Résultat de la recherche
3 recherche sur le tag
'neural networks' 




Contribution à la modélisation et à l’optimisation de structures et dispositifs microondes en utilisant divers types de réseaux de neurones. / Chahrazed Erredir
![]()
Titre : Contribution à la modélisation et à l’optimisation de structures et dispositifs microondes en utilisant divers types de réseaux de neurones. Type de document : texte imprimé Auteurs : Chahrazed Erredir, Auteur ; Mohamed Lahdi Riabi, Directeur de thèse Editeur : جامعة الإخوة منتوري قسنطينة Année de publication : 2018 Importance : 91 f. Format : 30 cm. Note générale : 2 copies imprimées disponibles Langues : Français (fre) Catégories : Français - Anglais
ElectroniqueTags : Electronique: Micro-ondes Réseaux de neurones Structures hyperfréquences Modélisation Algorithmes des essaims d'intelligents Neural Networks Microwave Structures Modeling Swarm Intelligence
Algorithms الشبكات العصبٌة هياكل الميكروويف النمذجة خوارزميات الأسراب الذكيةIndex. décimale : 621 Electronique Résumé :
In this work, a new strategy of neural networks (NN) is proposed to modeling microwave waveguide structures (Pseudo-Elliptic filter, Broad-band E-plane filters and Hplane waveguide filters considering rounded corners). In order to enhance the capacities of the NN, we trained NN by the hybrids algorithms based on combining between back propagation (BP) algorithm and swarm intelligence algorithms (Social-Spider optimization SSO, spider monkey optimization SMO and Teaching–Learning-Based Optimization TLBO). To validate the training of neural networks using the proposed algorithms, we compared the results of convergence and modeling obtained with the results obtained using basic algorithms (SSO, SMO and TLBO) and also compared with population based algorithm, which is widely used in training NN namely particle swarm optimization (PSO). The results prove that the proposed hybrids algorithms have given better results.Diplôme : Doctorat en sciences En ligne : ../theses/electronique/ERR7399.pdf Format de la ressource électronique : Permalink : index.php?lvl=notice_display&id=11049 Contribution à la modélisation et à l’optimisation de structures et dispositifs microondes en utilisant divers types de réseaux de neurones. [texte imprimé] / Chahrazed Erredir, Auteur ; Mohamed Lahdi Riabi, Directeur de thèse . - جامعة الإخوة منتوري قسنطينة, 2018 . - 91 f. ; 30 cm.
2 copies imprimées disponibles
Langues : Français (fre)
Catégories : Français - Anglais
ElectroniqueTags : Electronique: Micro-ondes Réseaux de neurones Structures hyperfréquences Modélisation Algorithmes des essaims d'intelligents Neural Networks Microwave Structures Modeling Swarm Intelligence
Algorithms الشبكات العصبٌة هياكل الميكروويف النمذجة خوارزميات الأسراب الذكيةIndex. décimale : 621 Electronique Résumé :
In this work, a new strategy of neural networks (NN) is proposed to modeling microwave waveguide structures (Pseudo-Elliptic filter, Broad-band E-plane filters and Hplane waveguide filters considering rounded corners). In order to enhance the capacities of the NN, we trained NN by the hybrids algorithms based on combining between back propagation (BP) algorithm and swarm intelligence algorithms (Social-Spider optimization SSO, spider monkey optimization SMO and Teaching–Learning-Based Optimization TLBO). To validate the training of neural networks using the proposed algorithms, we compared the results of convergence and modeling obtained with the results obtained using basic algorithms (SSO, SMO and TLBO) and also compared with population based algorithm, which is widely used in training NN namely particle swarm optimization (PSO). The results prove that the proposed hybrids algorithms have given better results.Diplôme : Doctorat en sciences En ligne : ../theses/electronique/ERR7399.pdf Format de la ressource électronique : Permalink : index.php?lvl=notice_display&id=11049 Exemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité ERR/7399 ERR/7399 Thèse Bibliothèque principale Thèses Disponible
Titre : Développement d’un outil de pronostic pour la maintenance des systèmes mécaniques. Type de document : texte imprimé Auteurs : Younes Debbah, Auteur ; Abdelhakim Cherfia, Directeur de thèse Editeur : جامعة الإخوة منتوري قسنطينة Année de publication : 2018 Importance : 134 f. Format : 30 cm. Note générale : 2 copies imprimées disponibles
Langues : Français (fre) Catégories : Français - Anglais
Génie MécaniqueTags : Pronostic diagnostic prédiction intelligence artificielle analyse vibratoire systèmes
experts réseaux de neurones Prognosis diagnosis prediction artificial intelligence vibration analysis expert
systems neural networks التنبؤ التشخيص الذكاء الاصطناعي تحليل الاهتزاز النظم الخبيرة الشبكات العصبيةIndex. décimale : 620 Génie Mécanique Résumé : Maintenance is becoming increasingly important in companies and tends to evolve for reactivity and cost needs. A particular evolution concerns the way to apprehend the phenomena of failure: little by little the industrialists tend, not only to anticipate them by the recourse to preventive actions, but in addition to do it in the most just possible way with a goal reducing costs and risks. This evolution has given a growing share to the prognosis process.
The activity of fault prognosis is today considered as a key process in industrial maintenance strategies. However, in practice, prognostic tools are still rare. Today's stabilized approaches rely on a history of significant incidents to be representative of potentially predictable events The purpose of this thesis is to propose a tool to predict the degradation of equipment without prior knowledge of its behavior, and to generate prognostic indicators to optimize maintenance strategies. Various techniques, of vibratory signal processing, have been explored
and tested, on a test bench designed and realized as part of the research axes of this work. Two techniques of artificial intelligence have been exploited in the diagnosis and prognosis of defects in rotating machines, where indicator selection techniques have been explored.
The combination of vibration signal processing techniques and artificial intelligence by neural networks has made it possible to provide an efficient prognostic tool and to quantify the relevance of the sources of information used and proposed.
Diplôme : Doctorat En ligne : ../theses/gmecanique/DEB7262.pdf Format de la ressource électronique : Permalink : index.php?lvl=notice_display&id=10859 Développement d’un outil de pronostic pour la maintenance des systèmes mécaniques. [texte imprimé] / Younes Debbah, Auteur ; Abdelhakim Cherfia, Directeur de thèse . - جامعة الإخوة منتوري قسنطينة, 2018 . - 134 f. ; 30 cm.
2 copies imprimées disponibles
Langues : Français (fre)
Catégories : Français - Anglais
Génie MécaniqueTags : Pronostic diagnostic prédiction intelligence artificielle analyse vibratoire systèmes
experts réseaux de neurones Prognosis diagnosis prediction artificial intelligence vibration analysis expert
systems neural networks التنبؤ التشخيص الذكاء الاصطناعي تحليل الاهتزاز النظم الخبيرة الشبكات العصبيةIndex. décimale : 620 Génie Mécanique Résumé : Maintenance is becoming increasingly important in companies and tends to evolve for reactivity and cost needs. A particular evolution concerns the way to apprehend the phenomena of failure: little by little the industrialists tend, not only to anticipate them by the recourse to preventive actions, but in addition to do it in the most just possible way with a goal reducing costs and risks. This evolution has given a growing share to the prognosis process.
The activity of fault prognosis is today considered as a key process in industrial maintenance strategies. However, in practice, prognostic tools are still rare. Today's stabilized approaches rely on a history of significant incidents to be representative of potentially predictable events The purpose of this thesis is to propose a tool to predict the degradation of equipment without prior knowledge of its behavior, and to generate prognostic indicators to optimize maintenance strategies. Various techniques, of vibratory signal processing, have been explored
and tested, on a test bench designed and realized as part of the research axes of this work. Two techniques of artificial intelligence have been exploited in the diagnosis and prognosis of defects in rotating machines, where indicator selection techniques have been explored.
The combination of vibration signal processing techniques and artificial intelligence by neural networks has made it possible to provide an efficient prognostic tool and to quantify the relevance of the sources of information used and proposed.
Diplôme : Doctorat En ligne : ../theses/gmecanique/DEB7262.pdf Format de la ressource électronique : Permalink : index.php?lvl=notice_display&id=10859 Exemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité DEB/7262 DEB/7262 Thèse Bibliothèque principale Thèses Disponible Répartition optimale des puissances utilisant les techniques de l’intelligence artificielle / Abdellah Draidi
![]()
Titre : Répartition optimale des puissances utilisant les techniques de l’intelligence artificielle Type de document : texte imprimé Auteurs : Abdellah Draidi, Auteur ; Djamel Labed, Directeur de thèse Editeur : جامعة الإخوة منتوري قسنطينة Année de publication : 2016 Importance : 126 f. Format : 30 cm. Note générale : 2 copies imprimées disponibles
Langues : Français (fre) Catégories : Français - Anglais
Electro-techniqueTags : réseaux électriques écoulement de puissance prévision de la charge réseau de
neurone logique floue ANFIS power systems load flow load forecast neural networks fuzzy logic أنظمة الطاقة تدفق الطاقة توقعات الاستهلاك الشبكات العصبية المنطق الضبابي .AIndex. décimale : 622 Electro-Technique Résumé : Power grids have been developing following the development of computer systems
and control software, today we are interested in smart grids. The introduction of artificial intelligence techniques in the control and the decision is essential in research and development of modern power systems. neural networks and fuzzy logic are among the techniques most used in the field of artificial intelligence. The optimal power flow is an important element for proper optimal and economical delivery of electrical energy between the production units and the various network loads. Load
forecasting has many applications for power systems, including energy purchasing and generation, load switching, contract evaluation, and infrastructure development.
Diplôme : Doctorat en sciences En ligne : ../theses/electrotec/DRA6920.pdf Format de la ressource électronique : Permalink : index.php?lvl=notice_display&id=10272 Répartition optimale des puissances utilisant les techniques de l’intelligence artificielle [texte imprimé] / Abdellah Draidi, Auteur ; Djamel Labed, Directeur de thèse . - جامعة الإخوة منتوري قسنطينة, 2016 . - 126 f. ; 30 cm.
2 copies imprimées disponibles
Langues : Français (fre)
Catégories : Français - Anglais
Electro-techniqueTags : réseaux électriques écoulement de puissance prévision de la charge réseau de
neurone logique floue ANFIS power systems load flow load forecast neural networks fuzzy logic أنظمة الطاقة تدفق الطاقة توقعات الاستهلاك الشبكات العصبية المنطق الضبابي .AIndex. décimale : 622 Electro-Technique Résumé : Power grids have been developing following the development of computer systems
and control software, today we are interested in smart grids. The introduction of artificial intelligence techniques in the control and the decision is essential in research and development of modern power systems. neural networks and fuzzy logic are among the techniques most used in the field of artificial intelligence. The optimal power flow is an important element for proper optimal and economical delivery of electrical energy between the production units and the various network loads. Load
forecasting has many applications for power systems, including energy purchasing and generation, load switching, contract evaluation, and infrastructure development.
Diplôme : Doctorat en sciences En ligne : ../theses/electrotec/DRA6920.pdf Format de la ressource électronique : Permalink : index.php?lvl=notice_display&id=10272 Exemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité DRA/6920 DRA/6920 Thèse Bibliothèque principale Thèses Disponible