Multilayer perceptron neural networks training through charged system search and its Application for non-technical losses detection

The non-technical loss is not a problem with trivial solution or regional character and its minimization represents the guarantee of investments in product quality and maintenance of power systems, introduced by a competitive environment after the period of privatization in the national scene. In this paper, we show how to improve the training phase of a neural network-based classifier using a recently proposed meta-heuristic technique called Charged System Search, which is based on the interactions between electrically charged particles. The experiments were carried out in the context of non-technical loss in power distribution systems in a dataset obtained from a Brazilian electrical power company, and have demonstrated the robustness of the proposed technique against with several others nature-inspired optimization techniques for training neural networks. Thus, it is possible to improve some applications on Smart Grids. © 2013 IEEE.

Decomposição de Dantzig-Wolfe aplicada ao problema de planejamento de reativos em sistemas de potência multi-áreas

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Estimação do diâmetro e rugosidade em um processo de furação utilizando multi sensores e redes neurais artificiais

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Pré-regulador retificador boost com controle digital por valores médios, para sistema de iluminação fluorescente multi-lâmpadas, utilizando dispositivo FPGA e VHDL

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Proposta para indicação de áreas para a implantação de aterro sanitário no município de Bauru-SP, utilizando análise multi critério de decisão e técnicas de geoprocessamento

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Planejamento e despacho ótimo de reativos (VAr) em sistemas de energia elétrica multi-áreas

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Estudo multi-temporal do uso, ocupação e perda de solos em projetos de assentamentos em Rondônia

Pós-graduação em Geociências e Meio Ambiente - IGCE

High pressure vapor-liquid equilibria of palm fatty acids distillates-carbon dioxide system

Equilíbrio líquido-vapor do sistema destilado ácido do óleo de palma-dióxido de carbono a alta pressão. Foi investigado experimentalmente o equilíbrio líquido-vapor para o sistema Destilado Ácido de Óleo de Palma (PFAD)/Dióxido de Carbono, nas temperaturas de 333, 353 e 373 K e pressões de 20, 23, 26 e 29 MPa, usando-se o método estático. Os dados experimentais do sistema pseudo-binário PFAD/CO₂ foram correlacionados com a equação de estado de Redlich-Kwong do pacote computacional ASPEN. O modelo reproduz bem os resultados experimentais. A seletividade obtida indica que o CO₂ supercrítico é um solvente razoável para a separação em coluna multi-estágio e contínua, do ácido graxo saturado (ácido palmítico) daqueles insaturados (ácido oleico e ácido linoleico) contidos no PFAD.

Ecological relevance of sentinels' biomarker responses: A multi-level approach

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Energy Management and Control for Islanded Microgrid Using Multi-Agents

This paper presents a multi-agent system for real-time operation of simulated microgrid using the Smart-Grid Test Bed at Washington State University. The multi-agent system (MAS) was developed in JADE (Java Agent DEvelopment Framework) which is a Foundation for Intelligent Physical Agents (FIPA) compliant open source multi-agent platform. The proposed operational strategy is mainly focused on using an appropriate energy management and control strategies to improve the operation of an islanded microgrid, formed by photovoltaic (PV) solar energy, batteries and resistive and rotating machines loads. The focus is on resource management and to avoid impact on loads from abrupt variations or interruption that changes the operating conditions. The management and control of the PV system is performed in JADE, while the microgrid model is simulated in RSCAD/RTDS (Real-Time Digital Simulator). Finally, the outcome of simulation studies demonstrated the feasibility of the proposed multi-agent approach for real-time operation of a microgrid.

A Multi-Stage Stochastic Non-Linear Model for Reactive Power Planning Under Contingencies

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Multi-vortex State Induced by Proximity Effects in a Small Superconducting Square

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Performance of a New One-step Multi-mode Adhesive on Etched vs Non-etched Enamel on Bond Strength and Interfacial Morphology

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Desenvolvimento, otimização e caracterização física de um novo sistema multi-sensores de Biosusceptometria de Corrente Alternada (BAC) para obtenção de imagens biomagnéticas

A novel AC Biosusceptometry (ACB) system with thirteen sensors it was implemented and characterized in vitro using magnetic phantoms. The system presenting coils in a coaxial arrangement with one pair of excitation coil outside and thirteen pairs of detection coils inside. A first-order gradiometric configuration was utilized for optimal detection of magnetic signals. Several physical parameters such as baseline, number of turns, excitation field and diameters were studied for improvement of the signal/noise ratio. This system exhibits an enhanced sensitivity and spatial resolution, due to the higher density of sensors/area. In the future those characteristics will turn possible to obtain images of magnetic marker or tracer in the gastrointestinal tract focusing on physiological and pharmaceutical studies. ACB emerged due to its interesting nature, noninvasiveness and low cost to investigate gastrointestinal parameters and this system can contribute for more accurate interpretation of biomedical signals and images

Planejamento de reativos em sistemas elétricos de potência multi-área através de modelos estocásticos

Pós-graduação em Engenharia Elétrica - FEIS