of determination (R 2) values. Though, model-1, model-2, model-3 and model-4 have R – squared values of 0.9112, 0.9333, 0.9109 and 0.9452 respectively. Therefore, they are correlated strongly and positively. The prediction of unconfined compressive strength of these soils correlated in linear regression, are fairly determined with Model-2 compared with model-1 and model-4 (MLR).

Prediction of Unconfined Compressive Strength and Flexural Strength of Cement-Stabilized Sandy Soils: A Case Study in Vietnam

Stabilization of sand by the deep mixing method increases its unconfined compressive strength (UCS) so that it can be used as a foundation for infrastructure. This paper presents research work on physicomechanical properties of soil–cement columns installed in the central area of Vietnam, which consists of sandy clay, fine sand, medium sand, and coarse sand. Two types of cement were mixed with these soils in amounts of 150–350 kg/m3 at a water-cement ratio of 0.6. Approximately 80 soil–cement samples were prepared and cured at standard moist conditions and then tested for unconfined compressive strengths and flexural strengths at 7, 14, 28, and 56 days. The maximum unconfined compressive strength of the soil–cement was 10 MPa after 56-day curing for the coarse sand mixed with 350 kg/m3 cement. The Bayesian Model Averaging and the Principal Component Analysis Methods were used to evaluate the influence of different variables on the UCS of the cement-stabilized soil. The analysis shows that the UCS of the soil–cement depended on the contents of SiO2, SO3, K2O in the soil, the soil grain size, the cement content, and the curing time. The prediction equations allow the determination of unconfined compressive strength and flexural strength of cement-stabilized sand by the wet mixing method used as a ground improvement method for foundations.

Prediction of unconfined compressive strength of cement stabilized pavement materials

This paper evaluated and justified suitable prediction equations for unconfined compressive strength (UCS) of cement stabilized pavement materials. Equations by multiple linear regression analysis were also proposed. Data including pavement recycling base and subbase layers were collected from the Bureau of Material, Analysis, and Inspection, Department of Highways, Thailand. Multiple linear regression was conducted using the SPSS software. Three equations obtained from multiple linear regression and past researches were compared. Two criteria were considered in the selection of equations in order to check the accuracy and precision of each equation. First criterion was based on the predicted UCS vs. actual UCS graph. The slope and interception values of each graph were evaluated. Second criterion used two indices: ranking distance (RD) and ranking index (RI). For a good correlation, both these indices shall approach zero. By considering the statistical analysis outputs from the two criteria, a relationship between UCS and California Bearing Ratio – water cement ratio [CBR/(w/c)] proposed by Sunitsakul in 2012 was justified as a suitable equation to predict the UCS of cement stabilized pavement materials. The study also confirmed that the relationship proposed by Sawangsuriya in 2016 for fine-grained soil with plasticity index was not appropriate for the prediction of UCS because the majority of the samples were non-plastic.

Artificial neural network (ANN) approach to predict unconfined compressive strength (UCS) of oil and gas well cement reinforced with nanoparticles

The prediction of unconfined compressive strength (UCS) of oil well cement class “H” based on the artificial neural network (ANN) modeling approach is presented in this study. 195 cement samples were embedded with varying dosages of strength enhancing pre-dispersed nanoparticles consisting of nanosilica (nano-SiO2), nanoalumina (nano-Al2O3), and nanotitanium dioxide (nano-TiO2) at various simulated wellbore temperatures. The efficacy of the pre-dispersed nanoparticle solutions was analyzed by transmission electron microscope (TEM) images. Nano-SiO2 and nano-Al2O3 displayed excellent dispersibility throughout the solution. However, nano-TiO2 readily agglomerates which, at high concentrations, is detrimental to the UCS of cement. 70% of the data set was used to train the ANN model, 15% was used for validation, and 15% was used to test the model. The model consisted of one input layer with five nodes, one hidden layer with 12 nodes, and one output layer with one node. 12 nodes in the hidden layer resulted in the lowest mean squared error (MSE). The model parameters were saved and used after seven epochs during training, at which point the validation error began to increase leading to overfitting. The statistical performance measures consisting of MSE, the square root of the coefficient of determination (R), and the mean absolute percentage error (MAPE) showed values close to zero, one, and less than five percent, respectively. The statistical performance measures of the ANN model displayed superior results when compared to the measures obtained by the multi-linear (MLR) and random forest (RF) regression algorithms. The developed ANN model displays high predictive accuracy and can replace, or be used in combination with, destructive UCS tests which can save the petroleum industry time, resources, and capital.

Prediction of unconfined compressive strength of cement-stabilized sandy soil in Vietnam using artificial neural networks (ANNs) model

ABSTRACT The unconfined compressive strength (UCS) of cement-stabilized soil depends on the particle size distribution, the soil chemistry composition, the cement content, the water content, and the curing time. Determining the UCS of soil-cement material is an important task in the design and construction of infrastructure supported on marginal soils that require ground improvement. In this research, the Artificial Neural Network (ANN) technique was applied to generate the UCS prediction model in relation to the selected parameters. A sensitivity analysis was conducted to examine the range of the contribution of variables. As a result, a statistical analysis shows that the proposed model developed in this study is accurate and reliable with a high correlation coefficient and low root mean squared errors. The UCS prediction model also satisfies well the external criteria; hence it illustrates the great potential of the predictive ability of the ANN technique for geotechnical parameters. The ANN-based model shows that the cement content and the percentage of the soil particle passing sieve 0.5 mm are the most important variables affecting the UCS value. The research results could be used for estimating the UCS of cement-stabilized sandy soil in situ and laboratory conditions.

Soil Unconfined Compressive Strength Prediction Using Random Forest (RF) Machine Learning Model

Aims: Understanding the mechanical performance and applicability of soils is crucial in geotechnical engineering applications. This study investigated the possibility of application of the Random Forest (RF) algorithm – a popular machine learning method to predict the soil unconfined compressive strength (UCS), which is one of the most important mechanical properties of soils. Methods: A total number of 118 samples collected and their tests derived from the laboratorial experiments carried out under the Long Phu 1 power plant project, Vietnam. Data used for modeling includes clay content, moisture content, specific gravity, void ratio, liquid limit and plastic limit as input variables, whereas the target is the UCS. Several assessment criteria were used for evaluating the RF model, namely the correlation coefficient (R), root mean squared error (RMSE) and mean absolute error (MAE). Results: The results showed that RF exhibited a strong capability to predict the UCS, with the R value of 0.914 and 0.848 for the training and testing datasets, respectively. Finally, a sensitivity analysis was conducted to reveal the importance of input parameters to the prediction of UCS using RF. The specific gravity was found as the most affecting variable, following by clay content, liquid limit, plastic limit, moisture content and void ratio. Conclusion: This study might help in the accurate and quick prediction of the UCS for practice purpose.

Prediction of unconfined compressive strength and deformation modulus of weak argillaceous rocks based on the standard penetration test

Standard penetration test is often used as an index for prediction of geomaterial elastic and strength properties. It consists of releasing a 63.5 kg hammer from a specified distance of 762 mm on a series of connected drill rods. The N-value is defined after a total 457 mm of penetration is achieved by counting the below counts for the last 300 mm of penetration. This required penetration is not often achieved in weak rocks due to their relatively large compressive strength. To eliminate the need for achieving a total required 457 mm of penetration, a novel approach is introduced where the rate of penetration of the split spoon sampler is used for the characterization of the engineering properties of the weak argillaceous rocks. The rate of penetration is defined as the slope of the final segment of the blow count versus penetration plot. The test results show that the average penetration rate at each test depth approaches a relatively constant value as the penetration increases. It is found that penetration rate is affected by the unconfined compressive strength, deformation modulus, and water content of the rock mass as well as the mean effective stress at the elevation of each test. Using in situ tests from 21 weak rock sites in Illinois, United States, models are proposed for the prediction of deformation modulus and unconfined compressive strength based on the penetration rate. The models account for the influence of mean effective stresses and the in situ water content of rock.

Statistical Analysis for Prediction of Unconfined Compressive Strength of Synthetic Fibre-Reinforced Clayey Soil

In order to obtain a simpler and more reliable prediction model of unconfined compressive strength (UCS) of soil for application, the UCS data of synthetic fibre-reinforced clayey soil (FRS) were analyzed by statistical method, which were collected from previous studies. Based on the data sources, the failure modes of FRS were analyzed, it can be verified that the slippage of fibre is the major failure mode for UCS test. Six principal parameters of soil and fibre were selected for the new models. The α model and β model were proposed to predict the UCS values of FRS by means of multivariate nonlinear regression analysis. Moreover, the UCS data collected from different studies were used to evaluate the two models and the α–β model was proposed for modification. It was shown from the results that the three models were all reasonable in statistics. The α–β model can be considered as reference for application and the suggested value of a is less than 0.5.

Mechanical and Physical Based Artificial Neural Network Models for the Prediction of the Unconfined Compressive Strength of Rock

Basalt rocks as building stones were used in many historical buildings in Jordan, and maintenance of these buildings is usually required with time. As part of the effort to collect the necessary information that is needed for future works in repair/strengthen the basaltic structures against any possible future damage. The dry density, Ultrasonic Pulse Velocity, Schmidt Hammer Rebound test, Brazilian Tensile Strength Test, Slake durability, and Point Load test were recorded for specimens tested in the lab to develop indirect methods of estimating the rocks Unconfined Compressive Strength (UCS). Simple regression (SR) analyses were performed to establish correlations between UCS and the results of each above-mentioned rock indices. The SR results showed that a regression model with multiple inputs is needed. In this study, the Back Propagation-Artificial Neural Network (BP-ANN) approach was utilized to predict the USC of Basalt Rock. Two ANN models were developed; one using the physical properties of rocks and the other one using the mechanical properties of rocks. Part of the data collected was used to train the ANN, and a set of independent data was used to validate the developed model. The performance of the ANN model in predicting UCS was compared to that of Multivariate Regression (MVR). The obtained results showed that the ANN model gave higher prediction performance compared to other models. A sensitivity analysis for the developed ANN model was performed to verify the importance of each input. The prediction of UCS can be used to design the proper conservation and repair/strengthen strategies that will allow dealing with the current conditions and the future natural hazards to which these structures are exposed.