检索结果-内蒙古大学图书馆

gene expression programming-based model prediction of performance and emission characteristics of a diesel engine fueled with linseed oil biodiesel/diesel blends: An artificial intelligence approach

引用

ENERGY SOURCES PART A-RECOVERY UTILIZATION AND ENVIRONMENTAL EFFECTS 2025年第1期47卷 1385-1399页

作者： Sharma, Prabhakar Guru Nanak Dev Inst Technol Mech Engn Dept Thermal Engn Lab Delhi 110089 India

In the present study, Artificial Intelligence (AI) based gene expression programming (GEP) is used to develop a model to predict the performance and emission characteristics of a single-cylinder diesel engine fueled with linseed oil methyl ester (LOME) blended with mineral diesel. The data to be used for GEP were obtained experimentally by varying the biodiesel/mineral diesel blending ratio, engine load, fuel injection pressure, and fuel injection timing. The GEP-based model was developed to predict the brake thermal efficiency (BTE), brake specific fuel consumption (BSFC), NOx, and unburned hydrocarbon (UHC) emission. A major part (70%) of the collected data was used for training and remaining (30%) was used for model validation. The developed GEP model was robust enough to provide a high degree of accuracy in the prediction of engine performance and emission parameters. The statistical measure of model robustness such as coefficient of correlation (R) was in the range of 0.9926-0.9999 and the coefficient of determination (R2) was 0.9854-0.9998 for the output prediction. The root mean square error (RMSE) in the GEP model predicted results were in the range of 0.0048-2.597 and mean absolute error (MSE) was ***: AI: Artificial Intelligence;BSFC: Brake specific fuel consumption;bTDC: Before top dead center;BTE: Brake thermal efficiency;B0: (MOME 0% + Mineral diesel 100%);B10: (MOME 10% + Mineral diesel 90%);B20: (MOME 20% + Mineral diesel 80%);CI: Compression ignition;CO: Carbon monoxide;ET: expression tree;FIP: Fuel injection pressure;FIT: Fuel injection timing;GEP: gene expression programming;ICE: Internal combustion engine;ID: Ignition delay;MAE: Mean absolute error;MIT: Machine identical tool;NOx: Nitrogen oxides;ppm: Parts per million;R: Regression coefficient;R2: Coefficient of determination;RMSE: Root mean square error;UHC: Unburned hydrocarbon

关键词： Artificial intelligence gene expression programming alternative fuel biodiesel linseed oil methyl ester

来源：评论

学校读者我要写书评

暂无评论

Wind turbine energy forecasting using real wind farm's measurement data and performance of gene expression programming analytical model in comparison to traditional algorithms

引用

INTERNATIONAL JOURNAL OF GREEN ENERGY 2025年第2期22卷 414-431页

作者： Mehmood, Zahid Wang, Zhenyu Zhejiang Univ Coll Civil Engn & Architecture Yuhangtang Rd 866 Hangzhou 310058 Peoples R China

Forecasting wind power is vital to ensure steady, sustainable, and renewable energy. The complex nonlinear nature of wind flow and its interrelated factors make power prediction challenging. This study predicted wind power curves inspired by the Biologically Inspired Evolutionary Computation (BIEC) paradigm, incorporating gene expression programming (GEP), Artificial Neural Networks (ANN), Least Square Support Vector Machines (LSSVM), and Random Forest (RF) models. Key input parameters include wind speed, yaw azimuth, turbulent intensity, veer, horizontal and vertical shear, ambient temperature, blade pitch, and rotor speed. The study evaluates these models' effectiveness using root mean square error (RMSE) and correlation coefficient R. Results indicate that the GEP model offers transparent modeling, emphasizing critical inputs like wind speed, rotor speed, blade pitch angle, and temperature for wind power prediction. The GEP model identified wind speed, rotor speed, blade pitch angle, and temperature as the most influential parameters, with variable importance index (Ii) values of 69.39%, 24.39%, 5.46%, and 0.64% for training, and 69.37%, 25.03%, 4.98%, and 0.54% for validation. The study demonstrates the GEP model's efficacy in accurately forecasting wind power curve, achieving a high correlation with training and validation coefficients of 0.9899 and 0.994, respectively, outperforming traditional models with minor errors.

关键词： data fusion data monitoring gene expression programming wind energy forecasting Wind power generation

来源：评论

学校读者我要写书评

暂无评论

Gradient Information and Regularization for gene expression programming to Develop Data-Driven Physics Closure Models

引用

FLOW TURBULENCE AND COMBUSTION 2025年第1期114卷 145-175页

作者： Waschkowski, Fabian Li, Haochen Deshmukh, Abhishek Grenga, Temistocle Zhao, Yaomin Pitsch, Heinz Klewicki, Joseph Sandberg, Richard D. Univ Melbourne Dept Mech Engn Melbourne Vic 3010 Australia Peking Univ Ctr Appl Phys & Technol Beijing 100871 Peoples R China Rhein Westfal TH Aachen Inst Combust Technol D-52062 Aachen Germany

Learning accurate numerical constants when developing algebraic models is a known challenge for evolutionary algorithms, such as gene expression programming (GEP). This paper introduces the concept of adaptive symbols to the GEP framework by Weatheritt and Sandberg (J Comput Phys 325:22-37, 2016a) to develop advanced physics closure models. Adaptive symbols utilize gradient information to learn locally optimal numerical constants during model training, for which we investigate two types of nonlinear optimization algorithms. The second contribution of this work is implementing two regularization techniques to incentivize the development of implementable and interpretable closure models. We apply L2\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$L_2$$\end{document} regularization to ensure small magnitude numerical constants and devise a novel complexity metric that supports the development of low complexity models via custom symbol complexities and multi-objective optimization. This extended framework is employed to four use cases, namely rediscovering Sutherland's viscosity law, developing laminar flame speed combustion models and training two types of fluid dynamics turbulence models. The model prediction accuracy and the convergence speed of training are improved significantly across all of the more and less complex use cases, respectively. The two regularization methods are essential for developing implementable closure models and we demonstrate that the developed turbulence models substantially improve simulations over state-of-the-art models.

关键词： gene expression programming Nonlinear optimization Regularization Model complexity

来源：评论

学校读者我要写书评

暂无评论

A Predictive Model for the Equivalent Hydraulic Aperture of Single Fracture Using gene expression programming

引用

ROCK MECHANICS AND ROCK ENGINEERING 2025年第2期58卷 1975-1993页

作者： Zhai, Zixuan Zhang, Shuai Ni, Zhihui Li, Dongxu Qian, Ruipeng Chongqing Jiaotong Univ Southwestern Res Inst Water Transport Engn Chongqing 400016 Peoples R China Tsinghua Univ Dept Hydraul Engn State Key Lab Hydrosci & Engn Beijing 100084 Peoples R China Taiyuan Univ Sci & Technol Coll Safety & Emergency Management Engn Taiyuan 030024 Peoples R China

The accurate prediction of the equivalent hydraulic aperture (EHA) in a single fracture is of paramount importance for the investigation of fracture flow capacity. Previous studies primarily relied on fitting experimental data to obtain the EHA, failing to accurately characterize the impact of the strong nonlinearity among fracture geometric parameters on EHA. This research integrates 170 datasets of measured EHA, incorporating key geometric parameters: average mechanical aperture (bm), peak roughness height (xi), and the joint roughness coefficient (JRC). These three main geometric characteristic parameters, used as input parameters, are the primary factors influencing the EHA. The gene expression programming (GEP) method was utilized to construct a model for predicting EHA (bh). The developed GEP model was then compared with 6 existing empirical models, as well as 2 AI models (Random Forest (RF) and Support Vector Machine (SVM)). The results indicate that the GEP model (R2 = 0.997) and the SVM model (R2 = 0.9944) both demonstrate high accuracy, evidenced by the GEP model's low RMSE (0.014) and MAE (0.01) values. The sensitivity analysis indicates that in the GEP model, the hydraulic aperture increases linearly with the increase of bm, decreases linearly with the increase of xi, and initially increases but then decreases as JRC increases. These findings provide insightful contributions to the assessment of hydraulic conductivity in the rough single fracture. GEP model accurately predicts hydraulic aperture (R-2 = 0.997) with clear *** model outperforms six existing empirical & two AI models in *** m, JRC as key in hydraulic aperture, impact is *** model shows complex impact of geometry on hydraulic aperture

关键词： gene expression programming Peak roughness height Average mechanical aperture Joint roughness coefficient Single fracture

来源：评论

学校读者我要写书评

暂无评论

Unconfined compressive strength of geopolymers based soil: Model development using gene expression programming and a comparison with other computer-based approaches

引用

MECHANICS OF ADVANCED MATERIALS AND STRUCTURES 2025年第5期32卷 841-851页

作者： Tran, Khiem Quang Duong, Nga Thanh Luu, Loc Xuan Tran, Linh Hoang Ton Duc Thang Univ Smart Comp Civil Engn Res Grp Ho Chi Minh City Vietnam Ton Duc Thang Univ Fac Civil Engn Ho Chi Minh City Vietnam Ho Chi Minh City Univ Technol HCMUT Fac Civil Engn 268 Ly Thuong Kiet StDist 10 Ho Chi Minh City Vietnam Vietnam Natl Univ Ho Chi Minh City Linh Trung Ward Ho Chi Minh City Vietnam

The present work aims to propose a model for calculating unconfined compressive strength (UCS) of soil stabilized by geopolymer based on gene expression programming (GEP). The new model is compared with earlier models developed from artificial neural networks (ANN), multivariable regression analysis (MVR), multi-gene genetic programming (MGGP), and support vector machines (SVM) models. The results indicate that the GEP model is superior to MVR and MGGP models and quite comparable to ANN and SVM models. The study demonstrates the robustness of the GEP model through parametric analysis. Additionally, this model is simpler and easier to use in practice.

关键词： Unconfined compressive strength soil mechanics soil stabilization geopolymers machine learning gene expression programming

来源：评论

学校读者我要写书评

暂无评论

Stability of a rectangular trapdoor in three dimensions: A gene expression programming method

引用

TUNNELLING AND UNDERGROUND SPACE TECHNOLOGY 2025年 157卷

作者： Domphoeun, Rithy Shiau, Jim Keawsawasvong, Suraparb Jamsawang, Pitthaya Thammasat Univ Thammasat Sch Engn Dept Civil Engn Res Unit Sci & Innovat Technol Civil Engn Infrastr Pathum Thani Thailand Univ Southern Queensland Sch Engn Toowoomba Qld 4350 Australia Thammasat Univ Thammasat Sch Engn Dept Civil Engn Res Unit Sci & Innovat Technol Civil Engn Infrastr Pathum Thani Thailand King Mongkuts Univ Technol North Bangkok Soil Engn Res Ctr Dept Civil Engn Bangkok 10800 Thailand

This paper focuses on the stability analysis of three-dimensional rectangular trapdoors beneath cohesivefrictional soils via three-dimensional finite element limit analysis (3D FELA). By applying Terzaghi's superposition method, the average upper bound and lower bound limit analyses are conducted to determine three stability factors: the cohesion factor (Fc), the surcharge factor (Fs), and the unit weight factor (Fr). Additionally, a machine learning technique, specifically genetic expression programming (GEP), is employed to develop explicit predictive equations for each stability factor. The numerical results show excellent performance of the GEP model prediction, with R2 values of 0.991, 0.992, and 0.994 for the cohesion, surcharge, and unit weight stability factors, respectively. A series of equations, figures, and tables were subsequently developed to determine the stability factors of a rectangular trapdoor. The incorporation of modern machine learning techniques with advanced 3D FELA makes this study highly significant for geotechnical engineering practices.

关键词： Rectangular trapdoor Stability factor Finite element limit analysis gene expression programming Terzaghi's superposition method

来源：评论

学校读者我要写书评

暂无评论

GEP-DNN4Mol: automatic chemical molecular design based on deep neural networks and gene expression programming

引用

HEALTH INFORMATION SCIENCE AND SYSTEMS 2025年第1期13卷 1-8页

作者： Zheng, Wen Li, Zhongji Chen, Yuanyuan Liao, Wenjia Deng, Lei Zhang, Hao Lin, Yanmei Peng, Yuzhong Nanning Normal Univ Guangxi Key Lab Human Machine Interact & Intellige Nanning 530001 Peoples R China Guangxi Acad Sci Nanning 530007 Peoples R China Hunan Univ Sch Math Changsha 410082 Peoples R China Cent South Univ Sch Comp Sci & Engn Changsha 410083 Peoples R China Chinese Acad Sci Shenzhen Inst Adv Technol Shenzhen 518000 Peoples R China Nanning Normal Univ Sch Environm & Sci Nanning 530001 Peoples R China

The inverse design of molecules has attracted widespread attention in the field of chemical molecular design. However, existing methods fail to address the diversity of the generated molecules. In this work, we propose a molecule generation method called GEP-DNN4Mol to generate molecules with good diversity and desired properties in the exploration of vast chemical space. GEP-DNN4Mol leverages a special gene expression programming algorithm as a generator for molecular generations, uses a deep neural network as an evaluator to guide the update of the generator by extracting the molecular features of the generated molecules, and couples with SMILES and SELFIES molecular representations. The experimental results show that the proposed approach outperforms the state-of-the-art methods in the performance of generated molecules and the efficiency of exploration in chemical space. The molecules generated by GEP-DNN4Mol have advantages in terms of total validity, high novelty, and good diversity.

关键词： Molecular generation Molecular design Deep neural network gene expression programming Molecular feature extraction

来源：评论

学校读者我要写书评

暂无评论

Consideration of Non-Locality for gene expression programming: Modeling the Transition to Turbulence in the Boundary Layer

引用

FLOW TURBULENCE AND COMBUSTION 2025年 1-23页

作者： Bleh, Alexander Morsbach, Christian German Aerosp Ctr Inst Prop Technol D-51147 Cologne Germany

The consideration of the inherently non-local characteristics of turbulence is an open challenge and subject to many investigations. Recent approaches rely on the utilization of spatially configured Neural Networks such as e.g. Convolutional Neural Networks to account for non-local effects (Comput. Methods Appl. Mech. Eng. 384:113927, 2021). Nevertheless, approaches featuring Neural Networks are not easily available for gene expression programming. An alternative option, to consider non-local effects, is the use of partial differential equations (PDE) like an additional convection-diffusion equation as is done for example in several transition models such as the \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\gamma$$\end{document}- model by Menter et al. (Flow Turbul. Combust. 583-619, 2015). Consequently, instead of only modeling a local correction factor directly using GEP, we equip the input quantities with an additional optional convection-diffusion equation of which we model the production term, diffusion constants and boundary type. The methodology is applied on a set of low pressure turbine testcases in order to find transition models. Resulting expressions are further analysed in terms of underlying mechnims and logical foundations.

关键词： gene expression programming Data-driven Turbulence Transition Non-locality

来源：评论

学校读者我要写书评

暂无评论

Advanced Machine Learning and gene expression programming Techniques for Predicting CO_(2)-Induced Alterations in Coal Strength

引用

Computer Modeling in Engineering & Sciences 2025年第4期143卷 153-183页

作者： Zijian Liu Yong Shi ChuanqiLi Xiliang Zhang Jian Zhou Manoj Khandelwal School of Resources and Safety Engineering Central South UniversityChangsha410083China Changsha Institute of Mining Research Co. Ltd.Changsha410012China State Key Laboratory of Safety and Health for Metal Mines Ma’anshan243000China Institute of Innovation Science and SustainabilityFederation University AustraliaBallaratVIC 3350Australia

Given the growing concern over global warming and the critical role of carbon dioxide(CO_(2))in this phenomenon,the study of CO_(2)-induced alterations in coal strength has garnered significant attention due to its implications for carbon sequestration.A large number of experiments have proved that CO_(2) interaction time(T),saturation pressure(P)and other parameters have significant effects on coal ***,accurate evaluation of CO_(2)-induced alterations in coal strength is still a difficult problem,so it is particularly important to establish accurate and efficient prediction *** study explored the application of advancedmachine learning(ML)algorithms and gene expression programming(GEP)techniques to predict CO_(2)-induced alterations in coal *** were developed,including three metaheuristic-optimized XGBoost models(GWO-XGBoost,SSA-XGBoost,PO-XGBoost)and three GEP models(GEP-1,GEP-2,GEP-3).Comprehensive evaluations using multiple metrics revealed that all models demonstrated high predictive accuracy,with the SSA-XGBoost model achieving the best performance(R2—Coefficient of determination=0.99396,RMSE—Root Mean Square Error=0.62102,MAE—Mean Absolute Error=0.36164,MAPE—Mean Absolute Percentage Error=4.8101%,RPD—Residual Predictive Deviation=13.4741).Model interpretability analyses using SHAP(Shapley Additive exPlanations),ICE(Individual Conditional Expectation),and PDP(Partial Dependence Plot)techniques highlighted the dominant role of fixed carbon content(FC)and significant interactions between FC and CO_(2) saturation pressure(P).Theresults demonstrated that the proposedmodels effectively address the challenges of CO_(2)-induced strength prediction,providing valuable insights for geological storage safety and environmental applications.

关键词： CO_(2)-induced coal strength meta-heuristic optimization algorithms XGBoost gene expression programming model interpretability

来源：评论

学校读者我要写书评

暂无评论

Development of prediction models for strength properties of concrete using gene expression programming

引用

INNOVATIVE INFRASTRUCTURE SOLUTIONS 2025年第3期10卷 1-29页

作者： Khan, Asad Ullah Javed, Muhammad Faisal Khan, Majid Univ Engn & Technol Dept Civil Engn Peshawar 25120 Pakistan GIK Inst Engn Sci & Technol Topi 23640 Khyber Pakhtunk Pakistan Western Caspian Univ Coll Engn Al Kharj Dept Civil Engn Baku Azerbaijan Southern Illinois Univ Edwardsville Dept Civil Engn Edwardsville IL 62026 USA

Accurately forecasting the strength properties of concrete is critical, especially for design code compliance. While statistical and empirical models are commonly used;however, these methods demand intensive experimentation and may yield inaccuracies in intricate relationships between concrete characteristics, mix components, and curing conditions. To address these limitations, the current study utilized the gene expression programming (GEP) method to forecast the mechanical characteristics of concrete, such as modulus of elasticity (E), modulus of rupture (MOR), and dynamic modulus (DM). For this purpose, 440 values for E and MOR and 279 values for DM were compiled to develop robust and reliable predictive models. Multiple statistical metrics were utilized to validate the predictions of the model. The GEP model exhibited excellent prediction accuracy with a correlation coefficient (R) of 0.95, 0.96, and 0.94 for MOR, E, and DM, respectively. The comparison between GEP and linear regression models revealed revealed that machine learning-based models (GEP) exhibit superior accuracy than traditional regression models. Moreover, SHapley Additive exPlanations (SHAP) revealed that age significantly influenced all three considered strength characteristics of concrete. In addition, a graphical user interface (GUI) has been created to simplify the utilization of ML-based models for predicting the strength characteristics of concrete. The outcome of this study has the potential to be utilized for smartly predicting concrete's strength properties, eliminating the need for expensive and time-consuming testing procedures.

关键词： Concrete Strength properties Machine learning gene expression programming SHAP Graphical user interface

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：