Abstract

With the evolution of the electricity market into a restructured smart version, load forecasting has emerged as an eminent research domain. Many forecasting models have been proposed by researchers for electricity price and load forecasting. This state of art introduces a load time series modeled with a hybrid technique culminating from the logical amalgamation of GARCH, a conventional hard computing method, Fuzzy ARTMAP, an artificial intelligence-based soft computing technique, and wavelet transform, for treating the load time series. The study investigates into the ability of the proposed hybrid model in tackling the electricity load time series forecasting problems. The work under this study also includes comparisons drawn among models which use either one or two of the mentioned techniques and the model proposed. Results certify the efficacy and effectiveness of the model over others.

Abstract

Deep Learning requires huge amount of data with related labels, that are necessary for proper training. Thanks to modern videogames, which aim at photorealism, it is possible to easily obtain synthetic dataset by extracting information directly from the game engine. The intent is to use data extracted from a videogame to obtain a representation of various scenarios and train a deep neural network to infer the information required for a specific task. In this work we focus on computer vision aids for automotive applications and we target to estimate the distance and speed of the surrounding vehicles by using a single dashboard camera. We propose two network models for distance and speed estimation, respectively. We show that training them by using synthetic images generated by a game engine is a viable solution that turns out to be very effective in real settings. Document type: Part of book or chapter of book

Abstract

Part 3: Computational Intelligence and Algorithms; International audience; Computational technologies under the domain of intelligent systems are expected to help the rapidly increasing traffic congestion problem in recent traffic management. Traffic management requires efficient and accurate forecasting models to assist real time traffic control systems. Researchers have proposed various computational approaches, especially in short-term traffic flow forecasting, in order to establish reliable traffic patterns models and generate timely prediction results. Forecasting models should have high accuracy and low computational time to be applied in intelligent traffic management. Therefore, this paper aims to evaluate recent computational modeling approaches utilized in short-term traffic flow forecasting. These approaches are evaluated by real-world data collected on the British freeway (M6) from 1st to 30th November in 2014. The results indicate that neural network model outperforms generalized additive model and autoregressive integrated moving average model on the accuracy of freeway traffic forecasting. Document type: Part of book or chapter of book

Abstract

Forecasting Internet traffic is receiving an increasing attention from the computer networks domain. Indeed, by improving this task efficient traffic engineering and anomaly detection tools can be developed, leading to economic gains due to better resource management. This paper presents a Neural Network (NN) approach to predict TCP/IP traffic for all links of a backbone network, using both univariate and multivariate strategies. The former uses only past values of the forecasted link, while the latter is based on the neighbor links of the backbone topology. Several experiments were held by considering real-world data from the UK education and research network. Also, different time scales (e.g. every ten minutes and hourly) were analyzed. Overall, the proposed NN approach outperformed other forecasting methods (e.g. Holt-Winters). R&D Algoritmi centre Document type: Part of book or chapter of book

Abstract

Turksoy, Omer/0000-0003-4620-4503 WOS: 000492797300026 The energy efficiency of the battery charging system directly affects the distance which electric vehicles can get with per charge process. In addition, reducing current harmonics distortion (THD) increases the electrical quality and power conversion performance. This paper proposes intelligent control of high-efficiency two-stage battery charger topology for electric vehicles (EVs). In the first stage, for low harmonics of input current, high power factor and high efficiency, the average current mode controlled ac/dc boost power factor (pf) correction method constructed and analyzed with 98% efficiency and the power factor is achieved higher than 0.99. Additionally, in the second stage, for high energy efficiency, higher battery lifespan and allowing EVs to get more miles with per charge, a half-bridge LLC resonant converter controlled with a designed artificial neural network (ANN). Moreover, the LLC resonant converter controlled under dynamic load to analysis system from no-load to full-load. A 3.1 kW powered system has been designed for this study, the efficiency of the system has been calculated based on European efficiency standards and the peak efficiency of the whole system is 96.2%, the load voltage ripple is less than 0.5 V and also total harmonic distortion of the source current is less than 5%. (C) 2019 Elsevier Ltd. All rights reserved.

Abstract

We have developed an artificial neural network, whose purpose is to automatically find in a database of synthetic stellar spectra the one which best reproduces an observed spectrum. Using the equivalent widths of selected spectral lines, the network fits a set of lines related to the physical parameters in the stellar atmosphere (i.e., temperature, gravity and mass loss rate). The main advantage of this approach is its scalability.

Abstract

The fuzzy sets theory and the artificial neural networks are computational intelligence tools which are nowadays widely used in earthquake engineering. This paper develops a method and a computer program which use these computational intelligence tools in order to support the damage and safety evaluation of buildings after strong earthquakes. The model uses an artificial neural network with three layers and a Kohonen learning algorithm, it also uses fuzzy sets in order to manage subjective information such as linguistic qualification of the damage levels in buildings and a fuzzy rule base to support the decision making process. All these techniques are incorporated in the developed computer program. The input data is the subjective and incomplete information about the building state obtained by possibly non experienced evaluators in the field of the seismic performance of buildings. The proposed method is implemented in a tool especially useful in the emergency response phase, when it supports the decision making regarding the building habitability and reparability. In order to show its effectiveness, two examples are included for two different types of buildings.

Abstract

The interest in the electric vehicles rose recently due both to environmental questions and to energetic dependence of the contemporary society. Accordingly, it is necessary to study and implement in these vehicle fault diagnosis systems which enable them to be more reliable and safe enhancing its sustainability. In this work after a review on problem of faults in the drivetrain of series hybrid electric vehicles (SHEV), a deep investigation on fault diagnosis of AC-DC power converter and permanent magnet synchronous motor (PMSM) have been done as two important parts of traction chains in SHEVs. In other major part of this work, four types of faults (stator winding inter turn short circuit, demagnetization, eccentricity ant bearing faults) of a PMSM have been studied. Inter turn short circuit of stator winding of PMSM in different speeds and loads has been considered to identify fault feature in all operation aspects, as it is expected by electric vehicle application. Experimental results aiming short circuits, bearing and eccentricity fault detection has been presented. Analytical and finite element method (FEM) aiming demagnetization fault investigation has been developed. The AC-DC converter switches are generally exposed to the possibility of outbreak open phase faults because of troubles of the switching devices. This work proposes a robust and efficient identification method for data acquisition selection aiming fault analysis and detection. Two new patterns under AC-DC converter failure are identified and presented. To achieve this goal, four different level of switches fault are considered on the basis of both simulation and experimental results. For accuracy needs of the identified pattern for SHEV application, several parameters have been considered namely: capacitor size changes, load and speed variations. On the basis of the developed fault sensitive models above, an ANN based fault detection, diagnosis strategy and the related algorithm have been developed to show the way of using the identified patterns in the supervision and the diagnosis of the PMSM drivetrain of SHEVs. ANN method have been used to develop three diagnosis based models for : the vector controlled PMSM under inter turn short circuit, the AC/DC power converter under an open phase fault and also the PMSM under unbalanced voltage caused by open phase DC/AC inverter. These models allow supervising the main components of the PMSM drivetrains used to propel the SHEV. The ANN advantages of ability to include a lot of data mad possible to classify the faults in terms of their type and severity. This allows estimating the performance degree of that drivetrains during faulty conditions through the parameter state of health (SOH). The latter can be used in a global control strategy of PMSM control in degraded mode in which the control is auto-adjusted when a defect occurs on the system. The goal is to ensure a continuity of service of the SHEV in faulty conditions to improve its reliability.; L'intérêt pour les véhicules électriques ne cesse de croitre au sein de la société contemporaine compte tenu de ses nombreuses interrogations sur l’environnement et la dépendance énergétique. Dans ce travail de thèse, nous essayons d’améliorer l’acceptabtabilité sociétale du véhicule électrique en essayant de faire avancer la recherche sur le diagnostique des défauts d’une chaine de traction électrique. Les résultats escomptés devraient permettre à terme d’améliorer la fiabilité et la durabilité de ces systèmes.Nous commençons par une revue des problèmes des défauts déjà apparus dans les véhicules hybrides séries qui disposent de l’architecture la plus proche du véhicule électrique. Une étude approfondie sur le diagnostic des défauts d’un convertisseur de puissance statique (AC-DC) ainsi que celle du moteur synchrone à aimants permanents est menée. Quatre types de défauts majeurs ont été répertoriés concernant le moteur (court-circuit au stator, démagnétisation, excentricité du rotor et défaut des roulements). Au niveau du convertisseur, nous avons considéré le défaut d’ouverture des interrupteurs. Afin d’être dans les mêmes conditions d’utilisation réelle, nous avons effectué des tests expérimentaux à vitesse et charge variables. Ce travail est basé aussi bien sur l’expérimentation que sur la modélisation. Comme par exemple, la méthode des éléments finis pour l’étude de la démagnétisation de la machine. De même, l’essai en court-circuit du stator du moteur en présence d’un contrôle vectoriel.Afin de réaliser un diagnostic en ligne des défauts, nous avons développé un modèle basé sur les réseaux de neurones. L’apprentissage de ce réseau de neurone a été effectué sur la base des résultats expérimentaux et de simulations, que nous avons réalisées. Le réseau de neurones est capable d'assimiler beaucoup de données. Ceci nous permet de classifier les défauts en termes de sévérité et de les localiser. Il permet ainsi d'évaluer le degré de performance de la chaine de traction électrique en ligne en présence des défauts et nous renseigner ainsi sur l'état de santé du système. Ces résultats devraient aboutir à l’élaboration d’une stratégie de contrôle tolérant aux défauts auto-reconfigurable pour prendre en compte les modes dégradés permettant une continuité de service du véhicule ce qui améliorera sa disponibilité.