检索结果-内蒙古大学图书馆

A comparison of monthly precipitation point estimates at 6 locations in Iran using integration of soft computing methods and GARCH time series model

引用

JOURNAL OF HYDROLOGY 2017年 554卷 721-742页

作者： Mehdizadeh, Saeid Behmanesh, Javad Khalili, Keivan Urmia Univ Water Engn Dept Orumiyeh Iran

Precipitation plays an important role in determining the climate of a region. Precise estimation of precipitation is required to manage and plan water resources, as well as other related applications such as hydrology, climatology, meteorology and agriculture. Time series of hydrologic variables such as precipitation are composed of deterministic and stochastic parts. Despite this fact, the stochastic part of the precipitation data is not usually considered in modeling of precipitation process. As an innovation, the present study introduces three new hybrid models by integrating soft computing methods including multivariate adaptive regression splines (MARS), Bayesian networks (BN) and gene expression programming (GEP) with a time series model, namely generalized autoregressive conditional heteroscedasticity (GARCH) for modeling of the monthly precipitation. For this purpose, the deterministic (obtained by soft computing methods) and stochastic (obtained by GARCH time series model) parts are combined with each other. To carry out this research, monthly precipitation data of Babolsar, Bandar Anzali, Gorgan, Ramsar, Tehran and Urmia stations with different climates in Iran were used during the period of 1965-2014. Root mean square error (RMSE), relative root mean square error (RRMSE), mean absolute error (MAE) and determination coefficient (R-2) were employed to evaluate the performance of conventional/single MARS, BN and GEP, as well as the proposed MARS-GARCH, BN-GARCH and GEP-GARCH hybrid models. It was found that the proposed novel models are more precise than single MARS, BN and GEP models. Overall, MARS-GARCH and BN-GARCH models yielded better accuracy than GEP-GARCH. The results of the present study confirmed the suitability of proposed methodology for precise modeling of precipitation. (C) 2017 Elsevier B.V. All rights reserved.

关键词： Bayesian networks gene expression programming generalized autoregressive conditional heteroscedasticity Modeling Multivariate adaptive regression splines Precipitation

来源：评论

学校读者我要写书评

暂无评论

Prediction of water quality index in free surface constructed wetlands

引用

ENVIRONMENTAL EARTH SCIENCES 2016年第2期75卷 1-12页

作者： Mohammadpour, Reza Shaharuddin, Syafiq Zakaria, Nor Azazi Ghani, Aminuddin Ab. Vakili, Mohammadtaghi Chan, Ngai Weng Islamic Azad Univ Dept Civil Engn Estahban Iran Univ Sains Malaysia River Engn & Urban Drainage Res Ctr REDAC Engn Campus Nibong Tebal 14300 Penang Malaysia Univ Sains Malaysia Sch Ind Technol George Town 11800 Malaysia Univ Sains Malaysia Sch Humanities George Town 11800 Malaysia

Water quality and its effects on human life have become one of the major concerns in aquatic ecosystems. The water quality index (WQI) is defined as a parameter to interpret water-monitoring data and clarify the quality of water. In this study, the gene expression programming (GEP) and artificial neural networks (ANNs) were employed to predict WQI in free surface constructed wetlands. Seventeen points of a selected wetland were monitored twice a month over a period of 14 months, and an extensive data set was collected for 11 water quality variables (WQVs). A principal factor analysis (PFA) indicated that WQI was greatly affected by pH and SS, while temperature no has significant effect on the WQI in tropical areas. A sensitivity analysis was carried out to reduce the number of 11 WQVs in prediction of the WQI. Subsequently, five significant parameters, pH, suspended solid (SS), ammoniacal nitrogen (AN), dissolved oxygen (DO) and chemical oxygen demand were selected to develop a GEP and ANNs. The GEP was able to successfully predict the WQI with high accuracy (R-2 = 0.983 and MAE = 0.295). The statistical parameters indicate that, although the ANNs with R-2 = 0.988 and MAE = 0.013 produced better results compared with GEP, the GEP-based formula is more useful for practical purposes. The GEP and ANNs are recommended as rapid and powerful WQI evaluation techniques to reduce substantial effort and time by optimizing the calculations.

关键词： Constructed wetland gene expression programming Water quality index Surface water Principal factor analysis Artificial neural networks

来源：评论

学校读者我要写书评

暂无评论

Prediction of scour depth at piers with debris accumulation effects using linear genetic programming

引用

MARINE GEORESOURCES & GEOTECHNOLOGY 2020年第4期38卷 468-479页

作者： Jamei, Mehdi Ahmadianfar, Iman Shohadaye Hoveizeh Univ Technol Fac Engn Dasht E Azadegan Susangerd Iran Behbahan Khatam Alanbia Univ Technol Dept Civil Engn Behbahan Iran

Exact evaluation of scour depth around piers under debris accumulation is crucial for the safe design of pier structures. Experimental studies on scouring around pier bridges with debris accumulation have been conducted to estimate the maximum scour depth using various empirical relationships. However, due to the oversimplification of a complex process, the proposed relationships have not always been able to accurately predict the pier scour depth. This research proposes linear genetic programming (LGP) approach as an extension of the genetic programming to predict the scour depth around bridge piers. Among the artificial intelligence techniques, LGP and locally weighted linear regression (LWLR) models have not been used to predict the scour depth at bridge piers. Literature experimental data were collected and used to develop the models. The performance of the LGP method was compared with gene-expression programming, LWLR, multilinear regression and empirical equations using rigorous statistical criteria. The correlation coefficient (R) and the root mean squared error (RMSE) were (R=0.962, RMSE =0.31) and (R=0.885, RMSE =0.542) for the LGP and LWLR, respectively. The results demonstrated the superiority of the LGP method for increasing the accuracy of the predicted scour depth in comparison with the other models.

关键词： Debris accumulation linear genetic programming locally weighted linear regression gene expression programming multi linear regression scour depth

来源：评论

学校读者我要写书评

暂无评论

A novel hybrid neural network based on phase space reconstruction technique for daily river flow prediction

引用

SOFT COMPUTING 2018年第7期22卷 2205-2215页

作者： Delafrouz, Hadi Ghaheri, Abbas Ghorbani, Mohammad Ali Iran Univ Sci & Technol Sch Civil Engn Tehran Iran Univ Tabriz Dept Water Engn Tabriz Iran

The main purpose of this study is to construct a new hybrid model (PSR-ANN) by combining phase space reconstruction (PSR) and artificial neural network (ANN) techniques to raise the accuracy for the prediction of daily river flow. For this purpose, river flow data at three measurement stations of the USA were used. To reconstruct the phase space and determine the input data for the PSR-ANN method, the delay time and embedding dimension were calculated by average mutual information and false nearest neighbors analysis. The presence of chaotic dynamics in the used data was identified by the correlation dimension methods. The results of the PSR-ANN, pure ANN and gene expression programming (GEP) models were inter-compared using the Nash-Sutcliffe and root-mean-square error criteria. The inter-comparisons showed that the proposed PSR-ANN method provides the best prediction of daily river flow. Moreover, the ANN model showed higher ability than the pure GEP in estimation of the river flow.

关键词： Artificial neural network gene expression programming Phase space reconstruction Prediction River flow

来源：评论

学校读者我要写书评

暂无评论

Estimating n-tetradecane/bitumen mixture viscosity in solvent-assisted oil recovery process using GEP and GMDH modeling approaches

引用

PETROLEUM SCIENCE AND TECHNOLOGY 2019年第14期37卷 1640-1647页

作者： Rostami, Alireza Hemmati-Sarapardeh, Abdolhossein Mohammadi, Amir H. PUT Dept Petr Engn Ahvaz Iran Shahid Bahonar Univ Kerman Dept Petr Engn Kerman Iran IRGCP Paris France Univ KwaZulu Natal Sch Engn Discipline Chem Engn Durban South Africa

In this study, the methods of group method of data handling (GMDH) and gene expression programming (GEP) were used to develop symbolic correlations for truthful viscosity estimation of n-tetradecane/bitumen mixture. A number of graphical and statistical tools were utilized to make evident the omnipotence of the proposed models as compared to the published literature correlations. It is found that the GMDH model is the best acting approach with the lowest total error of 2.51% and the highest R-2 of 0.9994. Sensitivity analysis verifies that concentration of the solvent is the most influencing input parameter on the viscosity estimation of n-tetradecane/bitumen mixture.

关键词： bitumen viscosity gene expression programming group method of data handling solvent-assisted recovery process sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

Prediction of barite scale formation and inhibition in hydrocarbon reservoirs using AI modeling: Focus on different optimization algorithms

引用

Results in Engineering 2025年 26卷

作者： Ouafa Belkacem Ahmed Rezrazi Kamel Aizi Lokmane Abdelouahed Maamar Laidi Abdelhafid Touil Leila Cherifi Salah Hanini Laboratory of Biomaterials and Transport Phenomena (LBMTP) Yahia Fares University Medea Algeria The Central Directorate of Research and Development (DCRD) SONATRACH Boumerdes Algeria Laboratoire des sciences et technologies de l’information de la communication et de la connaissance (Lab-STICC) University of Bretagne Sud France LSPC—Laboratoire de Securité des Procédes Chimiques INSA Rouen Normandie UNIROUEN Normandie Univiversity 76000 Rouen France

Barite scale formation is a persistent and detrimental challenge in the oil industry during water-flooding operations, primarily due to the incompatibility between injected water and formation water. This study introduces a novel and highly effective approach for predicting barite scale formation and inhibition by leveraging advanced artificial intelligence (AI) techniques. Innovative intelligent models, including Random Forest (RF), k-nearest Neighbors (KNN), Extreme Learning Machine (ELM), Support Vector Regression (SVR), Decision Trees (DT), and Multilayer Perceptron (MLP), were developed and optimized for this purpose. Notably, the MLP and SVR models were enhanced through training with the particle swarm optimization algorithm (PSO) and data augmentation techniques. The performance of the models was rigorously evaluated using statistical criteria and graphical tools, demonstrating exceptional accuracy with minimal errors. The ELM model emerged as the most precise (RMSE = 0.0005, R² = 0.999), closely followed by the SVR-PSO model (RMSE = 0.0008, R² = 0.999). Additionally, the ELM model successfully estimated over 95 % of the data points, with an applicability domain of 97.82 %. Moreover, we conducted an additional validation using a new independent dataset, which showed an excellent correlation coefficient (0.99) and a very low RMSE (0.01), further demonstrating the robustness and generalizability of the proposed models. This work shows the transformative potential of AI-driven modeling in addressing complex challenges such as barite scale formation. The findings underscore the practical implications of AI techniques in optimizing oilfield operations, enhancing efficiency, and reducing costs, thereby offering a significant advancement in the field.

关键词： Barite Inhibition Formation Intelligent models Water flooding Data augmentation AI Artificial Intelligence ANN Artificial Neural Network ANNs Artificial Neural Networks AARE Average Absolute Relative Error ARE Absolute Relative Error BFGS Broyden-Fletcher-Goldfarb-Shanno BR Bayesian Regularization C Ba ₂₊ Barium concentration C So4 ₂- Sulfate concentration C inb Concentration of barite inhibitor Cp Solubility of barite scale inhibitors C SVR specific parameter CFBPN Cascade-Forward Back-Propagation Network DETPMP Diethylenetriaminepenta (methylene phosphonic acid) DT Decision Tree EOR Enhanced Oil Recovery ELM Extreme Learning Machine GEP gene expression programming GBDT Decision Trees Optimized by Gradient Boosting GRNN generalized Regression Neural Network GWO Grey Wolf Optimizer Kᵢ Initial permeability K d The detected permeability K d exp Experimental permeability damage K d pred Predicted permeability damage Knn The k-nearest neighbors LSSVM Least Squares Support Vector Machine MLP Multi-Layer Perceptron MSE Mean Square Error MAE Mean Absolute Error Q Flow rate PPCA Poly-Phosphono Carboxylic Acid PSO Particle Swarm Optimization RELU Rectified Linear Unit RBF Radial Basis Function RMSE Root Mean Square Error R 2 Correlation Coefficient RF Random Forest SCG Scaled Conjugate Gradient SVR Support Vector Regression SVM Support Vector Machine SD Standard Deviation SHAP Shapley additive explanations T Temperature t Injection time V inj Volume of water injection ΔP Differential pressure ε Epsilon, SVR specific parameter

来源：评论

学校读者我要写书评

暂无评论

A novel ensemble model for predicting the performance of a novel vertical slot fishway

引用

Frontiers of Structural and Civil Engineering 2020年第6期14卷 1418-1444页

作者： Aydin SHISHEGARAN Mohammad SHOKROLLAHI Ali MIRNOROLLAHI Arshia SHISHEGARAN Mohammadreza MOHAMMAD KHANI Deparlment of Water and Environmental Engineering School of Civil EngineeringIran University of Science and TechnologyTehran ***Iran Department of Water and Environmental Engineering School of Civil EngineeringSemnan UniversitySemnan 35131-19111Iran Department of Water and Enironmental Engineering School of Civil EngineeringIslamic Azad University Central Tehran BranchTehran ***Iran School of Progress Engineering Iran University of Science and TechnologyTehran ***Iran

We investigate the performance of a novel vertical slot fishway by employing finite volume and surrogate *** linear regression,multiple log equation regression,gene expression programming,and combinations of these models are employed to predict the maximum turbulence,maximum velocity,resting area,and water depth of the middle pool in the *** statistical parameters and error terms,including the coefficient of determination,root mean square error,normalized square error,maximum positive and negative errors,and mean absolute percentage error were employed to evaluate and compare the accuracy of the *** also conducted a parametric *** independent variables include the opening between bafles(OBB),the ratio of the length of the large and small baffles,the volume flow rate,and the angle of the large *** results show that the key parameters of the maximum turbulence and velocity are the volume flow rate and OBB.

关键词： novel vertical slot fishway parametric study finite volume method ensemble model gene expression programming

来源：评论

学校读者我要写书评

暂无评论

An innovative model for predicting the displacement and rotation of column-tree moment connection under fire

引用

Frontiers of Structural and Civil Engineering 2021年第1期15卷 194-212页

作者： Mohammad Ali NAGHSH Aydin SHISHEGARAN Behnam KARAMI Timon RABCZUK Arshia SHISHEGARAN Hamed TAGHAVIZADEH Mehdi MORADI Department of Civil Engineering Isfahan University of TechnologyIsfahan 84156-83111Iran School of Civil Engineering School of Civil EngineeringIran University of Science and TechnologyTehran 13114-16846Iran Department of Civil Engineering International Institute of Earthquake Engineering and SeismologyTehran 19539-14453Iran Division of Computational Mechanics Ton Duc Thang UniversityHo Chi Minh CityVietnam Faculty of Civil Engineering Ton Duc Thang UniversityHo Chi Minh CityVietnam Department of Civil Engineering Islamic Azad UniversityTehran 16511-53311Iran Department of Civil Engineering Isfahan UniversityIsfahan 81746-73441Iran

In this study,we carried out nonlinear finite element simulations to predict the performance of a columntree moment connection(CTMC)under fire and static *** also conducted a detailed parameter study based on five input variables,including the applied temperature,number of flange bolts,number of web bolts,length of the beam,and applied static *** first variable is changed among seven levels,whereas the other variables are changed among three *** the Taguchi method for variables 2-5 and their levels,9 samples were designed for the parameter study,where each sample was exposed to 7 different temperatures yielding 63 *** related variables for each output are imported for the training and testing of different surrogate *** surrogate models include a multiple linear regression(MLR),multiple Ln equation regression(MLnER),an adaptive network-based fuzzy inference system(ANFIS),and gene expression programming(GEP).44 samples were used for training randomly while the remaining samples were employed for *** show that GEP outperforms MLR,MLnER,and *** results indicate that the rotation and deflection of the CTMC depend on the *** addition,the fire resistance increases with a decrease in the beam length;thus,a shorter beam can increase the fire resistance of the *** numbers of flanges and web bolts slightly affect the rotation and displacement of the CTMCs at temperatures of above 400℃.

关键词： column-tree moment connection Finite element model parametric study fire regression models gene expression programming

来源：评论

学校读者我要写书评

暂无评论

Interpretable machine learning approaches to assess the compressive strength of metakaolin blended sustainable cement mortar

引用

Scientific reports 2025年第1期15卷 19414页

作者： Naseer Muhammad Khan Liqiang Ma Waleed Bin Inqiad Muhammad Saud Khan Imtiaz Iqbal Muhammad Zaka Emad Saad S Alarifi Xinjiang Key Laboratory of Coal-bearing Resources Exploration and Exploitation Xinjiang Institute of Engineering Urumqi 830023 China. nmkhan@mce.nust.edu.pk. Key Laboratory of Xinjiang Coal Resources Green Mining (Xinjiang Institute of Engineering) Ministry of Education Urumqi 830023 China. nmkhan@mce.nust.edu.pk. Xinjiang Engineering Research Center of Green Intelligent Coal Mining Xinjiang Institute of Engineering Urumqi 830023 China. nmkhan@mce.nust.edu.pk. Sustainable Advanced Geomechanical Engineering Military College of Engineering National University of Sciences and Technology Risalpur 23200 Pakistan. nmkhan@mce.nust.edu.pk. School of Mines China University of Mining and Technology Xuzhou 221116 Jiangsu China. nmkhan@mce.nust.edu.pk. Xinjiang Key Laboratory of Coal-bearing Resources Exploration and Exploitation Xinjiang Institute of Engineering Urumqi 830023 China. ckma@***. Key Laboratory of Xinjiang Coal Resources Green Mining (Xinjiang Institute of Engineering) Ministry of Education Urumqi 830023 China. ckma@***. Xinjiang Engineering Research Center of Green Intelligent Coal Mining Xinjiang Institute of Engineering Urumqi 830023 China. ckma@***. School of Mines China University of Mining and Technology Xuzhou 221116 Jiangsu China. ckma@***. Department of Civil Engineering College of Engineering & Physical Sciences Aston University Aston St Birmingham B4 7ET UK. Department of Civil Engineering Price Faculty of Engineering University of Manitoba Winnipeg MB R3T 5V6 Canada. Department of Petroleum Engineering King Fahd University of Petroleum and Minerals Dhahran Eastern Province Saudi Arabia. Department of Geology and Geophysics College of Science King Saud University P.O. Box 2455 Riyadh 11451 Saudi Arabia.

The use of naturally available materials such as metakaolin (MK) can greatly reduce the utilization of emission intensive materials like cement in the construction sector. This would reduce the stress on depleting natural resources and foster a sustainable construction industry. However, the laboratory determination of 28 day compressive strength (C-S) of MK-based mortar is associated with several time and resource constraints. Thus, this study was conducted to develop reliable empirical prediction models to assess CS of MK-based mortar from its mixture proportion using machine learning algorithms like gene expression programming (GEP), extreme gradient boosting (XGB), multi expression programming (MEP), bagging regressor (BR), and AdaBoost etc. A comprehensive dataset compiled from published literature having five input parameters including water-to-binder ratio, mortar age, and maximum aggregate diameter etc. was used for this purpose. The developed models were validated by means of error metrics, residual assessment, and external validation checks which revealed that XGB is the most accurate algorithm having testing [Formula: see text] of 0.998 followed by BR having [Formula: see text] values equal to 0.946 while MEP had the lowest testing [Formula: see text] of 0.893. However, MEP and GEP algorithms expressed their output in the form of empirical equations which other black-box algorithms couldn't produce. Moreover, interpretable machine learning approaches including shapely additive explanatory analysis (SHAP), individual conditional expectation (ICE), and partial dependence plots (PDP) were conducted on the XGB model which highlighted that water-to-binder ratio and sample age are some of the most significant variables to predict the C-S of MK-based cement mortars. Finally, a graphical user interface (GUI) was made for implementation of findings of this study in the civil engineering industry.

关键词： Cement mortar Compressive strength gene expression programming Interpretable machine learning Metakaolin

来源：评论

学校读者我要写书评

暂无评论

A comparison of artificial intelligence models for the estimation of daily suspended sediment load: a case study on the Telar and Kasilian rivers in Iran

引用

WATER SUPPLY 2019年第1期19卷 165-178页

作者： Emamgholizadeh, Samad Demneh, Razieh Karimi Shahrood Univ Technol Dept Soil & Water Shahrood Iran Gorgan Univ Water Engn Gorgan Golestan Iran

The estimation of the suspended sediment load in rivers is one of the main issues in hydraulic engineering. Different traditional methods such as the sediment rating curve (SRC) can be used to estimate the suspended sediment load of rivers. The main problem with this method is its low accuracy and uncertainty. In this study, the ability of three intelligence models namely: gene expression programming (GEP), artificial neural networks (ANN) and adaptive neuro fuzzy inference system (ANFIS) were compared with the SRC method. The daily flow discharge and sediment discharge at two hydrometric stations of the Kasilian and Telar rivers in the period of 1964-2014 were used to develop intelligence models. The performance of these methods indicated that all intelligence models give reliable results in the estimation of the suspended sediment load and their performance was better than the SRC method. Moreover, results showed that the GEP model with a high coefficient of determination (R-2) and a low mean absolute error (MAE) was better than both the ANN and ANFIS models for the estimation of daily suspended sediment load of the two sub-basins of the Kasilian and Telar rivers.

关键词： adaptive neuro inference fuzzy system artificial neural network gene expression programming sediment rating curve suspended sediment load

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：