Classificação de padrões através de um comitê de máquinas aprimorado por aprendizagem por reforço

Reinforcement learning is a machine learning technique that, although finding a large number of applications, maybe is yet to reach its full potential. One of the inadequately tested possibilities is the use of reinforcement learning in combination with other methods for the solution of pattern classification problems. It is well documented in the literature the problems that support vector machine ensembles face in terms of generalization capacity. Algorithms such as Adaboost do not deal appropriately with the imbalances that arise in those situations. Several alternatives have been proposed, with varying degrees of success. This dissertation presents a new approach to building committees of support vector machines. The presented algorithm combines Adaboost algorithm with a layer of reinforcement learning to adjust committee parameters in order to avoid that imbalances on the committee components affect the generalization performance of the final hypothesis. Comparisons were made with ensembles using and not using the reinforcement learning layer, testing benchmark data sets widely known in area of pattern classification

Viabilidade da Utilização de Máquinas de Indução Convencionais como Motores sem Mancais Mecânicos

Electrical Motors transform electrical energy into mechanic energy in a relatively easy way. In some specific applications, there is a need for electrical motors to function with noncontaminated fluids, in high speed systems, under inhospitable conditions, or yet, in local of difficult access and considerable depth. In these cases, the motors with mechanical bearings are not adequate as their wear give rise to maintenance. A possible solution for these problems stems from two different alternatives: motors with magnetic bearings, that increase the length of the machine (not convenient), and the bearingless motors that aggregate compactness. Induction motors have been used more and more in research, as they confer more robustness to bearingless motors compared to other types of machines building with others motors. The research that has already been carried out with bearingless induction motors utilized prototypes that had their structures of stator/rotor modified, that differ most of the times from the conventional induction motors. The goal of this work is to study the viability of the use of conventional induction Motors for the beringless motors applications, pointing out the types of Motors of this category that can be more useful. The study uses the Finite Elements Method (FEM). As a means of validation, a conventional induction motor with squirrel-cage rotor was successfully used for the beringless motor application of the divided winding type, confirming the proposed thesis. The controlling system was implemented in a Digital Signal Processor (DSP)

Controle Robusto Aplicado a Conversor Buck-Boost em Sistemas Fotovoltaicos

The need to implement a software architecture that promotes the development of a SCADA supervisory system for monitoring industrial processes simulated with the flexibility of adding intelligent modules and devices such as CLP, according to the specifications of the problem, it was the motivation for this work. In the present study, we developed an intelligent supervisory system on a simulation of a distillation column modeled with Unisim. Furthermore, OLE Automation was used as communication between the supervisory and simulation software, which, with the use of the database, promoted an architecture both scalable and easy to maintain. Moreover, intelligent modules have been developed for preprocessing, data characteristics extraction, and variables inference. These modules were fundamentally based on the Encog software

Estudo de Superfícies Seletivas de Frequência com o Uso de Inteligência Computacional

The main objective of this work is to optimize the performance of frequency selective surfaces (FSS) composed of crossed dipole conducting patches. The optimization process is performed by determining proper values for the width of the crossed dipoles and for the FSS array periodicity, while the length of the crossed dipoles is kept constant. Particularly, the objective is to determine values that provide wide bandwidth using a search algorithm with representation in bioinspired real numbers. Typically FSS structures composed of patch elements are used for band rejection filtering applications. The FSS structures primarily act like filters depending on the type of element chosen. The region of the electromagnetic spectrum chosen for this study is the one that goes from 7 GHz to 12 GHz, which includes mostly the X-band. This frequency band was chosen to allow the use of two X-band horn antennas, in the FSS measurement setup. The design of the FSS using the developed genetic algorithm allowed increasing the structure bandwidth

Controle fuzzy espacialmente diferenciado para um sistema de irrigação

Traditional irrigation projects do not locally determine the water availability in the soil. Then, irregular irrigation cycles may occur: some with insufficient amount that leads to water deficit, other with excessive watering that causes lack of oxygen in plants. Due to the nonlinear nature of this problem and the multivariable context of irrigation processes, fuzzy logic is suggested to replace commercial ON-OFF irrigation system with predefined timing. Other limitation of commercial solutions is that irrigation processes either consider the different watering needs throughout plant growth cycles or the climate changes. In order to fulfill location based agricultural needs, it is indicated to monitor environmental data using wireless sensors connected to an intelligent control system. This is more evident in applications as precision agriculture. This work presents the theoretical and experimental development of a fuzzy system to implement a spatially differentiated control of an irrigation system, based on soil moisture measurement with wireless sensor nodes. The control system architecture is modular: a fuzzy supervisor determines the soil moisture set point of each sensor node area (according to the soil-plant set) and another fuzzy system, embedded in the sensor node, does the local control and actuates in the irrigation system. The fuzzy control system was simulated with SIMULINK® programming tool and was experimentally built embedded in mobile device SunSPOTTM operating in ZigBee. Controller models were designed and evaluated in different combinations of input variables and inference rules base

Ambiente de desenvolvimentoweb multiplataforma configurável para robótica educacional

We propose an online configurable multiplatform development environment specifically developed for educational robotics applications. The environment, which appears as an extension of RoboEduc software, allows the programming of several programmable robots to be performed using the R-Educ language. We make it possible for the user to program in the language R-Educ and then translate the code to a language previously registered, compiled and then sent or executed by the robot. To develop this work, we conducted a bibliographic research about the main programming languages used in robotics, as well as their definitions and paradigms, from which it was possible to define a set of patterns considered important for the creation of this environment. Then, in the software development phase, we implemented the development environment, bearing in mind the requirements and functionality defined in the design phase. Finally, to validate the platform, we conducted some trials of programming languages and verificate if the complete cycle was satisfied - registration of language, programming in R-Educ, compilation for the registered language, compilation to the machine code and send the code for the robot

Uso de funções de alívio para estimar o efeito de chaveamentos corretivos na eliminação de congestionamentos em sistemas de potência

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior

Controle de posição com restrição à orientação de um Veículo Aéreo Não-Tripulado tipo Quadrirrotor

Quadrotors aircraft are composed by four propellers mounted on four engines on a cross or x disposition, and, in this structure, the engines on the same arm spin in the same direction and the other arm in the opposite direction. By rotating each helix generates vertical upward thrust. The control is done by varying the rotational speed of each motor. Among the advantages of this type of vehicle can cite the mechanical simplicity of construction, the high degree of maneuverability and the ability to have vertical takeoffs and landings. The modeling and control of quadrirrotores have been a challenge due to problems such as nonlinearity and coupling between variables. Several strategies have been developed to control this type of vehicle, from the classical control to modern. There are air surveillance applications where a camera is fixed on the vehicle to point forward, where it is desired that the quadrotor moves at a fixed altitude toward the target also pointing forward, which imposes an artificial constraint motion, because it is not desired that it moves laterally, but only forwards or backwards and around its axes . This restriction is similar to the naturally existing on robots powered by wheels with differential drive, which also can not move laterally, due to the friction of the wheels. Therefore, a position control strategy similar to that used in this type of robot could be adapted for aerial robots like quadrotor. This dissertation presents and discusses some strategies for the control of position and orientation of quadrotors found in the literature and proposes a strategy based on dynamic control of mobile robots with differential drive, called the variable reference control. The validity of the proposed strategy is demonstrated through computer simulations

Avaliação de desempenho da codificação wavelet em canais seletivos em frequência

Wavelet coding has emerged as an alternative coding technique to minimize the fading effects of wireless channels. This work evaluates the performance of wavelet coding, in terms of bit error probability, over time-varying, frequency-selective multipath Rayleigh fading channels. The adopted propagation model follows the COST207 norm, main international standards reference for GSM, UMTS, and EDGE applications. The results show the wavelet coding s efficiency against the inter symbolic interference which characterizes these communication scenarios. This robustness of the presented technique enables its usage in different environments, bringing it one step closer to be applied in practical wireless communication systems

Projeto em FPGA de um controlador unificado para correção de fator de potência em retificadores boost bidirecionais monofásicos

The use of Field Programmable Gate Array (FPGA) for development of digital control strategies for power electronics applications has aroused a growing interest of many researchers. This interest is due to the great advantages offered by FPGA, which include: lower design effort, high performance and highly flexible prototyping. This work proposes the development and implementation of an unified one-cycle controller for boost CFP rectifier based on FPGA. This controller can be applied to a total of twelve converters, six inverters and six rectifiers defined by four single phase VSI topologies and three voltage modulation types. The topologies considered in this work are: full-bridge, interleaved full-bridge, half-bridge and interleaved half-bridge. While modulations are classified in bipolar voltage modulation (BVM), unipolar voltage modulation (UVM) and clamped voltage modulation (CVM). The proposed project is developed and prototyped using tools Matlab/Simulink® together with the DSP Builder library provided by Altera®. The proposed controller was validated with simulation and experimental results

Análise e projeto de superfícies seletivas em frequência multibanda e/ou banda larga

Frequency selective surfaces (Frequency Selective Surface - FSS) are often used in various applications in telecommunications. Some of these applications may require that these structures have response with multiple resonance bands. Other applications require that the FSS response have large frequency range, to meet the necessary requirements. FSS to design with these features there are numerous techniques cited in the scientific literature. Thus, the purpose of this paper is to examine some common techniques such as: Overlap of FSS; Elements combined; Elements Elements convolucionados and fractals. And designing multiband FSS and / or broadband selecting simple ways in terms of construction and occupy the smallest possible space, aiming at practical applications. Given these requirements, three projects FSS were performed: a technology applied to IEEE 802.11 a/b/g/n and two projects for application in UWB. In project development, commercial software Ansoft DesignerTM and experimental results were satisfactory was used

Compressão Seletiva de Imagens Coloridas com Detecção Automática de Regiões de Interesse

There has been an increasing tendency on the use of selective image compression, since several applications make use of digital images and the loss of information in certain regions is not allowed in some cases. However, there are applications in which these images are captured and stored automatically making it impossible to the user to select the regions of interest to be compressed in a lossless manner. A possible solution for this matter would be the automatic selection of these regions, a very difficult problem to solve in general cases. Nevertheless, it is possible to use intelligent techniques to detect these regions in specific cases. This work proposes a selective color image compression method in which regions of interest, previously chosen, are compressed in a lossless manner. This method uses the wavelet transform to decorrelate the pixels of the image, competitive neural network to make a vectorial quantization, mathematical morphology, and Huffman adaptive coding. There are two options for automatic detection in addition to the manual one: a method of texture segmentation, in which the highest frequency texture is selected to be the region of interest, and a new face detection method where the region of the face will be lossless compressed. The results show that both can be successfully used with the compression method, giving the map of the region of interest as an input

Desenvolvimento de material compósito a base de raspa de pneu e látex para isolamento térmico

The process of recycling has been stimulated by the markets for several reasons, mainly on economical and environmental. Several products have been developed from recycled materials that already exist as well as several residues have been studied in different forms of applications. The greater majority of the applications for thermal insulation in the domestic, commercial and industrial systems have been elaborated in the temperature ranges between low to medium reaching up to 180oC. Many materials such as glass wool, rock wool, polystyrene are being used which are aggressive to the environment. Such materials in spite of the effectiveness in the retention of heat flow, they cost more and when discarded take several years to be absorbed by the nature. This way, in order to adapt to a world politics concerning the preservation of the environment, the present study was intended to develop a material composed of natural/biodegradable materials and industrial residues. The development of such a product in the form of a composite material based on tyre scrapes and latex for thermal insulation is presented in this research work. Thermal and physical properties of the tire scrapes as well as latex were studied in order to use them as raw materials for the manufacture of the intended composite to be applied as a thermal insulator in hot and cold systems varying between 0ºC and 200oC, respectively. Composite blankets were manufactured manually, in weight proportions of 1:1 (50:50%); 1:2 (33:67%) and 2:1 (67:33%) (tire scrapes: latex) respectively. Physical, mechanical and thermal properties of the composites were analyzed to obtain data about the viability of using the composite as a thermal insulator. The analyses carried out were based on standards ABNT, ASTM and UL. The maximum temperature obtained for the composite as a thermal insulator was 200ºC, which meets the range of applications that could be used as a thermal insulator in domestic as well as industrial purposes. The experimental results prove that the composite can be used as a thermal insulator on heated or cooled surface

Obtenção e caracterização de um compósito de poliuretano de mamona e pó de vidro para aplicações em insolantes térmicos

Thermal insulation is used to protect the heated or cooled surfaces by the low thermal conductivity materials. The rigid ricin polyurethane foams (PURM) are used for thermal insulation and depend on the type and concentration of blowing agent. Obtaining PURM occurs by the use of polyol, silicone, catalyst and blowing agent are pre -mixed, reacting with the isocyanate. The glass is reusable, returnable and recyclable heat insulating material, whose time of heat dissipation determines the degree of relaxation of its structure; and viscosity determines the conditions for fusion, operating temperatures, annealing, etc. The production of PURM composites with waste glass powder (PV) represents economical and renewable actions of manufacturing of thermal insulating materials. Based on these aspects, the study aimed to produce and characterize the PURM composites with PV, whose the mass percentages were 5, 10, 20, 30, 40 and 50 wt%. PURM was obtained commercially, while the PV was recycled from the tailings of the stoning process of a glassmaking; when the refining process was applied to obtain micrometer particles. The PURM + PV composites were studied taking into account the standard sample of pure PURM and the influence of the percentage of PV in this PURM matrix. The results of the chemical, physical and morphological characterization were discussed taking into account the difference in the microstructural morphology of the PURM+PV composites and the pure PURM, as well the results of the physicochemical, mechanical e thermophysical tests by values obtained of density, hardness, compressive strength, specific heat, thermal conductivity and diffusivity. In general, the structure of pure PURM showed large, elongated and regular pores, while PURM+PV composites showed irregular, small and rounded pores with shapeless cells. This may have contributed to reducing their mechanical strength, especially for PURM - PV50. The hardness and density were found to have a proportional relationship with the PV content on PURM matrix. The specific heat, thermal diffusivity and thermal conductivity showed proportional relationship to each other. So, this has been realized that the increasing the PV content on PURM matrix resulted in the rise of diffusivity and thermal conductivity and the decrease of the specific heat. However, the values obtained by the PURM composites were similar the values of pure PURM, mainly the PURM-PV5 and PURM-PV10. Therefore, these composites can be applied like thermal insulator; furthermore, their use could reduce the production costs and to preserve the environment

Desenho e Construção de um protótipo gerador de jato de plasma frio a pressão atmosférica para aplicações biomédicas

Research for better performance materials in biomedical applications are constants. Thus recent studies aimed at the development of new techniques for modification of surfaces. The low pressure plasma has been highlighted for its versatility and for being environmentally friendly, achieving good results in the modification of physic chemical properties of materials. However, it is requires an expensive vacuum system and cannot able to generate superficial changes in specific regions. Furthermore, it is limits their use in polymeric materials and sensitive terms due to high process temperatures. Therefore, new techniques capable of generating cold plasma at atmospheric pressure (APPJ) were created. In order to perform surface treatments on biomaterials in specific regions was built a prototype capable of generating a cold plasma jet. The prototype plasma generator consists of a high voltage source, a support arm, sample port and a nozzle through which the ionized argon. The device was formed to a dielectric tube and two electrodes. This work was varied some parameters such as position between electrodes, voltage and electrical frequency to verify the behavior of glow discharges. The disc of titanium was polished and there was a surface modification. The power consumed, length, intensity and surface modifications of titanium were analyzed. The energy consumed during the discharges was observed by the Lissajous figure method. To check the length of the jets was realized with Image Pro Plus software. The modifications of the titanium surfaces were observed by optical microscopy (OM ) and atomic force microscopy (AFM ). The study showed that variations of the parameters such as voltage, frequency and geometric position between the electrodes influence the formation of the plasma jet. It was concluded that the plasma jet near room temperature and atmospheric pressure was able to cause modifications in titanium surface