Gaussian Process Regression Technique to Estimate the Pile Bearing Capacity

Enhanced prediction of bolt support drilling pressure using optimized Gaussian process regression

This study introduces a novel method for predicting drilling pressure in bolt support systems by optimizing Gaussian process time series regression (GPR) using hybrid optimization algorithms. The research initially identified significant variations in prediction outcomes based on different kernel functions and historical points combinations in the GPR algorithm. To address this, we explored 160 distinct schemes combining 10 kernel functions and 16 historical points for numerical analysis. Applying three hybrid optimization algorithms-Genetic Algorithm-GPR (GA-GPR), Particle Swarm Optimization-GPR (PSO-GPR), and Ant Colony Algorithm-GPR (ACA-GPR)-we iteratively optimized these key parameters. The PSO-GPR algorithm emerged as the most effective, achieving an 80% prediction accuracy with a deviation range of 1-2 MPa, acceptable in practical drilling operations. This optimization led to the RQ kernel function with 18 historical points as the optimal combination, yielding an RMSE value of 0.0047246, in contrast to the least effective combination (E kernel function with 6 historical points) producing an RMSE of 0.035704. The final outcome of this study is a robust and efficient prediction system for underground bolt support drilling pressure, verified through practical application. This approach significantly enhances the accuracy and efficiency of support systems in geotechnical engineering, demonstrating the practical applicability of the PSO-GPR model in real-world scenarios.

Interpretable Predictive Modelling of Basalt Fiber Reinforced Concrete Splitting Tensile Strength Using Ensemble Machine Learning Methods and SHAP Approach

Basalt fibers are a type of reinforcing fiber that can be added to concrete to improve its strength, durability, resistance to cracking, and overall performance. The addition of basalt fibers with high tensile strength has a particularly favorable impact on the splitting tensile strength of concrete. The current study presents a data set of experimental results of splitting tests curated from the literature. Some of the best-performing ensemble learning techniques such as Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), Random Forest, and Categorical Boosting (CatBoost) have been applied to the prediction of the splitting tensile strength of concrete reinforced with basalt fibers. State-of-the-art performance metrics such as the root mean squared error, mean absolute error and the coefficient of determination have been used for measuring the accuracy of the prediction. The impact of each input feature on the model prediction has been visualized using the Shapley Additive Explanations (SHAP) algorithm and individual conditional expectation (ICE) plots. A coefficient of determination greater than 0.9 could be achieved by the XGBoost algorithm in the prediction of the splitting tensile strength.

Modeling the pile settlement using the Integrated Radial Basis Function (RBF) neural network by Novel Optimization algorithms: HRBF-AOA and HRBF-BBO

The Pile movement is one of the most crucial matters in designing piles and foundations that need to be estimated for any project failure. Over the variables used in forecasting Pile Settlement, many methods have been introduced to appraise it. However, existing a wide range of theoretical strategies to investigate the pile subsidence, the soil-pile interactions are still ambiguous for academic researchers. Most studies have tried to work out the subsidence rate in piles after loading passing time by artificial intelligence methods. Generally, the Artificial Neural Network (ANN) has drawn attention to show the actual views of pile settlement over the loading phase vertically. This research aims to present the Hybrid Radial Basis Function neural network integrated with the Novel Arithmetic Optimization Algorithm and Biogeography-Based Optimization to calculate the optimal number of neurons embedded in hidden layers. The transportation network of Klang Valley, Mass Rapid Transit in Kuala Lumpur, Malaysia, was chosen to analyze the piles’ settlement and earth features using HRBF-AOA and HRBF-BBO scenarios. Over the prediction process, the R-values of HRBF-AOA and HRBF-BBO were obtained at 0.9825 and 0.9724, respectively. The MAE also shows a similar trend as 0.2837 and 0.323, respectively.

Prediction of Pile Bearing Capacity Using XGBoost Algorithm: Modeling and Performance Evaluation

The major criteria that control pile foundation design is pile bearing capacity (Pu). The load bearing capacity of piles is affected by the various characteristics of soils and the involvement of multiple parameters related to both soil and foundation. In this study, a new model for predicting bearing capacity is developed using an extreme gradient boosting (XGBoost) algorithm. A total of 200 driven piles static load test-based case histories were used to construct and verify the model. The developed XGBoost model results were compared to a number of commonly used algorithms—Adaptive Boosting (AdaBoost), Random Forest (RF), Decision Tree (DT) and Support Vector Machine (SVM) using various performance measure metrics such as coefficient of determination, mean absolute error, root mean square error, mean absolute relative error, Nash–Sutcliffe model efficiency coefficient and relative strength ratio. Furthermore, sensitivity analysis was performed to determine the effect of input parameters on Pu. The results show that all of the developed models were capable of making accurate predictions however the XGBoost algorithm surpasses others, followed by AdaBoost, RF, DT, and SVM. The sensitivity analysis result shows that the SPT blow count along the pile shaft has the greatest effect on the Pu.

Factors Influencing Pile Friction Bearing Capacity: Proposing a Novel Procedure Based on Gradient Boosted Tree Technique

In geotechnical engineering, there is a need to propose a practical, reliable and accurate way for the estimation of pile bearing capacity. A direct measure of this parameter is difficult and expensive to achieve on-site, and needs a series of machine settings. This study aims to introduce a process for selecting the most important parameters in the area of pile capacity and to propose several tree-based techniques for forecasting the pile bearing capacity, all of which are fully intelligent. In terms of the first objective, pile length, hammer drop height, pile diameter, hammer weight, and N values of the standard penetration test were selected as the most important factors for estimating pile capacity. These were then used as model inputs in different tree-based techniques, i.e., decision tree (DT), random forest (RF), and gradient boosted tree (GBT) in order to predict pile friction bearing capacity. This was implemented with the help of 130 High Strain Dynamic Load tests which were conducted in the Kepong area, Malaysia. The developed tree-based models were assessed using various statistical indices and the best performance with the lowest system error was obtained by the GBT technique. The coefficient of determination (R2) values of 0.901 and 0.816 for the train and test parts of the GBT model, respectively, showed the power and capability of this tree-based model in estimating pile friction bearing capacity. The GBT model and the input selection process proposed in this research can be introduced as a new, powerful, and practical methodology to predict pile capacity in real projects.

Toward the accurate estimation of elliptical side orifice discharge coefficient applying two rigorous kernel-based data-intelligence paradigms

In the present study, two kernel-based data-intelligence paradigms, namely, Gaussian Process Regression (GPR) and Kernel Extreme Learning Machine (KELM) along with Generalized Regression Neural Network (GRNN) and Response Surface Methodology (RSM), as the validated schemes, employed to precisely estimate the elliptical side orifice discharge coefficient in rectangular channels. A total of 588 laboratory data in various geometric and hydraulic conditions were used to develop the models. The discharge coefficient was considered as a function of five dimensionless hydraulically and geometrical variables. The results showed that the machine learning models used in this study had shown good performance compared to the regression-based relationships. Comparison between machine learning models showed that GPR (RMSE = 0.0081, R = 0.958, MAPE = 1.3242) and KELM (RMSE = 0.0082, R = 0.9564, MAPE = 1.3499) models provide higher accuracy. Base on the RSM model, a new practical equation was developed to predict the discharge coefficient. Also, the sensitivity analysis of the input parameters showed that the main channel width to orifice height ratio (B/b) has the most significant effect on determining the discharge coefficient. The leveraged approach was applied to identify outlier data and applicability domain.

Design deep neural network architecture using a genetic algorithm for estimation of pile bearing capacity

Determination of pile bearing capacity is essential in pile foundation design. This study focused on the use of evolutionary algorithms to optimize Deep Learning Neural Network (DLNN) algorithm to predict the bearing capacity of driven pile. For this purpose, a Genetic Algorithm (GA) was developed to select the most significant features in the raw dataset. After that, a GA-DLNN hybrid model was developed to select optimal parameters for the DLNN model, including: network algorithm, activation function for hidden neurons, number of hidden layers, and the number of neurons in each hidden layer. A database containing 472 driven pile static load test reports was used. The dataset was divided into three parts, namely the training set (60%), validation (20%) and testing set (20%) for the construction, validation and testing phases of the proposed model, respectively. Various quality assessment criteria, namely the coefficient of determination (R²), Index of Agreement (IA), mean absolute error (MAE) and root mean squared error (RMSE), were used to evaluate the performance of the machine learning (ML) algorithms. The GA-DLNN hybrid model was shown to exhibit the ability to find the most optimal set of parameters for the prediction process.The results showed that the performance of the hybrid model using only the most critical features gave the highest accuracy, compared with those obtained by the hybrid model using all input variables.

Machine Learning Classifiers for Modeling Soil Characteristics by Geophysics Investigations: A Comparative Study

To design geotechnical structures efficiently, it is important to examine soil’s physical properties. Therefore, classifying soil with respect to geophysical parameters is an advantageous and popular approach. Novel, quick, cost, and time effective machine learning techniques can facilitate this classification. This study employs three kinds of machine learning models, including the Decision Tree, Artificial Neural Networks, and Bayesian Networks. The Decision tree models included the chi-square automatic interaction detection (CHAID), classification and regression trees (CART), quick, unbiased, and efficient statistical tree (QUEST), and C5; the Artificial Neural Networks models included Multi-Layer Perceptron (MLP) and Radial Basis Function (RBF); and BN models included the Tree Augmented Naïve (TAN) and Markov Blanket, which were employed to predict the soil classifications using geophysics investigations and laboratory tests. The performance of each model was assessed through the accuracy, stability and gains. The results showed that while the BAYESIANMARKOV model achieved the highest overall accuracy (100%) in training phase, this model achieved the lowest accuracy (34.21%) in testing phases. Thus, this model had the worst stability. The QUEST had the second highest overall training accuracy (99.12%) and had the highest overall testing accuracy (94.74%). Thus, this model was somewhat stable and had an acceptable overall training and testing accuracy to predict the soil characteristics. The future studies can use the findings of this paper as a benchmark to classify the soil characteristics and select the best machine learning technique to perform this classification.