检索结果-内蒙古大学图书馆

Flexural strength prediction of concrete beams reinforced with hybrid FRP and steel bars based on machine learning

STRUCTURES 2024年 65卷

作者： Zhang, Tao Gao, Danying Xue, Chengcheng Zhengzhou Univ Sch Water Conservancy Engn 100 Sci Rd Zhengzhou 450001 Henan Peoples R China Zhengzhou Univ Sch Civil Engn 100 Sci Rd Zhengzhou 450001 Henan Peoples R China

In the past decade, hybrid fiber-reinforced polymer (FRP) and steel reinforced concrete (hybrid FRP-steel RC) beams have attracted significant interest due to their relatively superior flexural behavior compared with the pure FRP bars reinforced concrete (FRP-RC) beams. The recent trend in research involves the utilization of machine learning (ML) tools to accurately predict the flexural behavior of RC beams. In this study, the two artificial intelligence technologies, namely artificial neural network (ANN) and gene expression programming (GEP), through a data-driven approach, were used to establish reliable and accurate ML models for predicting the flexural strength of hybrid FRP-steel RC beams. To build the ML models, a huge database of 134 data points was collected from the peer-reviewed published work. In both ANN and GEP models, eight main parameters were considered as input variables, including the beam width (b) b ) and depth (d), d ), steel and FRP reinforcement area (As A s and A f ), yield strength of steel bar (fy), f y ), concrete compressive strength (fc), f c ), the elasticity modulus of FRP bar (Ef) E f ) and the ultimate tensile strength of FRP bar (ffu). f f u ). The results demonstrated that the proposed ML models had lower mean absolute error (MAE), MAE ), mean absolute percentage error ( MAPE ) and root mean squared error ( RMSE ) as well as higher correlation coefficient (R2) R 2 ) than the ACI 440.11-22 equations. Finally, a parametric study was conducted using the suggested ML models to explore the effect of each input variable on the flexural strength of hybrid FRP-steel RC beams.

关键词： Flexural strength Hybrid FRP-steel reinforcement Machine learning Artificial neural network gene expression programming Data-driven

来源：评论

学校读者我要写书评

暂无评论

Assessment of flow characteristics through a grassed canal

引用

INNOVATIVE INFRASTRUCTURE SOLUTIONS 2022年第1期7卷 1-18页

作者： Gad, Manal Sobeih, Mohamed F. Rashwan, I. M. H. Helal, Esam Delta Higher Inst Engn & Technol Civil Engn Dept Mansoura Egypt Menoufiya Univ Fac Engn Hydraul Civil Engn Dept Mansoura Egypt Tanta Univ Fac Engn Hydraul Irrigat & Hydraul Engn Dept Tanta Egypt El Menoufiya Univ Fac Engn Civil Engn Dept Al Minufiyah Egypt

Vegetation is defined as a kind of surface roughness, which reduces the capacity of the channel and retards the flow by causing loss of energy through turbulence and drag forces of moving water. In water channels, vegetation maybe used to stabilize the water surface and prevent erosion caused by concentrated water flow. In terms of channel lining, grass offers the least expensive option and is the most esthetically pleasing. Most previous studies on this subject were conducted using artificial vegetation in laboratory experiments;research conducted in canals with natural vegetation is lacking. In this study, flow characteristics through a natural grassed canal are studied. In addition, the Manning coefficient and specific energy were determined based on field measurements for both grassed and un-grassed canals. The fieldwork was conducted on Ganabia 9B, southeast of El-Mahalla El Kubra, El-Gharbia, Egypt. The average heights of vegetation in the grassed canal ranged from (28 to 100) cm and the values of flow rate range from (0.0504 to 0.1127) m(3)/s. The number of tests is 42 tests for the un-grassed canal and 205 tests for the grassed canal. This study indicated that the Manning coefficient increased with an increase in energy and momentum coefficients. The energy coefficient increased with a decrease in relative specific energy and an increase in grass height. The un-grassed canal exhibited a smaller relative specific energy than the grassed canal. The momentum coefficients for the non-grassed and grassed canals were 1.015-1.517 and 1.003-1.655, respectively. Therefore, the un-grassed canal showed a higher momentum coefficient than the grassed canal at a ratio of 0.264-1.196%. The relative specific energy was calculated in two ways: (i) using the actual energy coefficient values and (ii) setting it equal to one. As such, the error percentages of the specific energy for the grassed and un-grassed canals were 0.000105-0.1652% and 0.0048-0.2194%, respectively. The re

关键词： Froude number gene expression programming Grassed canal Manning's coefficient Specific energy Submerged Un-grassed canal Un-submerged

来源：评论

学校读者我要写书评

暂无评论

Migration-Based Load Balance of Virtual Machine Servers in Cloud Computing by Load Prediction Using genetic-Based Methods

引用

IEEE ACCESS 2021年 9卷 49760-49773页

作者： Hung, Lung-Hsuan Wu, Chih-Hung Tsai, Chiung-Hui Huang, Hsiang-Cheh Natl Univ Kaohsiung Dept Elect Engn Kaohsiung 811 Taiwan

This paper presents a two-stage genetic mechanism for the migration-based load balance of virtual machine hosts (VMHs) in cloud computing. Previous methods usually assume this issue as a job-assignment optimization problem and only consider the current VMHs' loads;however, without considering loads of VMHs after balancing, these methods can only gain limited effectiveness in real environments. In this study, two genetic-based methods are integrated and presented. First, performance models of virtual machines (VMs) are extracted from their creating parameters and corresponding performance measured in a cloud computing environment. The gene expression programming (GEP) is applied for generating symbolic regression models that describe the performance of VMs and are used for predicting loads of VMHs after load-balance. Secondly, with the VMH loads estimated by GEP, the genetic algorithm considers the current and the future loads of VMHs and decides an optimal VM-VMH assignment for migrating VMs and performing load-balance. The performance of the proposed methods is evaluated in a real cloud-computing environment, Jnet, wherein these methods are implemented as a centralized load balancing mechanism. The experimental results show that our method outperforms previous methods, such as heuristics and statistics regression.

关键词： Cloud computing Load management Hardware Virtualization Servers Computational modeling Virtual machine monitors Cloud computing virtualization load balancing migration genetic algorithm gene expression programming

来源：评论

学校读者我要写书评

暂无评论

Data mining for fast and accurate makespan estimation in machining workshops

引用

JOURNAL OF INTELLIGENT MANUFACTURING 2021年第2期32卷 483-500页

作者： Cheng, Lixin Tang, Qiuhua Zhang, Zikai Wu, Shiqian Wuhan Univ Sci & Technol Key Lab Met Equipment & Control Technol Wuhan 430081 Peoples R China Wuhan Univ Sci & Technol Hubei Key Lab Mech Transmiss & Mfg Engn Wuhan 430081 Peoples R China Wuhan Univ Sci & Technol Inst Robot & Intelligent Syst Sch Informat Sci & Engn Wuhan 430081 Peoples R China

The fast and accurate estimation of makespan is essential for the determination of the delivery date and the sustainable development of the enterprise. In this paper, a high-quality training dataset is constructed and an adaptive ensemble model is proposed to achieve fast and accurate makespan estimation. First, both the logistics features extracted by the Pearson correlation coefficient and the new meaningful nonlinear combination features dug out by gene expression programming are first involved in this paper for constructing a high-quality dataset. Secondly, an improved clustering with elbow criterion and a resampling operation are applied simultaneously to generate representative subsets;and correspondingly, several back propagation neural network (BPNN) with the architecture optimized by genetic algorithm are trained by these subsets respectively to generate effective diverse learners;and then, a K-nearest neighbor based dynamic weight combination strategy which is sensitive to current testing sample is proposed to make full use of the learner's positive effects and avoid its negative effects. Finally, the results of effective experiments prove that both the newly involved features and the improvements in the proposed ensemble are effective. In addition, comparison experiments confirm that the proposed enhanced ensemble of BPNNs outperforms significantly the prevailing approaches, including single, ensemble and hybrid models. And hence, the proposed model can be utilized as a convenient and reliable tool to support customer order acceptance.

关键词： Makespan estimation Ensemble of BPNN gene expression programming Clustering genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Prediction of Catenary Action Capacity of RC Beam-Column Substructures under a Missing Column Scenario Using Evolutionary Algorithm

引用

KSCE JOURNAL OF CIVIL ENGINEERING 2021年第3期25卷 891-905页

作者： Azim, Iftikhar Yang, Jian Iqbal, Muhammad Farjad Mahmood, Zafar Javed, Muhammad Faisal Wang, Feiliang Liu, Qing-feng Shanghai Jiao Tong Univ Sch Naval Architecture Ocean & Civil Engn Shanghai Key Lab Digital Maintenance Bldg & Infra Shanghai 200240 Peoples R China GIK Inst Engn Sci & Technol Dept Civil Engn Topi 23460 Pakistan Univ Agr Dept Maths Stats & Comp Sci Peshawar 25000 Pakistan COMSATS Univ Islamabad Dept Civil Engn Abbottabad 22060 Pakistan Shanghai Jiao Tong Univ State Key Lab Ocean Engn Shanghai 200240 Peoples R China

Catenary action plays crucial role in resisting the applied vertical load at large deformations stage in reinforced concrete (RC) structures. This paper aims to predict the catenary action capacity of RC beam-column substructures by utilizing the distinctive properties of gene expression programming (GEP). The input parameters selected for the modelling are: double-beam span-to-depth ratio, relative axial restraints stiffness, relative rotational restraints stiffness, bottom and top longitudinal reinforcement ratios, and yield strength of longitudinal rebars. A comprehensive and reliable database was collated from internationally published research articles to develop and verify the model. The GEP-based model was assessed by comparing its performance with regression based model. Various statistical indicators and external validation criteria suggested in literature proved that the model is accurate and possess high prediction and generalization capacity. Sensitivity analysis was carried out to show the contributions of the input parameters, while parametric analysis was performed to show that the proposed model is not merely a combination of the input parameters but can accurately represent the given physical system. The proposed formulation from GEP is found to be simple, robust, and easy to utilize for pre-design purposes.

关键词： Progressive collapse Catenary action gene expression programming RC beam-column substructure Regression analysis

来源：评论

学校读者我要写书评

暂无评论

Nondestructive prediction of rutting resistance of in-service middle asphalt layer based on gene expression programing

引用

CONSTRUCTION AND BUILDING MATERIALS 2021年 293卷 123481-123481页

作者： Yao, Linyi Leng, Zhen Jiang, Jiwang Ni, Fujian Zhao, Zili Hong Kong Polytech Univ Dept Civil & Environm Engn Kowloon Hong Kong 999077 Peoples R China Southeast Univ Sch Transportat Dept Roadway Engn Nanjing Jiangsu Peoples R China

For a multilayered asphalt pavement, rutting resistance of the mixture in the middle asphalt layer underneath the surface course plays a significant role in the high-tempearture stability of the whole pavement structure. Thus, evaluation of the rutting resistance of the middle asphalt layer using field cores is often necessary for project-level pavement maintenance decision-making. However, the extrusion and tests of field cores are time-consuming and destructive to pavement. To address this problem, developing an empirical model to predict the rutting resistance of the middle asphalt layer at a certain service time from historical test results may be a potential alternative. This study aims to address this challenge by using the gene expression programming (GEP) method and a database composed of a large number of multiple stress repeated load (MSRL) test results of field cores. By correlating the compound creep rate (CCR) of the middle asphalt layer from the MSRL tests to material properties, environmental and traffic parameters, field rutting depth, and middle layer age, the optimal GEP model was developed, and then compared with the conventional multiple linear regression (MLR) model built on the same database. Uncertainty analysis was also conducted through the Monte Carlo simulation (MCs). It was found that the GEP model outperformed the MLR model, with a 6%-7% higher R-square. The uncertainty analysis allows the transport agencies to estimate the reliability of their prediction and make maintenance and rehabilitation (M&R) plans according to the specified reliability target. (c) 2021 Elsevier Ltd. All rights reserved.

关键词： In-service asphalt mixture Rutting resistance Pavement maintenance gene expression programming Uncertainty analysis

来源：评论

学校读者我要写书评

暂无评论

A hybrid GEP and WOA approach to estimate the optimal penetration rate of TBM in granitic rock mass

引用

SOFT COMPUTING 2021年第17期25卷 11877-11895页

作者： Li, Zimu Bejarbaneh, Behnam Yazdani Asteris, Panagiotis G. Koopialipoor, Mohammadreza Armaghani, Danial Jahed Tahir, M. M. Southwest Univ Sch Comp & Informat Sci Chongqing 400715 Peoples R China Univ Teknol Malaysia Fac Civil Engn Dept Geotech & Transportat Skudai 81310 Johor Malaysia Sch Pedag & Technol Educ Computat Mech Lab Athens 14121 Greece Amirkabir Univ Technol Fac Civil & Environm Engn Tehran 15914 Iran Univ Malaya Fac Engn Dept Civil Engn Kuala Lumpur 50603 Malaysia Univ Teknol Malaysia UTM Construct Res Ctr Sch Civil Engn Inst Smart Infrastruct & Innovat Construct ISI Johor Baharu 81310 Johor Malaysia

The efficiency of tunnel boring machines (TBMs) in underground projects has great significance for the mining and tunneling industries, demanding a reliable estimation of the TBM's performance in different geotechnical conditions. The current research work attempted to suggest an optimal predictor model of TBM performance as a reliable alternative to experimental and numerical techniques. To achieve this target, three data-mining techniques, namely neural network (NN), gene expression programming (GEP), and multivariate adaptive regression splines (MARS), were employed for modelling the TBM performance, and then the most robust predictive model was optimized via a metaheuristic search method known as whale optimization algorithm (WOA). For the modelling purpose, an experimental database was compiled by performing a field assessment program in a tunneling project in Malaysia and then conducting laboratory testing on the derived rock specimens. Based on the measured experimental data, the six most influential parameters were identified and served as model inputs to predict penetration rate (PR). In order to indicate the capability of the developed GEP and NN models, a stepwise linear regression model, i.e., MARS, was designed for PR prediction as well. The predictive capacity of the constructed models was quantified using a series of statistical indices, i.e., root mean squared error (RMSE), determination coefficient (R-2) and variance account for (VAF). Based on the computed indices for testing records, both the proposed GEP and NN models (with RMSE values of 0.1882 and 0.2120 and R-2 values of 0.9058 and 0.8735, respectively) yielded more accurate predictive results than the MARS model with RMSE of 0.2553 and R-2 of 0.8346. Hence, by achieving the most robust performance compared to the rest, GEP-based model can provide a new practical equation with a high level of accuracy. In other part of this study, the six input parameters of the GEP model and its equation were

关键词： TBM performance Penetration rate gene expression programming Neural network Multivariate adaptive regression splines Whale optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Introduction of ABCEP as an automatic programming method

引用

INFORMATION SCIENCES 2021年 545卷 575-594页

作者： Nekoei, Masood Moghaddas, Seyed Amirhossein Golafshani, Emadaldin Mohammadi Gandomi, Amir H. Amirkabir Univ Technol Dept Elect Engn Tehran Iran Islamic Azad Univ Sci & Res Branch Dept Civil Engn Tehran Iran Univ Technol Sydney Fac Engn & Informat Technol Sydney NSW 2007 Australia

Automatic programming is a branch of artificial intelligence that presents each solution as a mathematical formula based on heuristic mechanisms. In this study, artificial bee colony expression programming (ABCEP) is presented, which is combined simultaneously with expression programming. By using expression sharing to generate new solutions, the proposed method can minimize certain deficiencies of artificial bee colony programming, such as weak convergence and high locality. A total number of 15 real-world regression benchmark functions was used to evaluate the performance of the proposed model. For comparison purposes, successful run percentage, mean best cost, convergence performance, and run time of ABCEP were compared to those of other tested automatic programming algorithms, including artificial bee colony programming, gene expression programming, genetic programming, and quick artificial bee colony programming. A Wilcoxon signed-rank test was also done to compare the behavior of the algorithms. Additionally, the accuracy of all algorithms was then evaluated using three real-world practical benchmarks. The results indicate that the predictions generated by ABCEP are better than those obtained by other control algorithms based on successful runs, mean fitness values, and convergence rate. (C) 2020 Elsevier Inc. All rights reserved.

关键词： Automatic programming Artificial bee colony expression programming gene expression programming genetic programming

来源：评论

学校读者我要写书评

暂无评论

Predicting the mechanical properties of plastic concrete: An optimization method by using genetic programming and ensemble learners

引用

CASE STUDIES IN CONSTRUCTION MATERIALS 2024年 20卷

作者： Asif, Usama Javed, Muhammad Faisal Abuhussain, Maher Ali, Mujahid Khan, Waseem Akhtar Mohamed, Abdullah Nazarbayev Univ Dept Civil Engn Astana Kazakhstan Ghulam Ishaq Khan Inst Engn Sci & Technol Dept Civil Engn Topi Pakistan Univ Louisiana Lafayette Dept Civil Engn Lafayette LA 70503 USA Silesian Tech Univ Fac Transport & Aviat Engn Dept Transport Syst Traff Engn & Logist Krasinskiego 8 St PL-40019 Katowice Poland Umm Al Qura Univ Coll Engn & Comp Al Qunfudah Dept Civil & Environm Engn Mecca Saudi Arabia Future Univ Egypt Res Ctr New Cairo 11835 Egypt

This study presents a comparative analysis of individual and ensemble learning algorithms (ELAs) to predict the compressive strength (CS) and flexural strength (FS) of plastic concrete. Multilayer perceptron neuron network (MLPNN), Support vector machine (SVM), random forest (RF), and decision tree (DT) were used as base learners, which were then combined with bagging and Adaboost methods to improve the predictive performance. In addition, gene expression programming (GEP) was used to develop computational equations that can be used to predict the CS and FS of plastic concrete. An extensive database containing 357 and 125 data points was obtained from the literature, and the eight most impactful ingredients were used in the model's development. The accuracy of all models was assessed using several statistical measures, including an error matrix, Akaike information criterion (AIC), K-fold cross-validation, and other external validation equations. Furthermore, sensitivity and SHAP analysis were performed to evaluate input variables' relative significance and impact on the anticipated CS and FS. Based on statistical measures and other validation criteria, GEP outpaces all other individual models, whereas, in ELAs, the SVR ensemble with Adaboost and RF modified with the Bagging technique demonstrated superior performance. SHapley Additive exPlanations (SHAP) and sensitivity analysis reveal that plastic, cement, water, and the age of the specimens have the highest influence, while superplasticizer has the lowest impact, which is consistent with experimental studies. Moreover, GUI and GEP-based simple mathematical correlation can enhance the practical scope of this study and be an effective tool for the pre-mix design of plastic concrete.

关键词： Plastic concrete Machine learning Compressive strength Flexural strength Sustainability Ensemble learning algorithms gene expression programming

来源：评论

学校读者我要写书评

暂无评论

Development of soft computing-based models for forecasting water quality index of Lorestan Province, Iran

引用

SCIENTIFIC REPORTS 2024年第1期14卷 1-17页

作者： Singh, Balraj Sepahvand, Alireza Sihag, Parveen Singh, Karan Prabha, Chander Nag, Anindya Hassan, Md. Mehedi Vimal, S. Kang, Dongwann Panipat Inst Engn & Technol Panipat 132102 India Lorestan Univ Khorramabad *** Iran Chandigarh Univ Mohali 140413 India Graphic Era Dept Civil Engn Dehra Dun 248002 India Chitkara Univ Chitkara Univ Inst Engn & Technol Rajpura Punjab India Khulna Univ Comp Sci & Engn Discipline Khulna Bangladesh Sri Eshwar Coll Engn Ctr Excellence Data Sci Dept Artificial Intelligence & Data Sci Coimbatore 641202 India Seoul Natl Univ Sci & Technol Dept Comp Sci & Engn Seoul 01811 South Korea

The Water Quality Index (WQI) is widely used as a classification indicator and essential parameter for water resources management projects. WQI combines several physical and chemical parameters into a single metric to measure the status of Water Quality. This study explores the application of five soft computing techniques, including gene expression programming, Gaussian Process, Reduced Error Pruning Tree (REPt), Artificial Neural Network with FireFly (ANN-FFA), and combinations of Reduced Error Pruning Tree with bagging. These models aim to predict the WQI of Khorramabad, Biranshahr, and Alashtar sub-watersheds in Lorestan province, Iran. The dataset consists of 124 observations, with input variables being sulfate (SO4), total dissolved solids (TDS), the potential of Hydrogen (pH), chloride (Cl), electrical conductivity (EC), Potassium (K), bicarbonate (HCO), magnesium (Mg), sodium (Na), and calcium (Ca), and WQI as the output variable. For model creation (train subset) and model validation (test subset), the data were split into two subsets (train and test) in a ratio of 70:30. The performance evaluation parameters values of training and testing stages of various models indicate that the ANN-FFA based data-driven model performs better than the other modeling techniques applied with the values of coefficient of correlation 0.9990 & 0.9989;coefficient of determination 0.9612 & 0.9980;root mean square error 0.3036 & 0.3340;Nash-Sutcliffe error 0.9980 & 0.9979;and Mean average percentage error 0.7259% & 0.7969% for the train and test subsets, respectively. Taylor diagram results also suggest that ANN-FFA is the best-performing model, followed by the GEP model. This study introduces a novel model for predicting WQI using advanced soft computing models that have not been previously applied in this study area, highlighting its novelty and relevance. The proposed model significantly enhances predictive accuracy and efficiency, offering real-time, cost-effective WQI predi

关键词： Water quality index Artificial neural network FireFly algorithm gene expression programming Reduced error pruning tree Lorestan Province

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：