作者:
Radi, ChamaAbabou, MariameRabiai, Sara
Fez Business School Private University of Fez Fez Morocco
University Mohammed I Oujda Oujda Morocco
Ibn Zohr University Agadir Morocco
Nowadays, artificial intelligence has become one of the pillars of companies’ business efficiency. To analyze trends in this field, we conducted a bibliometric study of 301 articles published in the Scopus database b...
详细信息
The proceedings contain 102 papers. The special focus in this conference is on Numerical Mathematics and Advanced Applications. The topics include: data-Parallel Neural Network Training via Nonlinearly Preconditi...
ISBN:
(纸本)9783031861680
The proceedings contain 102 papers. The special focus in this conference is on Numerical Mathematics and Advanced Applications. The topics include: data-Parallel Neural Network Training via Nonlinearly Preconditioned Trust-Region Method;numerical Approximation for a Solid Tumor Growth Model;a Priori Error Estimates for a Discretized Multirate Fixed-Stress Split Poro-Elastic System;optimal Design of an Estuarine Water Health Monitoring Network by Means of Optimal control Techniques;Comparison of the Different CFD Coupled DEM Models for Polymer Flooding;A High Order, Finite Volume, Multilevel WENO Scheme Applied to Porous Media;sound Radiation from Double Wall Structure with Poroelastic Layers: Variational Formulation and Finite Element results;goal-Oriented Error Estimates for Adaptive Mixed Finite Element Methods;scale-Space Properties for Discrete Cross-Diffusion Filtering;Optimal Order FEM for Dynamic Poroelasticity: Error analysis for Equal Order Elements;the Lowest-Order Neural Approximated Virtual Element Method;on the Motion of a Heat Conducting Compressible Fluid in Moving Domain with Nonhomogeneous Boundary;modeling the Hallmarks of Avascular Tumors;remark on the Strain Based Hemolysis Models for Viscoelastic Fluids;multipreconditioning with Directional Sweeping Methods for High-Frequency Helmholtz Problems;Numerical Study of Approximation Techniques for the Temporal Weights to the DWR Method;structure-Preserving Approximation for the Non-isothermal Cahn-Hilliard-Navier-Stokes System;Optimal Cost of (Goal-Oriented) Adaptive FEM for General Second-Order Linear Elliptic PDEs;Cost-Optimal Adaptive FEM for Semilinear Elliptic PDEs;numerical analysis of a Simplified Unified Model for Viscoelastic Fluids and Elastic Solids;Mixed Precision FGMRES-Based Iterative Refinement for Weighted Least Squares;Spline-Based Stochastic Collocation Methods for Uncertainty Quantification in Nonlinear Hyperbolic PDEs;weak Enforcement of Boundary Conditions for Maxwell’s Problem Us
This study proposes a dynamic modeling and prediction method for reservoir production based on multi parameter time series and particle swarm optimization algorithm (PSO), aiming to improve the accuracy and timeliness...
详细信息
ISBN:
(数字)9798331536169
ISBN:
(纸本)9798331536176
This study proposes a dynamic modeling and prediction method for reservoir production based on multi parameter time series and particle swarm optimization algorithm (PSO), aiming to improve the accuracy and timeliness of reservoir production prediction. This method integrates multi parameter time series data from the production process of oil reservoirs, such as oil well production, pressure, temperature, etc. It uses Long Short Term Memory (LSTM) neural networks to capture the dynamic changes of oil reservoirs, and combines PSO algorithm to optimize the LSTM model parameters to improve prediction accuracy. A reservoir production prediction model that can be dynamically updated with time is studied and constructed. This model can retrain the LSTM model with newly collected production data and re-optimize the model parameters to adapt to the changes in the reservoir production process. The empirical analysis shows that the prediction accuracy of the model on the test set is high, which can effectively capture the changing trend of reservoir production and provide important reference for oilfield operation. In addition, the model has the ability of real-time training and automatic updating, which ensures the timeliness of prediction. By accurately predicting reservoir production, the model is helpful for oilfield enterprises to arrange production plans reasonably, optimize resource allocation, reduce production costs and improve overall economic benefits.
The proceedings contain 102 papers. The special focus in this conference is on Numerical Mathematics and Advanced Applications. The topics include: data-Parallel Neural Network Training via Nonlinearly Preconditi...
ISBN:
(纸本)9783031861727
The proceedings contain 102 papers. The special focus in this conference is on Numerical Mathematics and Advanced Applications. The topics include: data-Parallel Neural Network Training via Nonlinearly Preconditioned Trust-Region Method;numerical Approximation for a Solid Tumor Growth Model;a Priori Error Estimates for a Discretized Multirate Fixed-Stress Split Poro-Elastic System;optimal Design of an Estuarine Water Health Monitoring Network by Means of Optimal control Techniques;Comparison of the Different CFD Coupled DEM Models for Polymer Flooding;A High Order, Finite Volume, Multilevel WENO Scheme Applied to Porous Media;sound Radiation from Double Wall Structure with Poroelastic Layers: Variational Formulation and Finite Element results;goal-Oriented Error Estimates for Adaptive Mixed Finite Element Methods;scale-Space Properties for Discrete Cross-Diffusion Filtering;Optimal Order FEM for Dynamic Poroelasticity: Error analysis for Equal Order Elements;the Lowest-Order Neural Approximated Virtual Element Method;on the Motion of a Heat Conducting Compressible Fluid in Moving Domain with Nonhomogeneous Boundary;modeling the Hallmarks of Avascular Tumors;remark on the Strain Based Hemolysis Models for Viscoelastic Fluids;multipreconditioning with Directional Sweeping Methods for High-Frequency Helmholtz Problems;Numerical Study of Approximation Techniques for the Temporal Weights to the DWR Method;structure-Preserving Approximation for the Non-isothermal Cahn-Hilliard-Navier-Stokes System;Optimal Cost of (Goal-Oriented) Adaptive FEM for General Second-Order Linear Elliptic PDEs;Cost-Optimal Adaptive FEM for Semilinear Elliptic PDEs;numerical analysis of a Simplified Unified Model for Viscoelastic Fluids and Elastic Solids;Mixed Precision FGMRES-Based Iterative Refinement for Weighted Least Squares;Spline-Based Stochastic Collocation Methods for Uncertainty Quantification in Nonlinear Hyperbolic PDEs;weak Enforcement of Boundary Conditions for Maxwell’s Problem Us
The proceedings contain 62 papers. The special focus in this conference is on Artificial intelligence and Machine Learning. The topics include: Comprehensive analysis of Football Player Performance with WorldfootballR...
ISBN:
(纸本)9783031790850
The proceedings contain 62 papers. The special focus in this conference is on Artificial intelligence and Machine Learning. The topics include: Comprehensive analysis of Football Player Performance with WorldfootballR: data Insights and Key Variables;Decision Making process for a Sustainable Horticulture Using AI;drug Delivery System – The Construction and Use of the Graphical Interface in modeling the controlled Release of Drugs in the Human Body;Enabling German SMEs and Crafts Through data-Driven Innovation: Developing a Scoring Model and Chronological Framework for Enhanced Decision-Makin;Exploring the Impact of AI-Driven Gamification on Visitor Engagement in Museums: A Critical Review;framework for Automating Bank Transactions and Invoice Mapping Using Multi-criteria Optimization and Neural Networks;measurements of Clothing Circumference Using Vision Methods;mechatronic Mannequin as A Way to Reduce the Number of Returns in Fashion E-Commerce;ontological modeling of the Financial Intermediation Models for Creating a System of Texts’ Semantic analysis;optimizing Delivery Routes with Spatially Distributed Orders;review of Artificial Intelligence Models for Constructing a Sales Forecasting Module to Enhance Decision-Making;Stock Price Prediction Using Sentiment analysis and LSTM Networks;unveiling Online Shopping Quality: Taxonomy-Based Multi-label Classification of Shopping App Reviews;unveiling the Dynamics in Shopping Behaviors: A Review;control of Technical Parameters of Industrial Products Through Machine Vision;automatic Coffee Roasting process Assistance System Based on Fuzzy Logic Techniques;a Simulation Study on the Influence of Prioritized Multicast Connections on Traffic Effectiveness Network Nodes;Advantages of Introducing the DVB-T2 Standard in Terrestrial Television;consensus Mechanisms in Blockchain Networks;Self-optimizing SD-WAN.
The proceedings contain 62 papers. The special focus in this conference is on Artificial intelligence and Machine Learning. The topics include: Comprehensive analysis of Football Player Performance with WorldfootballR...
ISBN:
(纸本)9783031774928
The proceedings contain 62 papers. The special focus in this conference is on Artificial intelligence and Machine Learning. The topics include: Comprehensive analysis of Football Player Performance with WorldfootballR: data Insights and Key Variables;Decision Making process for a Sustainable Horticulture Using AI;drug Delivery System – The Construction and Use of the Graphical Interface in modeling the controlled Release of Drugs in the Human Body;Enabling German SMEs and Crafts Through data-Driven Innovation: Developing a Scoring Model and Chronological Framework for Enhanced Decision-Makin;Exploring the Impact of AI-Driven Gamification on Visitor Engagement in Museums: A Critical Review;framework for Automating Bank Transactions and Invoice Mapping Using Multi-criteria Optimization and Neural Networks;measurements of Clothing Circumference Using Vision Methods;mechatronic Mannequin as A Way to Reduce the Number of Returns in Fashion E-Commerce;ontological modeling of the Financial Intermediation Models for Creating a System of Texts’ Semantic analysis;optimizing Delivery Routes with Spatially Distributed Orders;review of Artificial Intelligence Models for Constructing a Sales Forecasting Module to Enhance Decision-Making;Stock Price Prediction Using Sentiment analysis and LSTM Networks;unveiling Online Shopping Quality: Taxonomy-Based Multi-label Classification of Shopping App Reviews;unveiling the Dynamics in Shopping Behaviors: A Review;control of Technical Parameters of Industrial Products Through Machine Vision;automatic Coffee Roasting process Assistance System Based on Fuzzy Logic Techniques;a Simulation Study on the Influence of Prioritized Multicast Connections on Traffic Effectiveness Network Nodes;Advantages of Introducing the DVB-T2 Standard in Terrestrial Television;consensus Mechanisms in Blockchain Networks;Self-optimizing SD-WAN.
The success of completion systems in subsea wells relies on reliability and functionality. Traditional systems face challenges, leading to electrically driven solutions. These include intelligent completion, downhole ...
详细信息
ISBN:
(纸本)9781959025610
The success of completion systems in subsea wells relies on reliability and functionality. Traditional systems face challenges, leading to electrically driven solutions. These include intelligent completion, downhole safety valve, electro-hydraulic downhole wet disconnect system, metallic expandable openhole feedthrough packers, gas lift valves, chemical injection valves, and subsea interface. Electric solutions aim to ensure high availability throughout the well lifecycle. The proposed methodology estimates and monitors reliability metrics during all development stages. It consists of a multilevel system reliability model, Bayesian estimation, uncertainty analysis, optimal testing protocols, and design change recommendations. This standardized approach enhances the R&D process of completion systems with high reliability requirements. The proposed methodology is a systematic procedure that effectively evaluates reliability metrics. It aggregates various types of data, enabling the monitoring of reliability and uncertainty evolution during each stage of R&D. It also calculates accelerated test durations based on the probabilistic physics of failure and stress-life relationships for systems, subsystems, and components. This approach addresses challenges in the development process, including heterogeneous information sources and limited long-term data for new technologies. Compared to current reliability methodologies, which rely on reliability demonstration tests, the proposed methodology enables control and monitoring of the development process. By setting reliability and uncertainty targets, the evolution of these values can be tracked across Technology Readiness Levels (TRLs). This is achieved through a Bayesian approach that updates the reliability function as new evidence emerges. The proposed methodology was on various data types from different completion systems, yielding satisfactory results. This represents a milestone in the development of completion systems
EIS data are typically presented in the form of complex impedance spectra, which require interpretation through equivalent circuit models. Traditional methods for selecting equivalent circuits often rely on manual exp...
详细信息
Overloading of trucks will not only damage road infrastructure, lead to exhaust pollution, and even cause serious traffic accidents, resulting in huge losses of life and property. However, most of the methods to evalu...
详细信息
Learning Management Systems like Moodle generate detailed logs from student interactions, offering significant potential for learning analytics and educational process mining. However, raw logs capture interaction-bas...
详细信息
暂无评论