Application of extreme gradient boosting method for evaluating the properties of episodic failure of borehole breakout

Geoenergy Science and Engineering, Journal Year: 2023, Volume and Issue: 226, P. 211837 - 211837

Published: April 23, 2023

Language: Английский

---

Application of optimization‐based regression analysis for evaluation of frost durability of recycled aggregate concrete

Structural Concrete, Journal Year: 2024, Volume and Issue: 25(1), P. 716 - 737

Published: Jan. 7, 2024

Abstract Concrete constructed using recycled aggregates in place of natural is an efficient approach to increase the construction sector's sustainability. To improve aggregate concrete () technologies permafrost, it essential certify stability frost‐induced conditions. The main goal this study was use support vector regression methods forecast frost durability on basis agent value cold climates. Herein, three optimization called Ant lion (), Grey wolf and Henry Gas Solubility Optimization were employed for indicating optimal values key parameters. results depicted that all developed models have capability predicting regions. as a comprehensive index model has higher at 0.0571 weakest model, then 0.0312 recognized second‐highest finally system 0.0224 mentioned outperformed model. approaches likewise capable accurately forecasting regions, but created method them when taking into account explanations justifications.

Language: Английский

---

A case study of resilient modulus prediction leveraging an explainable metaheuristic-based XGBoost

Transportation Geotechnics, Journal Year: 2024, Volume and Issue: 45, P. 101216 - 101216

Published: Feb. 18, 2024

Language: Английский

---

Improved arithmetic optimization algorithm and its application to carbon fiber reinforced polymer-steel bond strength estimation

Composite Structures, Journal Year: 2022, Volume and Issue: 306, P. 116599 - 116599

Published: Dec. 15, 2022

Language: Английский

---

Support Vector Machine (SVM) Application for Uniaxial Compression Strength (UCS) Prediction: A Case Study for Maragheh Limestone

Applied Sciences, Journal Year: 2023, Volume and Issue: 13(4), P. 2217 - 2217

Published: Feb. 9, 2023

The geomechanical properties of rock materials, such as uniaxial compression strength (UCS), are the main requirements for geo-engineering design and construction. A proper understanding UCS has a significant impression on safe different foundations rocks. So, applying fast reliable approaches to predict based limited data can be an efficient alternative regular traditional fitting curves. In order improve prediction accuracy UCS, presented study attempted utilize support vector machine (SVM) algorithm. Multiple training testing datasets were prepared predictions total 120 samples recorded limestone from Maragheh region, northwest Iran, which used achieve high precision rate prediction. models validated using confusion matrix, loss functions, error tables (MAE, MSE, RMSE). addition, 24 tested (20% primary dataset) model justifications. Referring results study, SVM (accuracy = 0.91/precision 0.86) showed good agreement with actual data, estimated coefficient determination (R2) reached 0.967, showing that model’s performance was impressively better than

Language: Английский

---

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

Construction and Building Materials, Journal Year: 2023, Volume and Issue: 393, P. 131992 - 131992

Published: June 10, 2023

Language: Английский

---

Uncertainty quantification in multiaxial fatigue life prediction using Bayesian neural networks

Engineering Fracture Mechanics, Journal Year: 2024, Volume and Issue: 298, P. 109961 - 109961

Published: Feb. 15, 2024

Language: Английский

---

Development of machine learning models for forecasting the strength of resilient modulus of subgrade soil: genetic and artificial neural network approaches

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Aug. 6, 2024

Accurately predicting the Modulus of Resilience (MR) subgrade soils, which exhibit non-linear stress–strain behaviors, is crucial for effective soil assessment. Traditional laboratory techniques determining MR are often costly and time-consuming. This study explores efficacy Genetic Programming (GEP), Multi-Expression (MEP), Artificial Neural Networks (ANN) in forecasting using 2813 data records while considering six key parameters. Several Statistical assessments were utilized to evaluate model accuracy. The results indicate that GEP consistently outperforms MEP ANN models, demonstrating lowest error metrics highest correlation indices (R2). During training, achieved an R2 value 0.996, surpassing (R2 = 0.97) 0.95) models. Sensitivity SHAP (SHapley Additive exPlanations) analysis also performed gain insights into input parameter significance. revealed confining stress (21.6%) dry density (26.89%) most influential parameters MR. corroborated these findings, highlighting critical impact on predictions. underscores reliability as a robust tool precise prediction applications, providing valuable performance significance across various machine-learning (ML) approaches.

Language: Английский

---

Developing Two Hybrid Algorithms for Predicting the Elastic Modulus of Intact Rocks

Sustainability, Journal Year: 2023, Volume and Issue: 15(5), P. 4230 - 4230

Published: Feb. 26, 2023

In the primary and final designs of projects related to rock mechanics engineering geology, one key parameters that needs be taken into account is intact elastic modulus (E). To measure this parameter in a laboratory setting, core samples with high-quality costly tools are required, which also makes for time-consuming process. The aim study assess effectiveness two meta-heuristic-driven approaches predicting E. models proposed paper, based on integrated expert systems, hybridize adaptive neuro-fuzzy inference system (ANFIS) optimization algorithms, i.e., differential evolution (DE) firefly algorithm (FA). performance quality both ANFIS-DE ANFIS-FA was then evaluated by comparing them ANFIS neural network (NN) models. were formed basis data collected from Azad Bakhtiari dam sites Iran. After applying several statistical criteria, such as root mean square error (RMSE), model found superior ANFIS-DE, ANFIS, NN terms E value. Additionally, sensitivity analysis results showed P-wave velocity further influenced compared other independent variables.

Language: Английский

---

BILSTM-Based Deep Neural Network for Rock-Mass Classification Prediction Using Depth-Sequence MWD Data: A Case Study of a Tunnel in Yunnan, China

Applied Sciences, Journal Year: 2023, Volume and Issue: 13(10), P. 6050 - 6050

Published: May 15, 2023

Measurement while drilling (MWD) data reflect the rig–rock mass interaction; they are crucial for accurately classifying rock ahead of tunnel face. Although machine-learning methods can learn relationship between MWD and mechanics parameters to support classification, most current models do not consider impact continuous drilling-sequence process, thereby leading rock-classification errors, small unbalanced field datasets result in poor model performance. We propose a novel deep neural network based on Bi-directional Long Short-Term Memory (BILSTM) extract information-related sequences improve accuracy rock-mass classification. Two optimization modules were designed model’s generalization Stratified K-fold cross-validation was used datasets. Model validation is dataset highway Yunnan, China. Multiple metrics show that prediction ability significantly better than those multilayer perceptron (MLP) support-vector machine (SVM), exhibits an improved The reach 90%, which 13% 15% higher MLP SVM, respectively.

Language: Английский

---