génie Mécanique

URI permanent de cette collectionhttps://dspacee.univ-temouchent.edu.dz/handle/123456789/765

Parcourir par

Voici les éléments 1 - 20 sur 216

Réalisation d’une presse pour la récupération plastique
(2026) MEKHISSI Abdelkader; BENARBIA Kheireddine; Elahmar Kadi
Prévision de la demande électrique journalière d'une maison à l'aide de modèles de séries temporelles et de Machine Learning
(2026) REBHI Rim Chames El Houda; BELABANE Hayet Kaouter Zahra; DORBANE Abdelhakim
This Master's end-of-study project focuses on forecasting residential electricity consumption using Machine Learning techniques. The primary objective is to develop predictive models capable of accurately estimating electricity demand based on historical consumption data and relevant explanatory variables. Following a comprehensive literature review, four prediction models—Linear Regression, Random Forest, XGBoost, and CatBoost—were developed, implemented, and comparatively evaluated. The performance of these models was assessed using Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Percentage Error (MAPE), and the coefficient of determination (R2). The experimental results demonstrate the effectiveness of machine learning techniques in improving forecasting accuracy. The best-performing model achieved an MSE of **0.408103**, an RMSE of **0.638829**, an MAE of **0.480083**, and an **R2 score of 0.986685**, indicating excellent predictive performance. These findings highlight the potential of machine learning to support efficient energy management, accurate electricity demand forecasting, and improved electrical grid operation.
Modélisation en 3D et analyse des écoulements internes dans le compresseur axial Nasa Stage 37 Via ANSYS CFX
(2026) AGUILI MOHAMED; GUETTACHE MOUADE HOUSSEM; HARCHOUCHE Zine el abidine
This study focuses on the modeling, simulation, and analysis of the aerodynamic behavior of a NASA Stage 37 transonic axial compressor using computational fluid dynamics (CFD) with the ANSYS Fluent software. This compressor is a widely used reference case in the field of turbomachinery for studying compressible flows and high-speed transonic phenomena. A three- dimensional numerical model was developed to solve the conservation equations for mass, momentum, and energy. The simulation incorporates appropriate physical models, including turbulence models, rotational effects, and rotor-stator interactions. Boundary conditions were defined to reproduce the actual operating conditions of the compressor. The main objective of this study is to evaluate the aerodynamic performance of the NASA Stage 37 through the analysis of key parameters such as the compression ratio, isentropic efficiency, pressure distribution, velocity fields, and internal aerodynamic losses. The results obtained also allow the study of complex phenomena present in transonic compressors, such as shock waves, flow separations, and recirculation zones. Finally, this numerical approach offers a better understanding of the compressor's hydrodynamic behavior and provides an important basis for optimizing performance and improving the design of modern turbomachinery.
Étude expérimentale et numérique de la réparation des polymères fissurés par friction malaxage
(2026) SI ABDELKADER Abdelkader; BENCHOHRA Fatima Zahra; SERIER Mohamed
This work falls within the scope of repairing polymer structures damaged by cracking, proposing Friction Stir Welding (FSW) as an innovative alternative to conventional fusion welding processes. Following a literature review dedicated to the properties of High-Density Polyethylene (HDPE), the cracking mechanisms of semi-crystalline polymers, and the limitations of classic welding techniques, the study utilizes the Response Surface Methodology (RSM) / Design of Experiments (DoE) to quantify the influence of the FSW operating parameters—rotational speed, traverse speed, and tool tilt angle—on the maximum temperature developed within the weld zone. A full factorial design was employed to establish a predictive regression model, complemented by an artificial intelligence approach based on an Artificial Neural Network (ANN) to refine the thermal response modeling. The obtained results confirm that the process takes place entirely in a steady visco-plastic state, below the crystalline melting point of HDPE, and highlight the predominant role of the rotational speed and its interaction with the tilt angle. The identified operating conditions open promising perspectives for the industrial application of FSW in repairing thermoplastic polymer components, while emphasizing the need for additional testing to consolidate the statistical robustness of the proposed model.
Analyse numérique par la méthode des éléments finis (Abaqus) de la concentration des contraintes et du facteur d'intensité des contraintes au niveau des fissures dans les jonctions soudées des pipelines
(2026) AID DJIHENE; ALLIAOUI MEROUA; Bouafia Farida
This thesis focuses on the analysis of the mechanical behavior of pipelines, with particular emphasis on welded joints and their sensitivity to defects such as cracks. The main objective is to study the mechanisms of stress concentration and the fracture conditions in these critical zones, using an approach based on fracture mechanics and finite element numerical simulation (Abaqus).
Simulation du comportement d’une structure soumise à différente type de défaut (fissure/entaille)
(2026) BENSIYAKOUB Azeddine; SOUIDI Kheïreddine; BOUZITOUNA Wahiba Nesrine
Fracture mechanics is a fundamental discipline in mechanical engineering that focuses on the behavior of materials containing defects or discontinuities. Its primary objective is to understand the mechanisms of crack initiation and propagation in order to prevent sudden structural failures and enhance the reliability of engineering components during service. This work first presents the theoretical foundations of fracture mechanics, including the different fracture modes, the Stress Intensity Factor (K), and the development of the plastic zone near the crack tip. It also reviews the main analytical approaches used for notch assessment, such as Pluvinage’s volumetric approach, the equivalent crack concept, and the Creager–Paris formulation. The study then examines the nature and classification of structural defects, including cracks, notches, and corrosion damage, while discussing the maintenance and repair techniques commonly employed in industry. Particular attention is given to bonded composite patch repair, a widely adopted solution in the aerospace sector for restoring structural integrity and extending service life. Finally, a three-dimensional numerical investigation is carried out using the Abaqus software package to evaluate the effectiveness of a Boron/Epoxy composite patch in reinforcing an aluminum plate containing either a crack or a notch. The study also addresses the simulation of crack growth and fracture path propagation using the eXtended Finite Element Method (XFEM), providing a deeper understanding of the behavior and damage tolerance of repaired structures.
Simulation de l’écoulement du fluide dans un compresseur alternatif
(2026) Bensaad Mohamed Mehdi; Belghorzi Djawed; Guendouz Bouhelal
The enhancement of energy efficiency in gas compression systems constitutes a major industrial challenge, particularly in the refrigeration and energy storage sectors. The present master's thesis is devoted to the study of the performance of a positive displacement piston compressor. A 0D thermodynamic model, incorporating the principal sources of internal losses – namely thermal, fluidic and mechanical losses – and coupled with a parametric sensitivity analysis, was developed for this purpose. The obtained results reveal significant trends, most notably the predominant influence of the connecting rod length on both the maximum in-cylinder pressure and the volumetric efficiency. Moreover, the compression work per cycle, evaluated across the various simulated configurations, proves to be a relevant indicator of the machine's overall energy efficiency. This work contributes to a deeper understanding of the multiphysics couplings occurring in piston compressors and provides an accessible predictive tool to support design decisions. The perspectives arising from this study include experimental validation and the extension of the model to other compressor architectures.
Analyse énergétique et modélisation du comportement en fatigue du PEHD sous sollicitations cycliques
(2026) DJEBBOUR MOHAMED ABDELHADI; HICHOUR ABDERRHMANE; OUARI MOHAMED AMINE
The recent development of the global plastics industry, particularly polymer materials, has motivated this study focused on the energetic aspect of the behavior of High-Density Polyethylene (HDPE). The objective is to analyze the combined influence of testing conditions and stress amplitude on the evolution of dissipated energy and fatigue life expressed in the number of cycles, in order to optimize these parameters, reduce energy losses, and increase testing efficiency. The testing frequency and the applied stress amplitude were defined as input variables, while the number of cycles and dissipated energy were considered output variables. Loading– unloading loops were analyzed to extract the dissipated energy values associated with each experimental condition. Based on the datasets obtained for different amplitudes, mathematical models were developed to simultaneously estimate dissipated energy and the corresponding number of cycles. The results show that stress amplitude has the most significant effect on the cyclic behavior of HDPE, followed by testing frequency. The study of interactions between these factors made it possible to identify optimal combinations leading to a target number of cycles, thus providing opportunities to improve fatigue resistance and optimize testing protocols. These findings pave the way for practical recommendations regarding the design, sizing, and maintenance of HDPE structures.
Analyse tridimensionnelle d'un capteur solaire plan muni d'ailettes décalées
(2026) ZENASNI Malek; BENZENINE Hamidou
In this work, we numerically investigated the thermal and dynamic behavior of forced convection airflow inside a flat plate solar collector equipped with staggered rectangular fins. The continuity, momentum and energy equations are solved using the ANSYS Fluent code, based on the finite volume method. The k-ε turbulence model is used to simulate turbulence. This study examines the influence of fin number (0, 3 and 6 fins) and fin height (0.02 m, 0.05 m and 0.08 m) on the thermo-hydraulic performance of the collector, for different mass flow rates (0.02 to 0.06 kg/s). Performance is evaluated using the thermo-hydraulic criterion, which simultaneously accounts for heat transfer enhancement and pressure drop penalty."
Simulation-RANS des écoulements turbulent sans et avec combustion dans une tuyère supersonique
(2026) DJEROUAT Anes Mohammed Ryad; BOUNIF . A
This work focuses on the numerical simulation (CFD) using the RANS approach of turbulent supersonic flows within a turbojet nozzle. The study consists of modeling fluid behavior and shock wave dynamics by evaluating the influence of several physical and operational parameters. The methodology integrates a numerical model validation phase, a comparative analysis of turbulence models, and an investigation of steady versus unsteady regimes. In addition, a parametric analysis is conducted to characterize the impact of inlet pressure and temperature variations on the flow. Finally, the work includes the modeling and thermochemical analysis of a reactive hydrogen-air flow within the divergent section.
Optimisation thermique d'un mur composite par l’intégration d'un PCM pour l'amélioration du confort thermique des bâtiments.
(2026) ZENASNI Feriel; ZERGA Ramyz Ahmed; NEHARI Taieb
This thesis focuses on the thermal optimization of a composite wall incorporating a phase change material (PCM) in order to improve thermal comfort in buildings and reduce energy consumption. PCMs can store and release heat in the form of latent heat during solid/liquid phase transition, which helps limit indoor temperature fluctuations. The study is based on a numerical simulation carried out using ANSYS Fluent and the enthalpy-porosity method to model heat transfer and phase change phenomena. Several parameters were analyzed, including the type of PCM, its thickness, and its combination with passive insulation techniques. The results show that integrating PCMs improves the thermal inertia of walls, reduces heat flux, and enhances indoor thermal comfort while decreasing heating and cooling energy demands.
Reburning /C2H2 dans une flamme turbulente / réduction des émissions des NOx dans les installations industrielles
(2026) SIDI ALI CHERIF Dia Eddine; AOURAGH Mouna; NEHARI Taieb
This article presents the computational fluid dynamics (CFD) simulation of NOx reduction using the reburning technique of a NO/C2H2/O2 mixture at atmospheric pressure. Velocity fields, temperature profiles, and species distributions were studied numerically. Mathematical combustion models, namely the Finite Rate/Eddy Dissipation (FR-ED) model coupled with a detailed kinetic mechanism, were used in the numerical analysis, considering a complete combustion kinetic model. Furthermore, a series of CFD results incorporating the FR-ED model were obtained through two-dimensional simulations. An analysis has shown that 2D simulation with the FR-ED model accurately predicts the dynamic field, temperature profile, and species distribution of the combustion process, and allows for a detailed study of the flame structure during reburning, taking into account the various operating parameters. The CFD results are consistent with previously obtained experimental data.
Approche XFEM-CZM couplée à USDFLD pour la prédiction de l’endommagement dans les structures renforcées par composite gradués
(2026) Bousaadi Alla; Chenafa Hayet; CHAMA Mourad; HADJADJ M
A bi-graded composite patch is analyzed in this study. The aim of this bi-gradation concept is to enhance the reinforcement of a notched aluminum plate by tailoring the stiffness distribution through gradation parameters. The approach involves grading three different types of fibers, all with the same volume fraction and within the same epoxy matrix. The patch debonding, caused by adhesive failure, as well as the crack initiation and propagation in the plate, are simulated respectively using the Cohesive Zone Model (CZM) and the Extended Finite Element Method (XFEM), both implemented in the ABAQUSVR finite element code. The CZM model accounts for both shear and normal separation modes in the adhesive layer. Using FGM-based functions, the bi-gradation of the composite patch is defined along the thickness at the fiber scale, with each layer formulated through a power-law volume fraction between the fibers and the matrix. Three concepts are proposed and analyzed. In Concept C-1, the central region of the patch consists of CFRP-1 fibers, which are graded toward Glass- Epoxy and CFRP-2 fibers at the outer surfaces. Concept C-2 features CFRP-2 fibers in the center, graded toward CFRP-1 and Glass-Epoxy at the extremities, with Glass-Epoxy located at the adhesive interface. In Concept C-3, the core is made of Glass-Epoxy fibers, graded toward CFRP-1 and CFRP-2 at the outer surfaces, with CFRP-2 placed at the adhesive interface. These various gradation configurations aim to improve the patch’s ability to absorb loads transferred through the adhesive joint and to investigate how the gradation influences damage mechanisms, particularly debonding. The analysis, conducted under various loading conditions, demonstrates a competitive interaction between adhesive debonding and crack initiation in the notched plate, confirming the effectiveness of the proposed bi-graded composite patch designs.
Prévision de la demande électrique journalière d'une maison à l'aide de modèles de séries temporelles et de Machine Learning
(2026) REBHI Rim Chames El Houda; BELABANE Hayet Kaouter Zahra; DORBANE Abdelhakim
This Master's end-of-study project focuses on forecasting residential electricity consumption using Machine Learning techniques. The primary objective is to develop predictive models capable of accurately estimating electricity demand based on historical consumption data and relevant explanatory variables. Following a comprehensive literature review, four prediction models—Linear Regression, Random Forest, XGBoost, and CatBoost—were developed, implemented, and comparatively evaluated. The performance of these models was assessed using Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Percentage Error (MAPE), and the coefficient of determination (R2). The experimental results demonstrate the effectiveness of machine learning techniques in improving forecasting accuracy. The best-performing model achieved an MSE of **0.408103**, an RMSE of **0.638829**, an MAE of **0.480083**, and an **R2 score of 0.986685**, indicating excellent predictive performance. These findings highlight the potential of machine learning to support efficient energy management, accurate electricity demand forecasting, and improved electrical grid operation.
Finite Element Analysis of Crack and Scratch Defect Interaction in a Buried API X80 Pipeline
(2026) LAMRI SIDAHMED EL MAHDI; OUDAD WAHID
The structural integrity of oil and gas pipelines is strongly influenced by the presence of defects that may develop during manufacturing, installation, or service. Among these defects, cracks and scratches are considered critical because they create stress concentrations that can reduce the load-carrying capacity of the pipeline and increase the risk of failure. Understanding the interaction between such defects is therefore essential for ensuring safe and reliable pipeline operation. This work investigates the interaction between crack and scratch defects in a buried API 5L X80 steel pipeline using the Finite Element Method (FEM). Numerical simulations were performed with ABAQUS to analyze the influence of defect geometry, including crack depth, crack width, scratch depth, scratch width, and scratch orientation. The distributions of Von Mises stress, equivalent plastic strain (PEEQ), and J-integral were evaluated to characterize the mechanical and fracture behavior of the pipeline. The results show that increasing defect dimensions leads to higher stress concentration and plastic deformation levels. Furthermore, the J-integral values increase with crack size, indicating a greater tendency for crack propagation. The study also highlights the influence of repair configurations on reducing the crack driving force and improving structural integrity. The findings contribute to a better understanding of defect interaction mechanisms in high-strength pipeline steels and provide useful information for pipeline integrity assessment and maintenance strategies.
Simulation de la propagation de fissures Dans les structures sous chargement cyclique
(2026) MECELLEM MOHAMED ABDELLAH; ELRARBI SARA; CHAMA Mourad
Les bimatériaux sont largement utilisés dans différences branches de la technologie comme la mécanique, l’électronique et l’électrotechnique parce qu’ils sont constitués de deux matériaux dont les propriétés physiques et mécaniques sont totalement différentes. Le comportement en ruptures des matériaux hétérogènes nécessite des connaissances approfondies et le domaine de recherche reste complexe et ouvert. Le travail ainsi présenté a pour objectif d’analyser numériquement par la méthode éléments finis la propagation d’une fissure initiée dans la céramique et au voisinage proche de l'interface sous l’effet d’un chargement cyclique. L'étude porte sur l'analyse d’un modèle géométrique bidimensionnel, est une poutre en flexion, elle est composée de deux matériaux, alumine contient de teneur d’époxy avec et sans gradient au voisinage proche de l’interface. Une étude comparative a été faite en comportements élastiques. Plusieurs facteurs ont été mis en évidence tels que la résistance de la fatigue de la fissure et sa déviation dans la céramique. Abstract Bimaterials are widely used in various branches of technology, such as mechanics, electronics, and electrical engineering, because they are composed of two materials with completely different physical and mechanical properties. The fracture behavior of heterogeneous materials requires in-depth knowledge, and the research field remains complex and open. The work presented here aims to numerically analyze, using the finite element method, the propagation of a crack initiated in the ceramic and in the immediate vicinity of the interface under the effect of cyclic loading. The study focuses on the analysis of a two-dimensional geometric model, a beam in bending, composed of two materials: alumina containing epoxy with and without a gradient in the immediate vicinity of the interface. A comparative study was conducted on elastic behavior. Several factors were highlighted, such as the fatigue resistance of the crack and its deflection in the ceramic..
Techno-Economic Studty of Pumped Thermal Energy Storage
(2026) Mohamad El-Osman; Remlaoui Ahmed
As renewable energy continues to play an increasingly important role in modern power systems, the need for energy storage technologies capable of delivering large amounts of energy over extended periods is becoming more critical. Pumped Thermal Energy Storage (PTES) has emerged as a promising solution that stores electrical energy in the form of thermal energy and converts it back into electricity when required. This study focuses on the techno-economic assessment of a Brayton-cycle PTES system under the climatic conditions of Ain TEMOUCHENT, Algeria. The study employed the System Advisor Model (SAM) to simulate and evaluate the technical and economic performance of the proposed system. The simulation results were used to assess the thermodynamic performance, energy storage capacity, thermal losses, and overall economic feasibility of the PTES system. In addition, a parametric analysis was conducted to investigate the effects of storage duration and hot storage temperature on system performance. The results demonstrate that PTES is a promising technology for long-duration energy storage and offers significant technical and economic benefits for the integration of renewable energy into modern power systems.
Analyse tridimensionnelle de l'écoulement dans un échangeur bitube en présence d'un nanofluide hybride
(2026) MADANI Mohamed Abd El Ghafour; LOURMIL Souheyla; BENZENINE Hamidou
This work presents a thermal and numerical study of a double-tube heat exchanger equipped with longitudinal fins mounted on the outer surface of the inner tube using ANSYS Fluent software. The main objective of this study is to analyze the influence of flow rate, hybrid nanofluid type, and nanoparticle volume concentration on the thermal performance of the heat exchanger. The longitudinal fins were used to increase the heat exchange surface area and enhance heat transfer efficiency. After creating the geometry, mesh, and boundary conditions, several numerical simulations were carried out to evaluate the thermal behavior of the fluids and the evolution of outlet temperatures. The obtained results show that the variation of flow rate, hybrid nanofluid type, and concentration directly affects heat transfer efficiency and outlet temperatures. This study highlights the importance of numerical simulation in the analysis and optimization of heat exchangers.
Influence de la forme du pliage sur la résistance des tôles
(2026) BENMENDIL Rizlane Meriem; BENMECHTA Mama Imene; El AHMAR kadi
This research focuses on the impact of bend geometry on the mechanical properties of sheet metal used in industrial structures. The study compares three main configurations: plain sheet metal, U-bent sheet metal, and V-bent sheet metal. Through numerical simulations performed using Abaqus and by imposing realistic boundary conditions, the results show that bent shapes significantly improve stiffness and reduce deformation compared to flat sheets. This study highlights that optimizing the bend shape is an effective solution for strengthening sheet metal, improving its stability, and meeting the industry's increasing demands for reliability and performance.
Short-Term Prediction of the Photovoltaic Production of a Solar Farm Using Artificial Intelligence and Machine Learning
(2026) GHALEM Mohammed; HADDOU Zakarya Mohammed Nadir; DORBANE Abdelhakim
This thesis presents a short-term prediction study of the photovoltaic power production of a solar farm using Artificial Intelligence and Machine Learning techniques. Given Algeria's exceptional solar potential and the growing integration of photovoltaic systems into the national grid, accurate forecasting of PV output has become essential for grid stability and energy management. The study employs a data-driven regression approach using meteorological and operational data, including solar irradiance, ambient temperature, relative humidity, wind speed, wind direction, and sea-level pressure, as input features to predict the target variable Power_PACE. Five Machine Learning models were developed and compared: Linear Regression, Random Forest, Gradient Boosting, XGBoost, and CatBoost. After preprocessing and feature engineering in Python, each model was trained on historical data and evaluated on a held-out test set using MAE, RMSE, and R2 metrics. Results show that Linear Regression achieved the highest coefficient of determination (R2 = 0.9777) with the lowest RMSE (5,953 W), reflecting the dominant linear relationship between solar irradiance and power output in the summer dataset. Random Forest ranked second with the lowest MAE (4,232 W), demonstrating strong robustness and interpretability. SHAP analysis confirmed Solar_Mean as the primary predictor, followed by ambient temperature and hour of day. The findings demonstrate that even classical Machine Learning models can achieve high forecasting accuracy when solar irradiance is the dominant driver, while ensemble methods such as Random Forest offer a more reliable choice for real-world deployment due to their robustness to noisy data and nonlinear behavior.

Parcourir par

Dépôts récents