检索结果-内蒙古大学图书馆

Determining the abutment angle in longwall coal mining using NLMR, GEP and GEO techniques

EARTH SCIENCE INFORMATICS 2025年第2期18卷 1-19页

作者： Matinpour, Fariborz Majdi, Abbas Univ Tehran Coll Engn Sch Min Engn Tehran *** Iran

Abutment angle is a key parameter to correctly determine the weight of overlying strata of destressed zone above the longwall panel roof that is transmitted to the adjacent barrier pillars and the corresponding face access tunnels. Thus, estimation of the abutment angle is crucial to safely design the corresponding barrier pillars' widths. This paper, at first, presents a new quadratic model based on non-linear multivariate regression (NLMR) analysis to estimate the abutment angle. Then, the paper continues to present two new powerful mathematical models by utilizing gene expression programming (GEP) and golden eagle optimizer (GEO) algorithms. To do so, depth of cover (H), panel width (P), and barrier pillar width (W) were used as input parameters to result abutment angle (beta) as output. The accuracy and efficiency of the NLMR, GEP, and GEO models were evaluated by using performance indices including coefficient of determination (R2), variance accounted for (VAF), a20-index, root mean square error (RMSE), and mean absolute error (MAE) and compared with three existing empirical equations. Furthermore, the capability of all models, based on Taylor diagram and regression error characteristic (REC) curve, have been comparatively examined. Residual analysis confirmed the normal distribution and randomness of errors, indicating no systematic bias and confirming the models' reliability. The results revealed that the present developed GEO and GEP models perform with much higher accuracy than the NLMR model and the existing empirical equations. Additionally, the analysis of input parameters' importance using the Shapley Additive Explanation (SHAP) method indicated that the depth of cover (H) has the greatest influence on the abutment angle (beta). Finally, a case study was used to validate the practical applicability of the proposed models, demonstrating their accuracy and reliability in real-world scenarios.

关键词： Longwall mining Abutment angle Non-linear multivariate regression gene expression programming Golden eagle optimizer

来源：评论

学校读者我要写书评

暂无评论

Optimizing the small modular reactor core loading with dual-cooled fuel via Henry gas solubility optimization algorithm

引用

NUCLEAR ENGINEERING AND DESIGN 2025年 433卷

作者： Rishehri, H. Zayermohammadi Ansarifar, G. R. Univ Isfahan Fac Phys Dept Nucl Engn Esfahan *** Iran

An investigation into the influence of innovative dual-cooled fuel geometric structural characteristics on critical reactor core parameters, such as temperature reactivity coefficients and convective heat transfer coefficient, is essential for accurately assessing its neutronic and thermohydraulic performance and estimating safety margins. This study calculated the fuel and coolant/moderator temperature reactivity coefficients in the NuScale-type reactor using WIMS-CITATION codes. Additionally, the impact of increasing the size of dual-cooled fuel rods on these coefficients was analyzed. The study also calculated the hot rod convective heat transfer coefficient for proposed fuel rods using a Computational Fluid Dynamics (CFD) and sub-channel model method. The results demonstrated that increasing the internal radius of the fuel decreases the temperature reactivity feedback coefficient of fuels, while the feedback coefficient of coolant exhibits a parabolic trend. All proposed fuel rods exhibited negative coolant and fuel temperature reactivity coefficients, and increasing the internal radius resulted in a reduction in the convective heat transfer coefficient. Furthermore, the study explored the use of Artificial Neural Network (ANN) and gene expression programming (GEP) models to develop an optimal method with low computational cost. Based on statistical indicators, the ANN was found to outperform GEP. Finally, the designed ANN, coupled with the Henry Gas Solubility Optimization (HGSO) algorithm, was employed to determine the optimal dual-cooled fuel based on desired parameters.

关键词： Dual-cooled fuel Temperature reactivity coefficients Convective heat transfer coefficient Artificial neural network gene expression programming Henry Gas Solubility Optimization

来源：评论

学校读者我要写书评

暂无评论

Machine learning-based correlation for economic evaluation of HTSE-nuclear cogeneration plant

引用

INTERNATIONAL JOURNAL OF HYDROGEN ENERGY 2025年 114卷 337-351页

作者： Sadeghi, Khashayar Ghazaie, Seyed Hadi Sokolova, Ekaterina Sergeev, Vitaly Ksenia, Naypak Yang, Luopeng Peter the Great St Petersburg Polytech Univ Dept Nucl & Heat Power Engn St Petersburg 195251 Russia Shandong Jianzhu Univ Sch Thermal Engn Jinan 250101 Shandong Peoples R China

The integration of high-temperature steam electrolysis system (HTSE) into light-water nuclear reactors for low- emission hydrogen production is a newly introduced application of nuclear co-generation plants, which recently has attracted considerable interest due to its high compatibility with the net zero emissions goal. The economic evaluation of the HTSE-nuclear cogeneration plant has a crucial role in effectively persuading decision-makers to use this technology on an industrial scale. Machine learning algorithms trained by well-structured datasets can be used for facilitating the prediction of levelized hydrogen cost based on the most basic input parameters. In this study, a systematic procedure for developing some applicable correlations to predict the levelized cost of the HTSE-nuclear cogeneration plant by means of gene expression programming (GEP) as a powerful tool in evolutionary machine learning approaches is introduced. An economic model based on technical and economic parameters is used for generating datasets to train GEP. The one-way sensitivity analysis has been performed to purify the dataset and remove non-influential parameters from the dataset. The propagation of uncertainties in the dataset is done based on the statistical Wilk's method by taking 59 random samples. GEP is trained by 80% of the non-dimensional generated dataset and three correlations for prediction of levelized capital cost, levelized operation and maintenance cost, and levelized decommission cost are developed. The calculated MSE and R2 errors show that GEP successfully could make proper correlations between input parameters and cost components. The operating and maintenance correlation with the R2 > 0.98 could present the highest accuracy among other correlations. In addition, the obtained relative error for predicted values of total hydrogen cost is less than 2%, which indicates the high accuracy achieved from the correlations derived by GEP.

关键词： Nuclear cogeneration Machine learning gene expression programming High-temperature steam electrolysis Hydrogen economy

来源：评论

学校读者我要写书评

暂无评论

Reliable determination of peak shear strength of H-shaped concrete squat walls using explainable machine learning techniques

引用

STRUCTURES 2025年 76卷

作者： Bin Inqiad, Waleed Khan, Muhammad Saud Alarifi, Saad S. Aston Univ Coll Engn & Phys Sci Aston St Birmingham B4 7ET England Univ Manitoba Price Fac Engn Dept Civil Engn Winnipeg MB R3T 5V6 Canada Ghulam Ishaq Khan Inst Engn Sci & Technol Dept Civil Engn Topi 23640 Pakistan King Saud Univ Coll Sci Dept Geol & Geophys POB 2455 Riyadh 11451 Saudi Arabia

Flanged reinforced concrete walls also known as H-shaped walls are frequently used in nuclear facilities and conventional buildings due to their substantial lateral strength and stiffness in both directions. These walls mostly fail in shear, and it is essential to accurately estimate their peak shear strength (Vp). However, the provisions of existing building codes to determine peak shear strength have significant limitations such as exclusion of the influence of flanges and consideration of insufficient input parameters. Therefore, this study aimed to construct predictive models for H-shaped walls using machine learning techniques like Bagging Regressor (BR), gene expression programming (GEP), and Extreme Gradient Boosting (XGB), based on data gathered from existing literature. The gathered data had twelve inputs including shear span ratio (hw/lw), the ratio of flange thickness to web thickness (tf/tw), and loading type (M) etc. Out of all the algorithms, only GEP depicted its output as an equation. The performance of the algorithms was checked using error metrices like Objective Function (OF), and coefficient of determination (R2) etc. which showed that XGB exhibited the highest accuracy having the testing R2 equal to 0.99. Additionally, shapely (SHAP), Individual Conditional Expectation (ICE), and partial dependence plots (PDP) analysis were employed which showed that flange length, loading type, and shear span ratio are some of the most contributing variables to determine Vp. Furthermore, a graphical user interface (GUI) has been developed to efficiently compute Vp of RC squat H-shaped walls to help professionals in the civil engineering industry.

关键词： Peak Shear Strength H-shaped walls Machine Learning Shapely Analysis gene expression programming

来源：评论

学校读者我要写书评

暂无评论

Machine learning-assisted correlations for prediction of fission gas fractions and hydrogen concentration in VVER-1000 fuel

引用

ANNALS OF NUCLEAR ENERGY 2025年 212卷

作者： Kaan, Yalcin Ilteris Sadeghi, Khashayar Ghazaie, Seyed Hadi Sokolova, Ekaterina Modestov, Victor Sergeev, Vitaly Gao, Puzhen Peter Great St Petersburg Polytech Univ Dept Nucl & Heat Power Engn St Petersburg 195251 Russia Harbin Engn Univ Fundamental Sci Nucl Safety & Simulat Technol Lab Harbin Peoples R China

This study aims to develop correlations for predicting the fission gas fractions and hydrogen gas concentration during a fuel cycle, using gene expression programming as an evolutionary machine learning approach. The wellknown FRAPCON code is used for generating a straightforward dataset under steady-state conditions. The twostep sensitivity analysis is carried out to identify the most influential parameters for correlation development. Wilks' statistical method is used to generate 59 scenarios to distribute input parameter uncertainties evenly, which leads to a confidence level of 95 %. The mean squared error for xenon, krypton, and helium is 0, while hydrogen exhibited a value of 59.36 since fraction values are between 0 and 1 and concentration ranged from 5 PPM to 200 PPM. R2 values exceeded 0.97, indicating strong correlation accuracy. The high accuracy achieved from the correlations demonstrates that selecting a 59-sample dataset based on Wilk's method is sufficient to obtain accuracy exceeding 95 %.

关键词： Machine learning Fuel burnup Fission gas fraction Hydrogen concentration gene expression programming FRAPCON

来源：评论

学校读者我要写书评

暂无评论

Buckling behavior of orthotropic thin plates using analytical and machine learning methods

引用

ENGINEERING STRUCTURES 2025年 324卷

作者： Ullah, Salamat Zhang, Jincheng Bo, Hu Zhang, Jinghui Javed, Muhammad Faisal Chen, Weiqiu Zhejiang Univ Lab Soft Machines & Smart Devices Zhejiang Prov Key Lab CAD & CG Hangzhou 310027 Peoples R China Zhejiang Univ Dept Engn Mech Hangzhou 310027 Peoples R China Yanshan Univ State Key Lab Metastable Mat Sci & Technol Qinhuangdao 066004 Peoples R China Yanshan Univ Hebei Prov Engn Res Ctr Harmless Synergist Treatme Qinhuangdao 066004 Peoples R China Sinopec Shanghai Engn Co Ltd Shanghai 200120 Peoples R China Hainan Transportat Engn Construct Bur Hai Kou 570100 Peoples R China Yanshan Univ Key Lab Green Construct & Intelligent Maintenance Qinhuangdao 066004 Peoples R China Ghulam Ishaq Khan Inst Engn Sci & Technol Dept Civil Engn Topi 23640 Pakistan Western Caspian Univ Baku Azerbaijan

Designing plate structures poses challenges due to potential instabilities and the complexities involved in obtaining accurate analytical solutions, especially for non-Levy-type boundary conditions. This study employs the finite integral transform method to analyze the buckling behavior of orthotropic thin plates with complex boundary conditions. In solution procedure, the governing high-order partial differential equations are transformed into a system of linear algebraic equations, yielding exact and rapidly converging analytical solution. The method is simple and general and does not need to predetermine the deflection function. The correctness of the method is validated by comparison with numerical simulations performed using the ABAQUS software. Furthermore, gene expression programming (GEP) is utilized to develop empirical models that predict buckling coefficients of isotropic and orthotropic plates under classical and non-classical boundary conditions. Material properties, aspect ratio, rotating fixed coefficient, and boundary conditions are used as input parameters, with simplified mathematical formulations to predict the buckling coefficient. Model performance is assessed using parametric analysis and statistical tests to ensure accuracy and generalization. Further investigation shows aspect ratio and rotating fixed coefficient are significant variables influencing buckling coefficients under classical and non-classical boundary conditions, respectively, followed by boundary conditions and material property. The performance of the GEP model is further assessed by comparing with linear and non-linear regression models. The results show that GEP outperforms the regression models, showing its higher prediction accuracy. This study not only addresses the challenges of designing thin plates with complex boundary conditions, but it also presents an effective machine-learning method for predicting buckling behavior. The analytical solution can be use

关键词： Rectangular thin plate Analytical solution Finite integral transform method Machine learning method gene expression programming

来源：评论

学校读者我要写书评

暂无评论

Interpretable predictive modeling, sustainability assessment, and cost analysis of cement-based composite containing secondary raw materials

引用

CONSTRUCTION AND BUILDING MATERIALS 2025年 473卷

作者： Asif, Usama Memon, Shazim Ali Nazarbayev Univ Sch Engn & Digital Sci Dept Civil & Environm Engn Nur Sultan 010000 Kazakhstan Univ Maryland Dept Civil & Environm Engn College Pk MD 20742 USA

The use of secondary cementitious raw materials (SCMs) in concrete, such as silica fume (SF) and ground granulated blast furnace slag (GGBS), can be a worthy option to reduce COQ emissions arising from the use of cement in concrete. Previously, several experimental and machine learning (ML)-based research studies have been conducted to promote the use of SCMs in concrete. However, prior studies have the following shortcomings: (a) a smaller database, (b) use of individual ML models, which often suffer from overfitting, poor robustness, and limited predictive accuracy, (c) non-availability of experimental validation, raising concerns about the reliability of ML-based predictions, (d) absence of sustainability and economic assessments, which are essential for the large-scale adoption of SCMs, and (e) non-existence of a comprehensive predictive model for estimating the compressive strength (CS) of binary and ternary blended concrete containing SF and GGBS. Therefore, to address these shortcomings, this study presents an innovative approach that employs a larger database, comparative analysis of individual and ensemble learning algorithms (ELAs), and experimental validation to estimate the CS of concrete while considering the sustainability and economic aspects of SCMs. A comprehensive database with eight input parameters of concrete was used to develop ML-based models such as multi-linear regression (MLR), artificial neural network (ANN), gene expression programming (GEP), and ELAs, including modified random forest (RF), bagging, and boosting techniques to anticipate the CS of concrete. The efficacy of the proposed models was validated by performing experimental investigations, statistical evaluations, K-fold tests, and external validation criteria. Shapley's Additive explanations (SHAP) analysis was also performed to explain the impact of each individual and the combined influence of input parameters on the CS of concrete. Comparative analysis shows that GEP ranks as

关键词： Secondary cementitious raw materials Ensemble learning algorithms gene expression programming Shapley's Additive explanations Compressive strength Sustainability assessments

来源：评论

学校读者我要写书评

暂无评论

Local buckling behavior in high-strength steel beams: A concentrated plasticity approach

引用

THIN-WALLED STRUCTURES 2025年 210卷

作者： Alghossoon, Abdullah Omoush, Duaa Varma, Amit Hashemite Univ Fac Engn Civil Engn Dept POB 330127 Zarqa 13133 Jordan Purdue Univ Fac Engn Civil Engn Dept W Lafayette IN USA

This paper introduces the first model designed to simulate local buckling in high-strength steel (HS-S) beams within moment-resisting frame systems (MRFs), especially under seismic loading conditions. Existing code limitations on section slenderness are derived from research on conventional steel, overlooking the special stress- strain characteristics of HS-S. To address this, a 3D finite element (FE) model developed in ABAQUS, calibrated with experimental data, investigates the moment-rotation hysteretic behavior of HS-S beams. Building on this, a new concentrated plasticity-based model (CPM) is proposed using an idealized tri-linear moment-rotation curve with three anchor points representing yielding, post-yield, and residual strength stages. gene expression programming (GEP), a state-of-the-art AI tool, refines and formulates the mechanism of these anchor points, achieving prediction accuracies of 95 % for peak strength, 98 % for initial stiffness, and 90 % for dissipated energy. The partially mechanical-based CPM is implemented in SAP2000, offering engineers an accessible tool for analyzing HS-S beams with improved simulation accuracy. This model significantly enhances the prediction of local buckling, addresses the limitations of current design codes, and provides valuable insights for both new designs and the assessment of existing structures.

关键词： Concentrated plasticity model Steel local buckling High-strength steel beams Finite element analysis gene expression programming

来源：评论

学校读者我要写书评

暂无评论

Constraining genetic symbolic regression via semantic backpropagation

引用

geneTIC programming AND EVOLVABLE MACHINES 2025年第1期26卷 1-31页

作者： Reissmann, Maximilian Fang, Yuan Ooi, Andrew S. H. Sandberg, Richard D. Univ Melbourne Dept Mech Engn Grattan St Melbourne Vic 3010 Australia

Evolutionary symbolic regression approaches are powerful tools that can approximate an explicit mapping between input features and observation for various problems. However, ensuring that explored expressions maintain consistency with domain-specific constraints remains a crucial challenge. While neural networks are able to employ additional information like conservation laws to achieve more appropriate and robust approximations, the potential remains unrealized within genetic algorithms. This disparity is rooted in the inherent discrete randomness of recombining and mutating to generate new mapping expressions, making it challenging to maintain and preserve inferred constraints or restrictions in the course of the exploration. To address this limitation, we propose an approach centered on semantic backpropagation incorporated into the gene expression programming (GEP), which integrates domain-specific properties in a vector representation as corrective feedback during the evolutionary process. By creating backward rules akin to algorithmic differentiation and leveraging pre-computed subsolutions, the mechanism allows the enforcement of any constraint within an expression tree by determining the misalignment and propagating desired changes back. To illustrate the effectiveness of constraining GEP through semantic backpropagation, we take the constraint of physical dimension as an example. This framework is applied to discover physical equations from the Feynman lectures. Results have shown not only an increased likelihood of recovering the original equation but also notable robustness in the presence of noisy data.

关键词： gene expression programming Semantic backpropagation Symbolic regression

来源：评论

学校读者我要写书评

暂无评论

Dimensionless Machine Learning: Dimensional Analysis to Improve LSSVM and ANN models and predict bearing capacity of circular foundations

引用

ARTIFICIAL INTELLIGENCE REVIEW 2025年第4期58卷 1-53页

作者： Li, Hongchao Hosseini, Shahab Gordan, Behrouz Zhou, Jian Ullah, Sajid Kunming Univ Sci & Technol City Coll Kunming 650051 Peoples R China Tarbiat Modares Univ Fac Engn Tehran Iran Univ Teknol Malaysia UTM Fac Civil Engn Dept Geotech & Transportat Skudai 81310 Johor Malaysia Cent South Univ Sch Resources & Safety Engn Changsha 410083 Peoples R China Nangarhar Univ Dept Water Resources & Environm Engn Jalalabad 2600 Nangarhar Afghanistan

This research focuses on developing hybrid intelligence techniques to predict the bearing capacity of circular foundations using the most effective parameters. In this regard, a database involving 968 test circular foundations involving different rock properties, soil characteristics, and foundation radius has been prepared by laboratory tests for training and testing the new model presented in this study. For adequately considering various factors, the several parameters of depth (D) in m, density of soil (DS) in gr/cm3, internal angle of friction (IAF) in degree, cohesion of soil (CS) in kg/cm2, and foundation radius (FR) in m were considered as the input of the model and bearing capacity in kg/cm2 was considered as the target parameter. Three main strategies were addressed in this study. First, four well-known machine learning algorithms, Artificial Neural Network (ANN), Bagging Regressor (BR), Least Squares Support Vector Machine (LSSVM), and Gradient Boosting Regressor (GBR), were adopted to predict bearing capacity. Second, a novel and robust mathematical computation named dimensional analysis (DA) theorem was integrated with machine learning techniques to improve the accuracy and performance of the models by decreasing the number of inputs. Third, based on DA implementation, a rational mathematical formula using gene expression programming (GEP) was structured to anticipate bearing capacity. Furthermore, the sensitivity analysis process specified the impact of the five effective factors. The results of this study demonstrate the effectiveness of integrating DA with machine learning models to predict the BC of circular foundations. Among the developed models, the DA-LSSVM model showed superior performance, achieving an R-2 of 0.998 and 0.996 for training and testing, respectively, indicating high prediction accuracy. The results indicated that the IAF was the most sensitive factor with r = 0.709, while CS was the least sensitive with r = -0.087. A graphical us

关键词： Dimensional analysis Theorem Machine learning gene expression programming Bearing capacity Circular foundations

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：