Hybrid catboost models optimized with metaheuristics for predicting shear strength in rock joints

Bulletin of Engineering Geology and the Environment, Год журнала: 2025, Номер 84(3)

Опубликована: Фев. 25, 2025

Язык: Английский

---

Estimation of powder factor in mine blasting: feasibility of tree-based predictive models

Multiscale and Multidisciplinary Modeling Experiments and Design, Год журнала: 2025, Номер 8(2)

Опубликована: Янв. 15, 2025

Язык: Английский

---

Assessment of mechanical properties of rock using deep learning approaches

Measurement, Год журнала: 2025, Номер unknown, С. 117180 - 117180

Опубликована: Март 1, 2025

Язык: Английский

---

Enhanced Earth and Rockfill Dam Seepage Forecasting via an Integrated PLS-BO-BiLSTM Approach: A Novel Model Incorporating Lag Effects and Optimization Algorithms

Pure and Applied Geophysics, Год журнала: 2025, Номер unknown

Опубликована: Янв. 6, 2025

Язык: Английский

---

A theory-data-integrated intelligent framework for prediction of blasting-induced rock fragment size

Powder Technology, Год журнала: 2025, Номер unknown, С. 120638 - 120638

Опубликована: Янв. 1, 2025

Язык: Английский

---

Simulating the Deterioration Behavior of Tunnel Elements Using Amalgamation of Regression Trees and State-of-the-Art Metaheuristics

Mathematics, Год журнала: 2025, Номер 13(7), С. 1021 - 1021

Опубликована: Март 21, 2025

Tunnel infrastructures worldwide face escalating deterioration challenges due to aging materials, increasing load demands, and exposure harsh environmental conditions. Accurately predicting the onset progression of is paramount for ensuring structural safety, optimizing maintenance interventions, prolonging service life. However, complex interplay environmental, material, operational factors poses significant current predictive models. Additionally, they are constrained by small datasets a narrow range tunnel elements that limit their generalizability. This paper presents novel hybrid metaheuristic-based regression tree (REGT) model designed enhance accuracy robustness predictions. Leveraging metaheuristic algorithms’ strengths, developed method jointly optimizes critical hyperparameters identifies most relevant features prediction. A comprehensive dataset encompassing material properties, stressors, traffic loads, historical condition assessments was compiled development. Comparative analyses against conventional trees, artificial neural networks, support vector machines demonstrated consistently outperformed baseline techniques regarding While trees classic machine learning models, no single variant dominated all elements. Furthermore, optimization framework mitigated overfitting provided interpretable insights into primary driving deterioration. Finally, findings this research highlight potential models as powerful tools infrastructure management, offering actionable predictions enable proactive strategies resource optimization. study contributes advancing field modeling in civil engineering, with implications sustainable management infrastructure.

Язык: Английский

---

Durability Evaluation and Prediction of Civil Engineering Structures Combined with Spectral Clustering Algorithm

Опубликована: Май 30, 2024

Язык: Английский

---

Study on the technology of blasting to squeeze silt and build embankment in deep muddy soft soil under complex environment

Research Square (Research Square), Год журнала: 2024, Номер unknown

Опубликована: Окт. 3, 2024

Blasting mud displacement technology has always played a crucial role in reclamation projects. To further analyze the effectiveness and application of blasting dike construction complex thick silt soft soil layers, this study first utilized excellent linear classification prediction capabilities Support Vector Machines (SVM) to construct model for slope displacement. Additionally, traditional process was optimized by proposing full lateral technique aimed at achieving mud-rock layers. The eliminates need end blasting, instead using fixed-point widening methods accomplish task. In experimental results analysis section, performance SVM models with different kernel functions tested. indicated that RBF had best performance, mean squared error values measurement points not exceeding 0.35. By adjusting parameters sites comparing settlement four technique, it found plan is feasible, all remaining within reasonable ranges. This provides new approach layers construction.

Язык: Английский

---

Practical Application of Intelligent Technology in Grassroots Public Governance and Its Enhancement of Governance Effectiveness

Applied Mathematics and Nonlinear Sciences, Год журнала: 2024, Номер 9(1)

Опубликована: Янв. 1, 2024

Abstract The application and development of intelligent technology in the field public management has accelerated governance mode change process evolution. As a new direction system technological innovation era, holistic smart high theoretical coupling with grassroots governance. Based on transformation path governance, study designs model for then measures effectiveness using static DEA dynamic Malmquist index model. Subsequently, data from 16 regions Province M are taken as examples empirical analysis, augmented regression number is utilized to explore relative strengths influencing factors ways them. results show that M4, M7, M9, M12, M13 M15, six realize effective, but average value annual greater than 1 only M12 some have poor capacity, production difficult innovate, capacity not coordinated input = 3055 under tree ratio housing expenditure per capita disposable income greatest impact society (27.54%), which needs be focused on. concludes can realized five areas: philosophy, objectives, approach, structure, path.

Язык: Английский

---

Geostatistics-block-based characterization of the relationship between rock mass quality and powder factor and its application on open-pit limit optimization

International Journal of Mining Science and Technology, Год журнала: 2024, Номер unknown

Опубликована: Дек. 1, 2024

Язык: Английский

---