Otimização de superfícies seletivas de frequência com elementos pré-fractais utilizando rede neural MLP e algoritmos de busca populacional

This thesis describes design methodologies for frequency selective surfaces (FSSs) composed of periodic arrays of pre-fractals metallic patches on single-layer dielectrics (FR4, RT/duroid). Shapes presented by Sierpinski island and T fractal geometries are exploited to the simple design of efficient band-stop spatial filters with applications in the range of microwaves. Initial results are discussed in terms of the electromagnetic effect resulting from the variation of parameters such as, fractal iteration number (or fractal level), fractal iteration factor, and periodicity of FSS, depending on the used pre-fractal element (Sierpinski island or T fractal). The transmission properties of these proposed periodic arrays are investigated through simulations performed by Ansoft DesignerTM and Ansoft HFSSTM commercial softwares that run full-wave methods. To validate the employed methodology, FSS prototypes are selected for fabrication and measurement. The obtained results point to interesting features for FSS spatial filters: compactness, with high values of frequency compression factor; as well as stable frequency responses at oblique incidence of plane waves. This thesis also approaches, as it main focus, the application of an alternative electromagnetic (EM) optimization technique for analysis and synthesis of FSSs with fractal motifs. In application examples of this technique, Vicsek and Sierpinski pre-fractal elements are used in the optimal design of FSS structures. Based on computational intelligence tools, the proposed technique overcomes the high computational cost associated to the full-wave parametric analyzes. To this end, fast and accurate multilayer perceptron (MLP) neural network models are developed using different parameters as design input variables. These neural network models aim to calculate the cost function in the iterations of population-based search algorithms. Continuous genetic algorithm (GA), particle swarm optimization (PSO), and bees algorithm (BA) are used for FSSs optimization with specific resonant frequency and bandwidth. The performance of these algorithms is compared in terms of computational cost and numerical convergence. Consistent results can be verified by the excellent agreement obtained between simulations and measurements related to FSS prototypes built with a given fractal iteration

Desenvolvimento de um sistema Inteligente para a análise de cartas dinamométricas no método de elevação por bombeio mecânico

The artificial lifting of oil is needed when the pressure of the reservoir is not high enough so that the fluid contained in it can reach the surface spontaneously. Thus the increase in energy supplies artificial or additional fluid integral to the well to come to the surface. The rod pump is the artificial lift method most used in the world and the dynamometer card (surface and down-hole) is the best tool for the analysis of a well equipped with such method. A computational method using Artificial Neural Networks MLP was and developed using pre-established patterns, based on its geometry, the downhole card are used for training the network and then the network provides the knowledge for classification of new cards, allows the fails diagnose in the system and operation conditions of the lifting system. These routines could be integrated to a supervisory system that collects the cards to be analyzed

Sistema inteligente para estimar a porosidade em sedimentos a partir da análise de sinais GPR

This Thesis presents the elaboration of a methodological propose for the development of an intelligent system, able to automatically achieve the effective porosity, in sedimentary layers, from a data bank built with information from the Ground Penetrating Radar GPR. The intelligent system was built to model the relation between the porosity (response variable) and the electromagnetic attribute from the GPR (explicative variables). Using it, the porosity was estimated using the artificial neural network (Multilayer Perceptron MLP) and the multiple linear regression. The data from the response variable and from the explicative variables were achieved in laboratory and in GPR surveys outlined in controlled sites, on site and in laboratory. The proposed intelligent system has the capacity of estimating the porosity from any available data bank, which has the same variables used in this Thesis. The architecture of the neural network used can be modified according to the existing necessity, adapting to the available data bank. The use of the multiple linear regression model allowed the identification and quantification of the influence (level of effect) from each explicative variable in the estimation of the porosity. The proposed methodology can revolutionize the use of the GPR, not only for the imaging of the sedimentary geometry and faces, but mainly for the automatically achievement of the porosity one of the most important parameters for the characterization of reservoir rocks (from petroleum or water)

Emprego de redes neurais artificiais supervisionadas e não supervisionadas no estudo de parâmetros reológicos de excipientes farmacêuticos sólidos

In this paper artificial neural network (ANN) based on supervised and unsupervised algorithms were investigated for use in the study of rheological parameters of solid pharmaceutical excipients, in order to develop computational tools for manufacturing solid dosage forms. Among four supervised neural networks investigated, the best learning performance was achieved by a feedfoward multilayer perceptron whose architectures was composed by eight neurons in the input layer, sixteen neurons in the hidden layer and one neuron in the output layer. Learning and predictive performance relative to repose angle was poor while to Carr index and Hausner ratio (CI and HR, respectively) showed very good fitting capacity and learning, therefore HR and CI were considered suitable descriptors for the next stage of development of supervised ANNs. Clustering capacity was evaluated for five unsupervised strategies. Network based on purely unsupervised competitive strategies, classic "Winner-Take-All", "Frequency-Sensitive Competitive Learning" and "Rival-Penalize Competitive Learning" (WTA, FSCL and RPCL, respectively) were able to perform clustering from database, however this classification was very poor, showing severe classification errors by grouping data with conflicting properties into the same cluster or even the same neuron. On the other hand it could not be established what was the criteria adopted by the neural network for those clustering. Self-Organizing Maps (SOM) and Neural Gas (NG) networks showed better clustering capacity. Both have recognized the two major groupings of data corresponding to lactose (LAC) and cellulose (CEL). However, SOM showed some errors in classify data from minority excipients, magnesium stearate (EMG) , talc (TLC) and attapulgite (ATP). NG network in turn performed a very consistent classification of data and solve the misclassification of SOM, being the most appropriate network for classifying data of the study. The use of NG network in pharmaceutical technology was still unpublished. NG therefore has great potential for use in the development of software for use in automated classification systems of pharmaceutical powders and as a new tool for mining and clustering data in drug development

Conversor CC/CA de alta freqüência baseado em inversores ressonantes com comutação seqüencial para excitação de uma tocha indutiva a plasma térmico

This work describes the study, the analysis, the project methodology and the constructive details of a high frequency DC/AC resonant series converter using sequential commutation techniques for the excitation of an inductive coupled thermal plasma torch. The aim of this thesis is to show the new modulation technique potentialities and to present a technological option for the high-frequency electronic power converters development. The resonant converter operates at 50 kW output power under a 400 kHz frequency and it is constituted by inverter cells using ultra-fast IGBT devices. In order to minimize the turn-off losses, the inverter cells operates in a ZVS mode referred by a modified PLL loop that maintains this condition stable, despite the load variations. The sequential pulse gating command strategy used it allows to operate the IGBT devices on its maximum power limits using the derating and destressing current scheme, as well as it propitiates a frequency multiplication of the inverters set. The output converter is connected to a series resonant circuit constituted by the applicator ICTP torch, a compensation capacitor and an impedance matching RF transformer. At the final, are presented the experimental results and the many tests achieved in laboratory as form to validate the proposed new technique

Uma fonte chaveada de 50kW com correção de fator de potência para alimentação de uma tocha de plasma Indutiva utilizando técnicas de controle digital

This work deals with the development of an experimental study on a power supply of high frequency that provides the toch plasmica to be implemented in PLASPETRO project, which consists of two static converters developed by using Insulated Gate Bipolar Transistor (IGBT). The drivers used to control these keys are triggered by Digital Signal Processor (DSP) through optical fibers to reduce problems with electromagnetic interference (EMI). The first stage consists of a pre-regulator in the form of an AC to DC converter with three-phase boost power factor correction which is the main theme of this work, while the second is the source of high frequency itself. A series-resonant inverter consists of four (4) cell inverters operating in a frequency around 115 kHz each one in soft switching mode, alternating itself to supply the load (plasma torch) an alternating current with a frequency of 450 kHz. The first stage has the function of providing the series-resonant inverter a DC voltage, with the value controlled from the power supply provided by the electrical system of the utility, and correct the power factor of the system as a whole. This level of DC bus voltage at the output of the first stage will be used to control the power transferred by the inverter to the load, and it may vary from 550 VDC to a maximum of 800 VDC. To control the voltage level of DC bus driver used a proportional integral (PI) controller and to achieve the unity power factor it was used two other proportional integral currents controllers. Computational simulations were performed to assist in sizing and forecasting performance. All the control and communications needed to stage supervisory were implemented on a DSP

Desenvolvimento de uma arquitetura em hardware prototipada em FPGA para aplicações genéricas utilizando redes neurais artificiais embarcadas

This work proposes hardware architecture, VHDL described, developed to embedded Artificial Neural Network (ANN), Multilayer Perceptron (MLP). The present work idealizes that, in this architecture, ANN applications could easily embed several different topologies of MLP network industrial field. The MLP topology in which the architecture can be configured is defined by a simple and specifically data input (instructions) that determines the layers and Perceptron quantity of the network. In order to set several MLP topologies, many components (datapath) and a controller were developed to execute these instructions. Thus, an user defines a group of previously known instructions which determine ANN characteristics. The system will guarantee the MLP execution through the neural processors (Perceptrons), the components of datapath and the controller that were developed. In other way, the biases and the weights must be static, the ANN that will be embedded must had been trained previously, in off-line way. The knowledge of system internal characteristics and the VHDL language by the user are not needed. The reconfigurable FPGA device was used to implement, simulate and test all the system, allowing application in several real daily problems

Modelos de dispositivos de microondas e ópticos através de redes neurais artificiais de alimentação direta

This dissertation contributes for the development of methodologies through feed forward artificial neural networks for microwave and optical devices modeling. A bibliographical revision on the applications of neuro-computational techniques in the areas of microwave/optical engineering was carried through. Characteristics of networks MLP, RBF and SFNN, as well as the strategies of supervised learning had been presented. Adjustment expressions of the networks free parameters above cited had been deduced from the gradient method. Conventional method EM-ANN was applied in the modeling of microwave passive devices and optical amplifiers. For this, they had been proposals modular configurations based in networks SFNN and RBF/MLP objectifying a bigger capacity of models generalization. As for the training of the used networks, the Rprop algorithm was applied. All the algorithms used in the attainment of the models of this dissertation had been implemented in Matlab

Análise de desempenho da rede neural artificial do tipo multilayer perceptron na era multicore

Artificial neural networks are usually applied to solve complex problems. In problems with more complexity, by increasing the number of layers and neurons, it is possible to achieve greater functional efficiency. Nevertheless, this leads to a greater computational effort. The response time is an important factor in the decision to use neural networks in some systems. Many argue that the computational cost is higher in the training period. However, this phase is held only once. Once the network trained, it is necessary to use the existing computational resources efficiently. In the multicore era, the problem boils down to efficient use of all available processing cores. However, it is necessary to consider the overhead of parallel computing. In this sense, this paper proposes a modular structure that proved to be more suitable for parallel implementations. It is proposed to parallelize the feedforward process of an RNA-type MLP, implemented with OpenMP on a shared memory computer architecture. The research consistes on testing and analizing execution times. Speedup, efficiency and parallel scalability are analyzed. In the proposed approach, by reducing the number of connections between remote neurons, the response time of the network decreases and, consequently, so does the total execution time. The time required for communication and synchronization is directly linked to the number of remote neurons in the network, and so it is necessary to investigate which one is the best distribution of remote connections

Controle de Temperatura do Sistema de Refrigeração a água de uma tocha plasmática Indutiva Utilizando Lógica fuzzy

Este projeto propõe desenvolver e implementar um controlador para o sistema de refrigeração da tocha indutiva a plasma térmico. Este processo é feito a partir da medição da temperatura através de um sensor do sistema de refrigeração. O sinal produzido será enviado para uma entrada analógica do microcontrolador da família PIC, que utilizando os conceitos de lógica fuzzy, controla a velocidade de um motor bomba. Este é responsável por diminuir ou aumentar o fluxo circulante de água que passa pela bobina, pelo corpo da tocha e pelo flange de fixação, deixando-os na temperatura desejada. A velocidade desta bomba será controlada por um inversor de frequência. O microcontrolador, também, acionará um ventilador caso exceda a temperatura de referência. A proposta inicial foi o desenvolvimento do controle da temperatura da bobina de uma tocha indutiva a plasma, mas com algumas adequações, foi possível também aplicar no corpo da tocha. Essa tocha será utilizada em uma planta de tratamento de resíduos industriais e efluentes petroquímicos. O controle proposto visa garantir as condições físicas necessárias para tocha de plasma, mantendo a temperatura da água em um determinado nível que permita o resfriamento sem comprometer, no entanto, o rendimento do sistema. No projeto será utilizada uma tocha de plasma com acoplamento indutivo (ICPT), por ter a vantagem de não possuir eletrodos metálicos internos sendo erodidos pelo jato de plasma, evitando uma possível contaminação, e também devido à possibilidade do reaproveitamento energético através da cogeração de energia. O desenvolvimento da tecnologia a plasma na indústria de tratamento de resíduos vem obtendo bons resultados. Aplicações com essa tecnologia têm se tornado cada vez mais importantes por reduzir, em muitos casos, a produção de resíduos e o consumo de energia em vários processos industriais

Aspectos clínicos, radiográficos e histológicos da superfície oclusal de molares decíduos com e sem lesão de cárie: estudo in vitro

Fundação de Amparo a Pesquisa do Estado de São Paulo

Estampa temporal na memória de reconhecimento em estudantes universitários

Several studies have shown that there is a circadian modulation of explicit memory. This modulation can occur independently in each one of the mnemonic processes. The aim of this study was to evaluate the influence of time of training on short-term memory (STM) and long-term memory (LTM), using a recognition task. Moreover, a possible circadian modulation in retrieving was investigated when this process matched the acquisition hour (time stamp). The chronotype variable was also considered. Fifty-seven undergraduate students aging between 18 and 25 years (21,72 ± 2,14; 28 ♂) participated in this study. In the training phase (acquisition) the subjects heard a ten word list. Following this, they answered a recognition test to evaluate STM and one week later they answered a recognition test to evaluate LTM. In each chronotype, the subjects were divided in groups according to the training hour, part of them in the morning and the other in the afternoon. One week later some of the subjects in each group underwent LTM testing in the morning and others in the afternoon. When the subjects performances were analyzed together, independently of the chronotypes, a training hour effect was found in the LTM. The subjects trained in the afternoon had better performance. No time of day effect was found in the STM and in retrieving from the LTM. However, the morning types who were trained and tested in the same hour had a better performance in the LTM when compared to morning types trained and tested in different hours. This effect did not occur when the other chronotypes were analyzed. The circadian modulation seems to occur at least in two different ways. First, there is a circadian modulation in the acquisition/consolidation processes, with a better performance occuring in the afternoon. Secondly, there is a modulation in the retrieval mnemonic process, called time stamp phenomenon. This phenomenon, that occurred in the morning types, is showed for the first time in humans

Uma Análise de métodos de distriubuição de atributos em comitês de classificadores

The objective of the researches in artificial intelligence is to qualify the computer to execute functions that are performed by humans using knowledge and reasoning. This work was developed in the area of machine learning, that it s the study branch of artificial intelligence, being related to the project and development of algorithms and techniques capable to allow the computational learning. The objective of this work is analyzing a feature selection method for ensemble systems. The proposed method is inserted into the filter approach of feature selection method, it s using the variance and Spearman correlation to rank the feature and using the reward and punishment strategies to measure the feature importance for the identification of the classes. For each ensemble, several different configuration were used, which varied from hybrid (homogeneous) to non-hybrid (heterogeneous) structures of ensemble. They were submitted to five combining methods (voting, sum, sum weight, multiLayer Perceptron and naïve Bayes) which were applied in six distinct database (real and artificial). The classifiers applied during the experiments were k- nearest neighbor, multiLayer Perceptron, naïve Bayes and decision tree. Finally, the performance of ensemble was analyzed comparatively, using none feature selection method, using a filter approach (original) feature selection method and the proposed method. To do this comparison, a statistical test was applied, which demonstrate that there was a significant improvement in the precision of the ensembles

Contribuições para a detecção e identificação de faltas em inversores Multiníveis

This work presents contributions in the detection and identication of faults in multilevel inverters through the study of the converters behavior under these operation conditions. Basically, the approached fault consists of an open-circuit in any switch of a three-level clamped diode inverter. The converter operation is characterized in the pre and post-fault states. A wave form behavior analysis of the pole voltage, phase current and dc-bus current is also done, which highlights characteristics that allow the detection of failure and, even, under favorable conditions, the identication of the faulty device. A compensation strategy of the approached fault (open-switch) is also investigated with the purpose of maintaining the driving system operational when a failure occurs. The proposed topology uses SCRs in parallel with the internal switches of the inverter, which allows, in some occasions, the full utilization of the dc-bus

Protótipo de rastreador solar de um eixo baseado em microcontrolador

The increase in the efficiency of photo-voltaic systems has been the object of various studies the past few years. One possible way to increase the power extracted by a photovoltaic panel is the solar tracking, performing its movement in order to follow the sun’s path. One way to activate the tracking system is using an electric induction motor, which should have sufficient torque and low speed, ensuring tracking accuracy. With the use of voltage source inverters and logic devices that generate the appropriate switching is possible to obtain the torque and speed required for the system to operate. This paper proposes the implementation of a angular position sensor and a driver to be applied in solar tracker built at a Power Electronics and Renewable Energies Laboratory, located in UFRN. The speed variation of the motor is performed via a voltage source inverter whose PWM command to actuate their keys will be implemented in an FPGA (Field Programmable Gate Array) device and a TM4C microcontroller. A platform test with an AC induction machine of 1.5 CV was assembled for the comparative testing. The angular position sensor of the panel is implemented in a ATMega328 microcontroller coupled to an accelerometer, commanded by an Arduino prototyping board. The solar position is also calculated by the microcontroller from the geographic coordinates of the site where it was placed, and the local time and date obtained from an RTC (Real-Time Clock) device. A prototype of a solar tracker polar axis moved by a DC motor was assembled to certify the operation of the sensor and to check the tracking efficiency.