No description available.

Vehicle acoustic signals have long been considered as unwanted traffic noise. In this research acoustic signals generated by each vehicle will be used to detect its presence and classify its type. Circular arrays of microphones were designed and built to detect desired signals and suppress unwanted ones. Circular arrays with multiple rings have an interesting and important property that is constant sidelobe levels. A modified genetic algorithm that can work directly with real numbers is used in the circular array design. It offers more effective ways to solve numerical problems than a standard genetic algorithm. In classifier design two main paradigms are considered: multilayer perceptrons and adaptive fuzzy logic systems. A multilayer perceptron is a network inspired by biological neural systems. Even though it is far from a biological system, it possesses the capability to solve many interesting problems in variety fields. Fuzzy logic systems, on the other hand, were inspired by human capabilities to deal with fuzzy terms. Its structures and operations are based on fuzzy set theory and its operations. Adaptive fuzzy logic systems are fuzzy logic systems equipped with training algorithms so that its rules can be extracted or modified from available numerical data similar to neural networks. Both fuzzy logic systems and multilayer perceptrons have been proved to be universal function approximators. Since there are approximations in almost every stage, both of these system types are good candidates for classification systems. In classification problems unequal learning of each class is normally encountered. This unequal learning may come from different learning difficulties and/or unequal numbers of training data from each class. The classifier tends to classify better for a well-learned class while doing poorly for other classes. Classification costs that may be different from class to class can be used to train and test a classifier. An error backpropagation algorithm can be modified so that the classification costs along with unequal learning factors can be used to control classifier learning during its training phase. / Ph. D.

Un micro-réseau est un exemple prometteur d’évolution d’architecture de réseau qui consiste à regrouper les différents producteurs et consommateurs autour d'un réseau moyenne tension. Ce système hybride multi-source est donc composé d'au moins une unité de production décentralisée conventionnelle et éventuellement d'une unité de stockage et d’une unité de production basée sur des énergies renouvelables. L’utilisation de cette structure permet de réaliser une minimisation immédiate des pertes liées au transport de l’énergie, une fiabilité accrue de la fourniture et une possibilité de fournir une énergie d’une haute qualité. Dans ce mémoire, nous étudions un micro réseau reposant sur l’utilisation d’une turbine à gaz, d’une centrale photovoltaïque et d’une unité de stockage à base de supercondensateurs. Toutes ces sources sont couplées au micro réseau par des convertisseurs électroniques de puissance et sont interconnectées au gestionnaire central du micro-réseau. Des supervisions locales et une supervision centrale sont utilisées pour ce micro-réseau étudié afin de réaliser une optimisation de son fonctionnement. Par conséquence, la première partie de ce mémoire est consacrée à la formalisation d’une méthode permettant la conception systématique des supervisions locales et des dispositifs de commande des unités de production et de stockage. La seconde partie de cette thèse est consacrée à la gestion proprement dite de l’ensemble de ces moyens de production et de stockage en vue d’optimiser les services fournis aux micro-réseaux. Des résultats de la simulation et de l’expérimentation valident notre conception de la supervision du micro-réseau / A microgrid is a promising future network architecture which is coupling the various generators and consumers in a distribution network. This hybrid multi-source system is composed of at least one conventional generation unit and possibly a storage unit and/or a production unit based on renewable energies. Using this structure allows an immediate minimization of the losses by the energy transport, a greater reliability of power delivery and an ability to provide a high power quality energy. In this paper, we study a microgrid based on the use of a micro gas turbine, a photovoltaic array and supercapacitors. All these sources are coupled to the microgrid by power electronic converters and are interconnected to a microgrid central controller. Some local controllers and the microgrid central controller are used for the studied microgrid to achieve its operation optimization. Therefore, the first part of this thesis is devoted to establish a formalism method for a systematic design of local controllers. The second part of this thesis is devoted to the management of all these production and storage units, in order to optimize the microgrid operating. Simulation and testing results validate our design of the microgrid controllers