Índice
Literatura académica sobre el tema "Commande Prédictive Basée sur l’Apprentissage"
Crea una cita precisa en los estilos APA, MLA, Chicago, Harvard y otros
Consulte las listas temáticas de artículos, libros, tesis, actas de conferencias y otras fuentes académicas sobre el tema "Commande Prédictive Basée sur l’Apprentissage".
Junto a cada fuente en la lista de referencias hay un botón "Agregar a la bibliografía". Pulsa este botón, y generaremos automáticamente la referencia bibliográfica para la obra elegida en el estilo de cita que necesites: APA, MLA, Harvard, Vancouver, Chicago, etc.
También puede descargar el texto completo de la publicación académica en formato pdf y leer en línea su resumen siempre que esté disponible en los metadatos.
Tesis sobre el tema "Commande Prédictive Basée sur l’Apprentissage"
Hosseinkhan-Boucher, Rémy. "On Learning-Based Control of Dynamical Systems". Electronic Thesis or Diss., université Paris-Saclay, 2025. http://www.theses.fr/2025UPASG029.
Texto completoEnvironmental needs are driving renewed research interest in fluid flow control to reduce energy consumption and emissions in various applications such as aeronautics and automotive industries. Flow control strategies can optimise the system in real time, taking advantage of sensor measurements and physical models. These strategies aim at manipulating the behaviour of a system to reach a desired state (textit{e.g.}, stability, performance, energy consumption). Meanwhile, the development of data-driven control approaches in concurrent areas such as games and robotics has opened new perspectives for flow control. However, the integration of learning-based control in fluid dynamics comes with multiple challenges, including the robustness of the control strategy, the sample efficiency of the learning algorithm, and the presence of delays of any nature in the system. Thus, this thesis aims to study and develop learning-based control strategies with respect to these challenges where two main classes of data-driven control strategies are considered: Reinforcement Learning (RL) and Learning-based Model Predictive Control (LB-MPC). Multiple contributions are made in this context. First, an extended development on the connection between the fields of (continuous-time) Stochastic Control and (discrete-time) Markov Decision Process is provided to bridge the gap between the two approaches. Second, empirical evidence on the regularisation properties of the Maximum Entropy Reinforcement Learning algorithm is presented through statistical learning concepts to further understand the robustness feature of the Maximum Entropy approach. Third, the notion of temporal abstraction is used to improve the sample efficiency of a Learning-based Model Predictive Control algorithm driven by an Information Theoretic sampling rule. Lastly, neural differential models are introduced through the concept of Neural Delay Differential Equations to model continuous-time systems with delays for Model Predictive Control applications. The different studies are developed with numerical simulations applied on minimalistic systems from Dynamical Systems and Control theories to illustrate the theoretical results. The training experiments of the last part are also conducted on 2D fluid flow simulations
Vachon, Alexandre. "Trajectographie d'un lanceur de satellites basée sur la commande prédictive". Thesis, Université Laval, 2013. http://www.theses.ulaval.ca/2013/29554/29554.pdf.
Texto completoThis thesis deals with the exo-atmospheric trajectory of a space launcher. The solution is obtained by solving a constrained optimization problem : the two-point boundary value problem. The solution is the required actions to reach the desired position and velocity while consuming the least energy as possible. These actions must comply with the constraints imposed by the dynamics and the structure of the vehicle. Also, for a space launcher, the control is limited to the thrust orientation. To solve this problem, this project is divided into three distinct parts : modeling the dynamics, obtaining a reference trajectory and the guidance function. The first part, the modeling, is the definition of an accurate and realistic model of the space launcher translational dynamics. Therefore, it requires the application of Newton's second law on the launcher center of mass. In this thesis, this is carried out using three different representations. The representation using a full quaternion is new to this field of application and fills the hole between the two others. With the model of the vehicle to be guided, it becomes possible to define a reference trajectory governed by this model. To do it, this project proposes a direct optimization where the thrust orientation is discretized and becomes the unknown of the optimization problem. The criterion of this optimization problem includes terms for a priori knowledge of the trajectory improving the convergence properties of the optimization. The optimization problem also includes constraints, relaxed by slack variables, on the injection orbit. The resulting trajectory is used as reference in a trajectory tracking guidance function. The trajectory tracking is a way to circumvent the resolution of the two-point boundary value problem, which accelerates the resolution to fit in on-board computing capabilities. The algorithms developed in this thesis are based on predictive control in which the outputs of predictive model are the instantaneous orbital parameters of the trajectory. A first algorithm uses a non-linear model for prediction while two others are rather based on a linear time-varying representation and a linear fractional representation. These three algorithms are compared to a conventional space launcher guidance solution, which directly solves the two-point boundary value problem. Even if the developped algorithms give a more accurate orbit and a less consuming trajectory, their computationnal time and poor robustness properties do not make them a viable alternative to the comparison solution.
Bouchard, Jocelyn. "Commande prédictive basée sur la simulation. Application à la flottation en colonne". Thesis, Université Laval, 2007. http://www.theses.ulaval.ca/2007/24892/24892.pdf.
Texto completoApplications of dynamic simulators for model predictive controllers design are rather scarce in the litterature. The complexity of solving the resulting optimization problems may explain this lack of popularity. In fact, nonlinear programming algorithms are not always well suited to efficiently reach the optimum of a fundamentaly-based cost function. The situation is even worse when the equations used in the model are unknown by the control designers (black box models). The simulation-based model predictive controller is an alternative formulation to perform model predictive control (MPC) without making use of any explicit optimization solver, but rather based on an easy-to-compute closed-loop simulation. The resulting scheme generally provides a sub-optimal solution and benefits from many interesting features of conventional MPC without being restricted by the model complexity. Two algorithms are proposed: decentralized and decoupled. The decentralized simulation structure allows a flexible setting of the prediction horizon (Hp) that is not possible in the decoupled case, easier to tune, but where Hp must generally be in the same order of magnitude that the system settling time. A second contribution of this thesis is the development of a framework for the dynamic simulation of a mineral separation process: column flotation. Until now, most of the proposed models or simulators were restricted to the steady-state behavior. When dynamic mass-balance equations were considered, a constant pulp level during the simulation was always assumed. The presented framework aims to simulate water, solids and gas motion and their effect on the pulp level and output flow rates. As it often happens in mineral processing, the column flotation process has not benefited from advanced control techniques. This is where the two previous subjects merge. The proposed simulation framework is used to design a simulation-based model predictive controller for process variables having a strong influence on metallurgical results (grade and recovery). A case study is presented where the pulp level, bias and air hold-up in the pulp zone are kept within an acceptable operating region.
Slama, Tahar. "Contribution à la commande prédictive basée sur un modèle pour les systèmes de télé-opération bilatérale". Orléans, 2007. http://www.theses.fr/2007ORLE2059.
Texto completoMouni, Emile Bowendnéré. "Contribution à l'amélioration des performances des génératrices synchrones : nouvelle structure d'excitation basée sur une machine à aimants et combinée à des lois de commande avancées". Poitiers, 2008. http://theses.edel.univ-poitiers.fr/theses/2008/Mouni-Emile-Bowendnere/2008-Mouni-Emile-Bowendnere-These.pdf.
Texto completoThe works presented in this dissertation are focussed on the study and the performances improvement of the synchronous generator. Then, a new excitation structure is proposed to directly feed the SG’s main armature. This exciter is based on a permanent magnet generator and thyristors bridge. In order to take real advantage of the new excitation structure, two modern and efficient control laws have been used: the predictive control and H∞ control. Both provide similar and very satisfactory results in simulation. Thanks to the real time implementation using the Dspace 1104, the effectiveness and the high performances of the new excitation approach have been proved. At the same time, an already used industrial excitation structure has been involved in the comparative study in order to quantify and qualify the real advantage of the new approach. Then, as regards voltage overshoots and drops, the time response and the output signal total harmonic distortion, the new excitation approach combined with modern control law gives better satisfaction than classical one
Qian, Jun. "Identification paramétrique en boucle fermée par une commande optimale basée sur l’analyse d’observabilité". Thesis, Lyon 1, 2015. http://www.theses.fr/2015LYO10113/document.
Texto completoFor online parameter identification, the developed methods here allow to design online and in closed loop optimal inputs that enrich the information in the current experience. These methods are based on real-time measurements of the process, on a dynamic nonlinear (or linear) multi-variable model, on a sensitivity model of measurements with respect to the parameters to be estimated and a nonlinear observer. Analysis of observability and predictive control techniques are used to define the optimal control which is determined online by constrained optimization. Stabilization aspects are also studied (by adding fictitious constraints or by a Lyapunov technique). Finally, for the particular case of a first order linear system, the explicit control law is developed. Illustrative examples are processed via the ODOE4OPE software : a bio-reactor, a continuous stirred tank reactor and a delta wing. These examples help to see that the parameter estimation can be performed with good accuracy in a single and less costly experiment
Benasser, Lakhdar. "Méthodologie de conception des régulateurs de climatisation automobile : une approche systémique basée sur l'analyse de modèles de comportement de la thermorégulation humaine et des échanges thermiques dans un habitacle". Lille 1, 2000. http://www.theses.fr/2000LIL10158.
Texto completoEl, Hadef Jamil. "Approche quasi-systématique du contrôle de la chaîne d'air des moteurs suralimentés, basée sur la commande prédictive non linéaire explicite". Phd thesis, Université d'Orléans, 2014. http://tel.archives-ouvertes.fr/tel-01062186.
Texto completoEl, Hadef Jamil. "Approche quasi-systématique du contrôle de la chaîne d’air des moteurs suralimentés, basée sur la commande prédictive non linéaire explicite". Thesis, Orléans, 2014. http://www.theses.fr/2014ORLE2002/document.
Texto completoThe hundreds of millions of passenger cars and other vehicles on our roads emphasize our society’s reliance on internal combustion engines. Despite striking progress in terms of pollutant emissions and fuel consumption, gasoline and diesel engines remain one of the most important sources of air pollution in modern urban areas. This leads the authorities to lay down increasingly drastic pollutant emission standards, which entail ever more complex engine technical definitions. In particular, due to an increasing number of actuators in the past few years, the air path of internal combustion engines represents one of the biggest challenges of engine control design. The present thesis addresses this issue of increasing engine complexity with respect to the continuous reduction in development time, dictated by a more and more competitive globalized market. The proposal consists in a three-step approach that combines physics-based engine modeling, nonlinear model predictive control and multi-parametric nonlinear programming. The latter leads to an explicit piecewise affine feedback control law, compatible with a real-time implementation. The proposed approach is applied to the particular case of the control of the air path of a turbocharged gasoline engine. Overall, the developments presented in this thesis provide a quasi-systematic approach for the synthesis of the control of the air path of turbocharged gasoline engines. Intuitively, this approach can be extended to other control loops in both gasoline and diesel engines
Mosrati, Rhida. "Nouvelle approche de la cinétique fermentaire de Saccharomyces cerevisiae et de la conduite d'un procédé semi-continu : modélisation de la croissance basée sur le bilan énergétique de la levure, commande prédictive et floue". Vandoeuvre-les-Nancy, INPL, 1993. http://docnum.univ-lorraine.fr/public/INPL_T_1993_MOSRATI_R.pdf.
Texto completo