Sistema Híbrido de Inferência Baseado em Análise de Componentes Principais e Redes Neurais Artificiais Aplicado a Plantas de Processamento de Gás Natural

Nowadays, where the market competition requires products with better quality and a constant search for cost savings and a better use of raw materials, the research for more efficient control strategies becomes vital. In Natural Gas Processin Units (NGPUs), as in the most chemical processes, the quality control is accomplished through their products composition. However, the chemical composition analysis has a long measurement time, even when performed by instruments such as gas chromatographs. This fact hinders the development of control strategies to provide a better process yield. The natural gas processing is one of the most important activities in the petroleum industry. The main economic product of a NGPU is the liquefied petroleum gas (LPG). The LPG is ideally composed by propane and butane, however, in practice, its composition has some contaminants, such as ethane and pentane. In this work is proposed an inferential system using neural networks to estimate the ethane and pentane mole fractions in LPG and the propane mole fraction in residual gas. The goal is to provide the values of these estimated variables in every minute using a single multilayer neural network, making it possibly to apply inferential control techniques in order to monitor the LPG quality and to reduce the propane loss in the process. To develop this work a NGPU was simulated in HYSYS R software, composed by two distillation collumns: deethanizer and debutanizer. The inference is performed through the process variables of the PID controllers present in the instrumentation of these columns. To reduce the complexity of the inferential neural network is used the statistical technique of principal component analysis to decrease the number of network inputs, thus forming a hybrid inferential system. It is also proposed in this work a simple strategy to correct the inferential system in real-time, based on measurements of the chromatographs which may exist in process under study

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

Utilização de redes neurais artificiais para detecção e diagnóstico de falhas

In a real process, all used resources, whether physical or developed in software, are subject to interruptions or operational commitments. However, in situations in which operate critical systems, any kind of problem may bring big consequences. Knowing this, this paper aims to develop a system capable to detect the presence and indicate the types of failures that may occur in a process. For implementing and testing the proposed methodology, a coupled tank system was used as a study model case. The system should be developed to generate a set of signals that notify the process operator and that may be post-processed, enabling changes in control strategy or control parameters. Due to the damage risks involved with sensors, actuators and amplifiers of the real plant, the data set of the faults will be computationally generated and the results collected from numerical simulations of the process model. The system will be composed by structures with Artificial Neural Networks, trained in offline mode using Matlab®

Separação cega de fontes lineares e não lineares usando algoritmo genético, redes neurais artificiais RBF e negentropia de Rényi como medida de independência

Conventional methods to solve the problem of blind source separation nonlinear, in general, using series of restrictions to obtain the solution, often leading to an imperfect separation of the original sources and high computational cost. In this paper, we propose an alternative measure of independence based on information theory and uses the tools of artificial intelligence to solve problems of blind source separation linear and nonlinear later. In the linear model applies genetic algorithms and Rényi of negentropy as a measure of independence to find a separation matrix from linear mixtures of signals using linear form of waves, audio and images. A comparison with two types of algorithms for Independent Component Analysis widespread in the literature. Subsequently, we use the same measure of independence, as the cost function in the genetic algorithm to recover source signals were mixed by nonlinear functions from an artificial neural network of radial base type. Genetic algorithms are powerful tools for global search, and therefore well suited for use in problems of blind source separation. Tests and analysis are through computer simulations

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

Redes neurais artificiais no ambiente de redes industriais foundation fieldbus usando blocos funcionais padrões

Industrial automation networks is in focus and is gradually replacing older architectures of systems used in automation world. Among existing automation networks, most prominent standard is the Foundation Fieldbus (FF). This particular standard was chosen for the development of this work thanks to its complete application layer specification and its user interface, organized as function blocks and that allows interoperability among different vendors' devices. Nowadays, one of most seeked solutions on industrial automation are the indirect measurements, that consist in infering a value from measures of other sensors. This can be made through implementation of the so-called software sensors. One of the most used tools in this project and in sensor implementation are artificial neural networks. The absence of a standard solution to implement neural networks in FF environment makes impossible the development of a field-indirect-measurement project, besides other projects involving neural networks, unless a closed proprietary solution is used, which dos not guarantee interoperability among network devices, specially if those are from different vendors. In order to keep the interoperability, this work's goal is develop a solution that implements artificial neural networks in Foundation Fieldbus industrial network environment, based on standard function blocks. Along the work, some results of the solution's implementation are also presented

Predição da incrustação em um trocador de calor baseada em redes neurais artificiais

A serious problem that affects an oil refinery s processing units is the deposition of solid particles or the fouling on the equipments. These residues are naturally present on the oil or are by-products of chemical reactions during its transport. A fouled heat exchanger loses its capacity to adequately heat the oil, needing to be shut down periodically for cleaning. Previous knowledge of the best period to shut down the exchanger may improve the energetic and production efficiency of the plant. In this work we develop a system to predict the fouling on a heat exchanger from the Potiguar Clara Camarão Refinery, based on data collected in a partnership with Petrobras. Recurrent Neural Networks are used to predict the heat exchanger s flow in future time. This variable is the main indicator of fouling, because its value decreases gradually as the deposits on the tubes reduce their diameter. The prediction could be used to tell when the flow will have decreased under an acceptable value, indicating when the exchanger shutdown for cleaning will be needed

Utilização de análise multivariada e redes neurais artificiais na determinação do comportamento de colonização de populações de macrófitas aquáticas no reservatório de Santana

As análises de agrupamento e de componentes principais e as redes neurais artificiais foram utilizadas na determinação de padrões de comportamento das populações de macrófitas aquáticas que colonizaram o reservatório de Santana, Piraí-RJ, durante o ano de 2004. As análises de agrupamento dividiram o comportamento das populações durante o ano em dois grupos distintos, apresentando um padrão no primeiro semestre que difere daquele observado no segundo semestre do ano. A análise de componentes principais demonstrou que esse comportamento da comunidade (grupo de populações) é influenciado principalmente pelas espécies S. montevidensis, Heteranthera reniformis, Ludwigia sp., Rhynchospora aurea, C. iria, C. ferax e Aeschynomene denticulata no primeiro grupo e por Echinochloa polystachya, Polygonum lapathifolium, Alternanthera phyloxeroides, Pistia stratiotes, Eichhornia azurea, Brachiaria arrecta e Oxyscarium cubense no segundo grupo. As redes neurais artificiais agruparam as populações de macrófitas aquáticas em nove grupos, conforme sua densidade nos diferentes meses do ano. A aplicação da análise de componentes principais (ACP) nos valores de frequência das populações presentes nos primeiros três grupos de Kohonen permitiu discriminar três grupos de meses, cujas populações apresentaram características diferentes de colonização. A aplicação das redes neurais artificiais permitiu melhor discriminação dos meses e das espécies que compõem as comunidades correspondentes, quando utilizada a análise de componentes principais.

Modelagem de Superfícies Seletivas de Freqüência e Antenas de Microfita utilizando Redes Neurais Artificiais

This work has as main objective the application of Artificial Neural Networks, ANN, in the resolution of problems of RF /microwaves devices, as for example the prediction of the frequency response of some structures in an interest region. Artificial Neural Networks, are presently a alternative to the current methods of analysis of microwaves structures. Therefore they are capable to learn, and the more important to generalize the acquired knowledge, from any type of available data, keeping the precision of the original technique and adding the low computational cost of the neural models. For this reason, artificial neural networks are being increasily used for modeling microwaves devices. Multilayer Perceptron and Radial Base Functions models are used in this work. The advantages/disadvantages of these models and the referring algorithms of training of each one are described. Microwave planar devices, as Frequency Selective Surfaces and microstrip antennas, are in evidence due the increasing necessities of filtering and separation of eletromagnetic waves and the miniaturization of RF devices. Therefore, it is of fundamental importance the study of the structural parameters of these devices in a fast and accurate way. The presented results, show to the capacities of the neural techniques for modeling both Frequency Selective Surfaces and antennas

Controle inteligente de sistemas eletroidráulicos utilizando redes neurais artificiais

This work describes the development of a nonlinear control strategy for an electro-hydraulic actuated system. The system to be controlled is represented by a third order ordinary differential equation subject to a dead-zone input. The control strategy is based on a nonlinear control scheme, combined with an artificial intelligence algorithm, namely, the method of feedback linearization and an artificial neural network. It is shown that, when such a hard nonlinearity and modeling inaccuracies are considered, the nonlinear technique alone is not enough to ensure a good performance of the controller. Therefore, a compensation strategy based on artificial neural networks, which have been notoriously used in systems that require the simulation of the process of human inference, is used. The multilayer perceptron network and the radial basis functions network as well are adopted and mathematically implemented within the control law. On this basis, the compensation ability considering both networks is compared. Furthermore, the application of new intelligent control strategies for nonlinear and uncertain mechanical systems are proposed, showing that the combination of a nonlinear control methodology and artificial neural networks improves the overall control system performance. Numerical results are presented to demonstrate the efficacy of the proposed control system

Desenvolvimento de perfis aerodinâmicos a partir de suas características utilizando redes neurais artificiais

One of the current major concerns in engineering is the development of aircrafts that have low power consumption and high performance. So, airfoils that have a high value of Lift Coefficient and a low value for the Drag Coefficient, generating a High-Efficiency airfoil are studied and designed. When the value of the Efficiency increases, the aircraft s fuel consumption decreases, thus improving its performance. Therefore, this work aims to develop a tool for designing of airfoils from desired characteristics, as Lift and Drag coefficients and the maximum Efficiency, using an algorithm based on an Artificial Neural Network (ANN). For this, it was initially collected an aerodynamic characteristics database, with a total of 300 airfoils, from the software XFoil. Then, through the software MATLAB, several network architectures were trained, between modular and hierarchical, using the Back-propagation algorithm and the Momentum rule. For data analysis, was used the technique of cross- validation, evaluating the network that has the lowest value of Root Mean Square (RMS). In this case, the best result was obtained for a hierarchical architecture with two modules and one layer of hidden neurons. The airfoils developed for that network, in the regions of lower RMS, were compared with the same airfoils imported into the software XFoil

Tensão superficial dinâmica e ângulo de contato de soluções aquosas com surfatantes em superfícies artificiais e naturais

O trabalho objetivou avaliar o efeito de surfatantes em soluções aquosas sobre a tensão superficial dinâmica e ângulo de contato das gotas em diferentes superfícies: artificiais (lâmina de vidro e de óxido de alumínio) e naturais (superfícies adaxiais de folhas de Euphorbia heterophylla, Ipomoea grandifolia e Brachiaria plantaginea). Seis formulações de surfatantes (Antideriva®; Uno®; Pronto 3®; Li-700®; Supersil® e Silwet L-77®), respectivamente nas doses recomendadas do produto comercial (0,050; 0,025; 0,100; 0,250; 0,100 e 0,100 % v v-1) e o dobro delas, foram avaliadas em soluções aquosas. A tensão superficial dinâmica e o ângulo de contato formado sobre as superfícies naturais foram medidos por tensiômetro. Os ângulos de contato formados pelas gotas nas superfícies artificiais foram obtidos por análise de imagens capturadas por uma câmera digital. Os surfatantes influenciam nas propriedades físico-químicas de soluções aquosas. As soluções contendo os surfatantes Silwet L-77® e Supersil®; nas doses de 0,100 e 0,200% v v-1; proporcionaram maiores reduções na tensão superficial dinâmica e menores ângulos de contato das gotas sobre as superfícies artificiais e naturais. Os surfatantes organossiliconados em solução aquosa foram mais eficientes na redução da tensão superficial e proporcionaram maior molhamento de superfícies natural e artificial. em alvos naturais, essas propriedades obtidas com organossiliconados são dependentes das características de superfície das espécies vegetais.

Estrutura genética de Chromis multilineata (Guichenot, 1853) (Perciformes Pomacentridae) na costa NE do Brasil e ilhas oceânicas: evidências de um passado evolutivo instável.

The fauna of Brazilian reef fishes comprises approximately 320 species distributed along the coast of the mainland and islands ocean. Little is known about the levels of connectivity between their populations, but has been given the interest in the relations between the offshore and the islands of the Brazil, in a biogeographical perspective. The oceanic islands Brazilian hosting a considerable number of endemic species, which are locally abundant, and divide a substantial portion of its reef fish fauna with the Western Atlantic. Among the richest families of reef fish in species are Pomacentridae. This study analyzed through analysis of sequences of the mitochondrial DNA control region (D-loop), the standards-breeding population of C. Multilineata in different areas of the NE coast of Brazil, involving both oceanic islands (Fernando de Noronha Archipelago and of St. Peter and St. Paul) and continental shelf (RN and BA). To this aim, partial sequences were used in the region HVR1 of mtDNA (312pb). The population structure and parameters for the estimates of genetic variability, molecular variance (AMOVA), estimation of the index for fixing (FST) and number of migrants were determined. The phylogenetic relationships between the populations were estimated using neighbor-joining (NJ) method. A group of Bayesian analysis was used to verify population structure, according to haplotype frequency of each individual. The genetic variability of populations was extremely high. The populations sampled show moderate genetic structure, with a higher degree of genetic divergence being observed for the sample of the Archipelago of St. Peter and St. Paul. At smaller geographical scale, the sample of Rio Grande do Norte and the Archipelago of Fernando de Noronha do not have genetic differentiation. Three moderately differentiated population groups were identified: a population group (I), formed by the Rio Grande do Norte (I') and the archipelago of Fernando de Noronha (I''), and two other different groups formed by the island population of the archipelago of Saint Peter and St. Paul (II) and Bahia (III). The genetic patterns found suggest that the species has suffered a relatively recent radiation favoring the absence of shared haplotypes. C. multilineata seems to constitute a relatively homogenous population along the West Atlantic coast, with evidence of a moderate population genetic structure in relation to the Archipelago of St. Peter and St. Paul. These data supports the importance of the dispersal larvae by marine current and the interpopulation similarity this species.

Estudo da estabilidade térmica de adoçantes naturais e artificiais

Sweeteners provide a pleasant sensation of sweetness that helps the sensory quality of the human diet, can be divided into natural sweeteners such as fructose, galactose, glucose, lactose and sucrose, and articial sweeteners such as aspartame, cyclamate and saccharin. This work aimed to study the thermal stability of natural and artificial sweeteners in atmospheres of nitrogen and syntetic air using thermogravimetry (TG), derivative thermogravimetry (DTG), Differential Thermal Analysis (DTA) and Differential Scanning Calorimetry (DSC). Among the natural sweeteners analyzed showed higher thermal stability for the lactose and sucrose, which showed initial decomposition temperatures near 220 ° C, taking advantage of the lactose has a higher melting point (213 ° C) compared to sucrose (191 ° C). The lower thermal stability was observed for fructose, it has the lowest melting point (122 °C) and the lower initial decomposition temperature (170 °C). Of the artificial sweeteners studied showed higher thermal stability for sodium saccharin, which had the highest melting point (364 ° C) as well as the largest initial decomposition temperature (466 ° C under nitrogen and 435 ° C in air). The lower thermal stability was observed for aspartame, which showed lower initial decomposition temperature (158 ° C under nitrogen and 170 ° C under air). For commercial sweeteners showed higher thermal stability for the sweeteners L and C, which showed initial temperature of thermal decomposition near 220 ° C and melting points near 215 ° C. The lower thermal stability was observed for the sweetener P, which showed initial decomposition temperature at 160 ° C and melting point of 130 °C. Sweeteners B, D, E, I, J, N and O had low thermal stability, with the initial temperature of decomposition starts near 160 °C, probably due to the presence of aspartame, even if they have as the main constituent of the lactose, wich is the most stable of natural sweeteners. According to the results we could also realize that all commercial sweeteners are in its composition by at least a natural sweeteners and are always found in large proportions, and lactose is the main constituent of 60% of the total recorded

Desenvolvimento de metodologia capaz de detectar e quantificar misturas de corantes em sucos artificiais em pó

Foi desenvolvido um método para detectar e quantificar misturas de corantes em sucos artificiais em pó fabricados no Brasil, de diferentes marcas e sabores. Foram estudados 6 corantes artificiais: amarelo tartrazina, amarelo crepúsculo, vermelho ponceau 4R, vermelho bordeaux S, vermelho 40 e azul brilhante presentes de forma unitária ou em misturas nos sucos com sabores laranja, tangerina, maracujá, abacaxi, limão e uva. A identificação dos corantes nas amostras foi feita através da comparação com os espectros dos padrões, utilizando-se a análise por infravermelho médio e pelos respectivos valores de absorção máxima nos comprimentos de onda relativos aos padrões e valores de referência na literatura. Também foram estudados os perfis de decomposição térmica por termogravimetria, termogravimetria derivada e calorimetria diferencial exploratória dos corantes e dos sucos em pó, sendo determinados os teores de umidade, de matéria orgânica e de cinzas. O teor de umidade encontrado não ultrapassou 4% para todas as amostras de suco analisadas. Com relação ao teor de matéria orgânica obteve-se para 57% dos sucos analisados um teor médio de 51,3% e para 43% das outras amostras obteve-se uma média de 67,2 %. Os resultados obtidos para o teor de cinzas indicaram que 29% das amostras apresentaram um teor de 26,7% para esse parâmetro enquanto 71% das amostras apresentaram um teor de cinzas de 46,4%. Os resultados obtidos por análise térmica mostraram-se adequados considerando-se que para obter os resultados pelo método tradicional há um investimento maior de tempo, de pessoal envolvido e de material, além da proteção ao meio ambiente. Para a análise por espectroscopia de absorção molecular foi proposta uma equação simplificada para a determinação de cada corante na mistura utilizando-se a lei de Beer. Para validação, empregou-se a espectroscopia de absorção molecular no visível, onde foi investigada a influência dos interferentes (TiO2 e açúcar) presentes nas amostras de sucos, os testes de fotodegradação e a avaliação do efeito do pH. Para quantificação tomou-se como referência 512 amostras sintéticas contendo um e dois corantes (1,5625 a 25,000 mg L-1) para obtenção das curvas analíticas que foram aplicadas à análise dos sucos em pó. Os resultados indicaram que o teor máximo do amarelo crepúsculo foi encontrado nos sucos com os sabores laranja, tangerina e manga que correspondeu a 25,6% da ingestão diária aceitável (para ser ultrapassada corresponderia a ingestão de 4 copos). O teor máximo encontrado para o amarelo tartrazina nos sucos foi para o sabor maracujá que correspondeu a 8,5% da ingestão diária aceitável, (para ser alcançado corresponderia a ingestão de 12 copos). O método proposto foi testado e validado com sucesso para amostras de sucos em pó sendo de simples execução e de rapidez na obtenção dos resultados