| Titre : |
Fuzzy predictive control of the coupled tanks process |
| Type de document : |
document électronique |
| Auteurs : |
Said Guerazem, Auteur ; Tarik Benslimane, Auteur ; Djamel Boukhetala, Directeur de thèse ; Hakim Achour, Directeur de thèse |
| Editeur : |
[S.l.] : [s.n.] |
| Année de publication : |
2024 |
| Importance : |
1 fichier PDF (7 Mo) |
| Présentation : |
ill. |
| Note générale : |
Mode d'accès : accès au texte intégral par intranet.
Mémoire de Projet de Fin d’Études : Automatique : Alger, École Nationale Polytechnique : 2024
Bibliogr. p. 132 - 135 |
| Langues : |
Français (fre) |
| Mots-clés : |
Quadruple
Tank process
Decentralized PI control
Model Predictive Control (MPC)
Recurrent neural networks (RNNs)
Takagi-Sugeno fuzzy models
PDC control
linear matrix inequality (LMI)
Particle Swarm Optimization (PSO) |
| Index. décimale : |
PA00224 |
| Résumé : |
The main objective of this End of Studies project concerns the level control of the coupled tank systems. We begin with a description of the benchmark available in the laboratory of the Control Engineering Department, then we develop an analytical mathematical model of the system in question through which the description of the dynamic characteristics of the system has been carried out. A decentralised PI controller was adopted whilst the adjustment of its parameters has been carried out using a PSO algorithm. This control technique was taken as a reference for comparison with the techniques that we developed subsequently. Firstly, we develop two control techniques , linear and non-linear model predictive control (MPC) techniques. Additionally, we propose another approach based on recurrent neural networks (RNN) to predict the control inputs and reduce the computation time compared with conventional methods. Finally, we used Takagi-Sugeno type fuzzy systems to describe the non-linear model for multi-model control with stability analysis and trajectory tracking. Robustness tests have been carried out to evaluate the performance of each method |
Fuzzy predictive control of the coupled tanks process [document électronique] / Said Guerazem, Auteur ; Tarik Benslimane, Auteur ; Djamel Boukhetala, Directeur de thèse ; Hakim Achour, Directeur de thèse . - [S.l.] : [s.n.], 2024 . - 1 fichier PDF (7 Mo) : ill. Mode d'accès : accès au texte intégral par intranet.
Mémoire de Projet de Fin d’Études : Automatique : Alger, École Nationale Polytechnique : 2024
Bibliogr. p. 132 - 135 Langues : Français ( fre)
| Mots-clés : |
Quadruple
Tank process
Decentralized PI control
Model Predictive Control (MPC)
Recurrent neural networks (RNNs)
Takagi-Sugeno fuzzy models
PDC control
linear matrix inequality (LMI)
Particle Swarm Optimization (PSO) |
| Index. décimale : |
PA00224 |
| Résumé : |
The main objective of this End of Studies project concerns the level control of the coupled tank systems. We begin with a description of the benchmark available in the laboratory of the Control Engineering Department, then we develop an analytical mathematical model of the system in question through which the description of the dynamic characteristics of the system has been carried out. A decentralised PI controller was adopted whilst the adjustment of its parameters has been carried out using a PSO algorithm. This control technique was taken as a reference for comparison with the techniques that we developed subsequently. Firstly, we develop two control techniques , linear and non-linear model predictive control (MPC) techniques. Additionally, we propose another approach based on recurrent neural networks (RNN) to predict the control inputs and reduce the computation time compared with conventional methods. Finally, we used Takagi-Sugeno type fuzzy systems to describe the non-linear model for multi-model control with stability analysis and trajectory tracking. Robustness tests have been carried out to evaluate the performance of each method |
|
Ajouter le résultat dans votre panier
Visionner les documents numériques
Faire une suggestion Affiner la rechercheFuzzy predictive control of the coupled tanks process (2024)
