检索结果-内蒙古大学图书馆

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

Machine learning-based prediction of CO 2 solubility in methyldiethanolamine solutions: A comparative study

Results in Engineering

引用

Results in Engineering 2025年 26卷

作者： Sajjad Fazeli Mohammad Amin Moradkhani Behrouz Bayati Chemical Engineering Department Ilam University P.O. Box 69315/516 Iran

Methyldiethanolamine (MDEA) is a widely used solvent in carbon capture processes owing to its high absorption capacity. However, there is a lack of comprehensive predictive tools for estimating CO 2 solubility in MDEA-based solution. To fulfil this research gap, in the current study, 2969 experimental data pertinent to the CO 2 dissolution in MDEA solutions blended with various co-solvent, including water, amines, ionic liquids, electrolytes, etc., have been collected from the literature. The foregoing databank envelop a widespread range of pressures and temperatures. In order to construct robust models, three heuristic soft computing methods, including radial basis function neural network (RBF-NN), gaussian process regression (GPR) and multilayer perceptron neural network (MLP-NN) were employed. Despite the satisfactory performance of all intelligent models, the one designed based on the GPR method gave the superior accuracy with average absolute relative error (AARE) and R 2 values of 4.94 % and 97.5 %, respectively, for the testing dataset. Moreover, it estimated more than 91 % of the analyzed samples within ± 15 error margin. A statistical investigation through the William’s plot implied the fact that both the collected databank and the suggested predictive tools benefit from high credibility. The novel models also favorably described the absorption capacity of diverse MDEA-based solutions under a wide range of operating conditions. Finally, the order of significance of influential factors in controlling solubility was determined based on a sensitivity analysis.

关键词： CO 2 capture Methyldiethanolamine (MDEA) Machine learning algorithm Solubility Prediction AARE average absolute relative error AMP aminomethyl propanol BP backpropagation DEA diethanolamine MDEA methyldiethanolamine MEA monoethanolamine GPR Gaussian process regression MLP-NN multilayer perceptron neural network RBF-NN radial basis function neural network

来源：评论

学校读者我要写书评

暂无评论

Standard error of the genetic correlation: how much data do we need to estimate a purebred-crossbred genetic correlation?

引用

GENETICS SELECTION EVOLUTION 2014年第1期46卷 1-6页

作者： Bijma, Piter Bastiaansen, John W. M. Wageningen Univ Anim Breeding & Genom Ctr NL-6700 AH Wageningen Netherlands

Background: The additive genetic correlation (r(g)) is a key parameter in livestock genetic improvement. The standard error (SE) of an estimate of r(g), (r) over cap (g), depends on whether both traits are recorded on the same individual or on distinct individuals. The genetic correlation between traits recorded on distinct individuals is relevant as a measure of, e. g., genotype-by-environment interaction and for traits expressed in purebreds vs. crossbreds. In crossbreeding schemes, r(g) between the purebred and crossbred trait is the key parameter that determines the need for crossbred information. This work presents a simple equation to predict the SE of (r) over cap (g) between traits recorded on distinct individuals for nested full-half sib schemes with common-litter effects, using the purebred-crossbred genetic correlation as an example. The resulting expression allows a priori optimization of designs that aim at estimating rg. An R-script that implements the expression is included. Results: The SE of (r) over cap (g) is determined by the true value of r(g), the number of sire families (N), and the reliabilities of sire estimated breeding values (EBV): [GRAPHICS] where rho(2)(x) and rho(2)(y) are the reliabilities of the sire EBV for both traits. Results from stochastic simulation show that this equation is accurate since the average absolute error of the prediction across 320 alternative breeding schemes was 3.2%. Application to typical crossbreeding schemes shows that a large number of sire families is required, usually more than 100. Since SE ((r) over cap (g)) is a function of reliabilities of EBV, the result probably extends to other cases such as repeated records, but this was not validated by simulation. Conclusions: This work provides an accurate tool to determine a priori the amount of data required to estimate a genetic correlation between traits measured on distinct individuals, such as the purebred-crossbred genetic correlation.

关键词： Genetic Correlation Estimate Breeding Value Distinct Individual absolute relative error average absolute relative error

来源：评论

学校读者我要写书评

暂无评论

Prediction and analysis of near-road concentrations using a reduced-form emission/dispersion model

引用

ENVIRONMENTAL HEALTH 2010年第2010期9卷 29-29页

作者： Batterman, Stuart A. Zhang, Kai Kononowech, Robert Univ Michigan Dept Environm Hlth Sci Ann Arbor MI 48109 USA

Background: Near-road exposures of traffic-related air pollutants have been receiving increased attention due to evidence linking emissions from high-traffic roadways to adverse health outcomes. To date, most epidemiological and risk analyses have utilized simple but crude exposure indicators, most typically proximity measures, such as the distance between freeways and residences, to represent air quality impacts from traffic. This paper derives and analyzes a simplified microscale simulation model designed to predict short- (hourly) to long-term (annual average) pollutant concentrations near roads. Sensitivity analyses and case studies are used to highlight issues in predicting near-road exposures. Methods: Process-based simulation models using a computationally efficient reduced-form response surface structure and a minimum number of inputs integrate the major determinants of air pollution exposures: traffic volume and vehicle emissions, meteorology, and receptor location. We identify the most influential variables and then derive a set of multiplicative submodels that match predictions from "parent" models MOBILE6.2 and CALINE4. The assembled model is applied to two case studies in the Detroit, Michigan area. The first predicts carbon monoxide (CO) concentrations at a monitoring site near a freeway. The second predicts CO and PM(2.5) concentrations in a dense receptor grid over a 1 km(2) area around the intersection of two major roads. We analyze the spatial and temporal patterns of pollutant concentration predictions. Results: Predicted CO concentrations showed reasonable agreement with annual average and 24-hour measurements, e. g., 59% of the 24-hr predictions were within a factor of two of observations in the warmer months when CO emissions are more consistent. The highest concentrations of both CO and PM(2.5) were predicted to occur near intersections and downwind of major roads during periods of unfavorable meteorology (e. g., low wind speeds) and high emis

关键词： Geographical Information System Traffic Volume Road Segment Downwind Distance average absolute relative error

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：