No description available.

<p>In the process of designing an electric power supply system for an aircraft, parameters like low weight and low losses are important. Reliability, robustness and low cost are other important factors. In the Saab Gripen aircraft, the design of the primary power supply of the electric flight control system was updated by exchanging a switching transistor regulator to a magnetic amplifier (magamp). By introducing a magamp design, weight was saved and a more reliable power supply system at a lower cost was achieved.</p><p> In this particular case, with the power supply of the electric flight control system in the Saab Gripen fighter, advantage could be taken of a specific permanent magnet generator (PM-generator). The frequency of the generator offered the perfect conditions for a magamp controller. A key parameter in designing magnetic amplifiers (magamps) is low losses. New amorphous alloys offer new possibilities of the technique in designing magnetic amplifiers, because of their extremely low losses.</p><p> The core losses are evaluated by studying the equations and diagrams specifying the power losses. The core losses are evaluated and compared with the copper losses in the process of optimizing low weight and low losses. For this an engineering tool is developed and demonstrated.</p><p> Evaluations of the hysteresis characteristics for the magnetic alloys, as well as modeling and simulation of the core losses, are presented in this work. The modeling of the core losses includes hysteresis losses, eddy current losses and excess losses as well as copper losses. The losses are studied dynamically during realistic operational conditions. The model can be used for any generic analysis of hysteresis in magnetic circuits. Applications of magnetic amplifiers in aircrafts have been demonstrated to be a feasible alternative</p>

Dans un problème de prédiction à multiples pas discrets, la prédiction à chaque instant peut dépendre de l’entrée à n’importe quel moment dans un passé lointain. Modéliser une telle dépendance à long terme est un des problèmes fondamentaux en apprentissage automatique. En théorie, les Réseaux de Neurones Récurrents (RNN) peuvent modéliser toute dépendance à long terme. En pratique, puisque la magnitude des gradients peut croître ou décroître exponentiellement avec la durée de la séquence, les RNNs ne peuvent modéliser que les dépendances à court terme. Cette thèse explore ce problème dans les réseaux de neurones récurrents et propose de nouvelles solutions pour celui-ci. Le chapitre 3 explore l’idée d’utiliser une mémoire externe pour stocker les états cachés d’un réseau à Mémoire Long et Court Terme (LSTM). En rendant l’opération d’écriture et de lecture de la mémoire externe discrète, l’architecture proposée réduit le taux de décroissance des gradients dans un LSTM. Ces opérations discrètes permettent également au réseau de créer des connexions dynamiques sur de longs intervalles de temps. Le chapitre 4 tente de caractériser cette décroissance des gradients dans un réseau de neurones récurrent et propose une nouvelle architecture récurrente qui, grâce à sa conception, réduit ce problème. L’Unité Récurrente Non-saturante (NRUs) proposée n’a pas de fonction d’activation saturante et utilise la mise à jour additive de cellules au lieu de la mise à jour multiplicative. Le chapitre 5 discute des défis de l’utilisation de réseaux de neurones récurrents dans un contexte d’apprentissage continuel, où de nouvelles tâches apparaissent au fur et à mesure. Les dépendances dans l’apprentissage continuel ne sont pas seulement contenues dans une tâche, mais sont aussi présentes entre les tâches. Ce chapitre discute de deux problèmes fondamentaux dans l’apprentissage continuel: (i) l’oubli catastrophique d’anciennes tâches et (ii) la capacité de saturation du réseau. De plus, une solution est proposée pour régler ces deux problèmes lors de l’entraînement d’un réseau de neurones récurrent. / In a multi-step prediction problem, the prediction at each time step can depend on the input at any of the previous time steps far in the past. Modelling such long-term dependencies is one of the fundamental problems in machine learning. In theory, Recurrent Neural Networks (RNNs) can model any long-term dependency. In practice, they can only model short-term dependencies due to the problem of vanishing and exploding gradients. This thesis explores the problem of vanishing gradient in recurrent neural networks and proposes novel solutions for the same. Chapter 3 explores the idea of using external memory to store the hidden states of a Long Short Term Memory (LSTM) network. By making the read and write operations of the external memory discrete, the proposed architecture reduces the rate of gradients vanishing in an LSTM. These discrete operations also enable the network to create dynamic skip connections across time. Chapter 4 attempts to characterize all the sources of vanishing gradients in a recurrent neural network and proposes a new recurrent architecture which has significantly better gradient flow than state-of-the-art recurrent architectures. The proposed Non-saturating Recurrent Units (NRUs) have no saturating activation functions and use additive cell updates instead of multiplicative cell updates. Chapter 5 discusses the challenges of using recurrent neural networks in the context of lifelong learning. In the lifelong learning setting, the network is expected to learn a series of tasks over its lifetime. The dependencies in lifelong learning are not just within a task, but also across the tasks. This chapter discusses the two fundamental problems in lifelong learning: (i) catastrophic forgetting of old tasks, and (ii) network capacity saturation. Further, it proposes a solution to solve both these problems while training a recurrent neural network.

In the process of designing an electric power supply system for an aircraft, parameters like low weight and low losses are important. Reliability, robustness and low cost are other important factors. In the Saab Gripen aircraft, the design of the primary power supply of the electric flight control system was updated by exchanging a switching transistor regulator to a magnetic amplifier (magamp). By introducing a magamp design, weight was saved and a more reliable power supply system at a lower cost was achieved. In this particular case, with the power supply of the electric flight control system in the Saab Gripen fighter, advantage could be taken of a specific permanent magnet generator (PM-generator). The frequency of the generator offered the perfect conditions for a magamp controller. A key parameter in designing magnetic amplifiers (magamps) is low losses. New amorphous alloys offer new possibilities of the technique in designing magnetic amplifiers, because of their extremely low losses. The core losses are evaluated by studying the equations and diagrams specifying the power losses. The core losses are evaluated and compared with the copper losses in the process of optimizing low weight and low losses. For this an engineering tool is developed and demonstrated. Evaluations of the hysteresis characteristics for the magnetic alloys, as well as modeling and simulation of the core losses, are presented in this work. The modeling of the core losses includes hysteresis losses, eddy current losses and excess losses as well as copper losses. The losses are studied dynamically during realistic operational conditions. The model can be used for any generic analysis of hysteresis in magnetic circuits. Applications of magnetic amplifiers in aircrafts have been demonstrated to be a feasible alternative / QC 20101103