Técnicas de avaliação da confiabilidade em estruturas de concreto armado

Neste trabalho é dado ênfase à inclusão das incertezas na avaliação do comportamento estrutural, objetivando uma melhor representação das características do sistema e uma quantificação do significado destas incertezas no projeto. São feitas comparações entre as técnicas clássicas existentes de análise de confiabilidade, tais como FORM, Simulação Direta Monte Carlo (MC) e Simulação Monte Carlo com Amostragem por Importância Adaptativa (MCIS), e os métodos aproximados da Superfície de Resposta( RS) e de Redes Neurais Artificiais(ANN). Quando possível, as comparações são feitas salientando- se as vantagens e inconvenientes do uso de uma ou de outra técnica em problemas com complexidades crescentes. São analisadas desde formulações com funções de estado limite explícitas até formulações implícitas com variabilidade espacial de carregamento e propriedades dos materiais, incluindo campos estocásticos. É tratado, em especial, o problema da análise da confiabilidade de estruturas de concreto armado incluindo o efeito da variabilidade espacial de suas propriedades. Para tanto é proposto um modelo de elementos finitos para a representação do concreto armado que incorpora as principais características observadas neste material. Também foi desenvolvido um modelo para a geração de campos estocásticos multidimensionais não Gaussianos para as propriedades do material e que é independente da malha de elementos finitos, assim como implementadas técnicas para aceleração das avaliações estruturais presentes em qualquer das técnicas empregadas. Para o tratamento da confiabilidade através da técnica da Superfície de Resposta, o algoritmo desenvolvido por Rajashekhar et al(1993) foi implementado. Já para o tratamento através de Redes Neurais Artificias, foram desenvolvidos alguns códigos para a simulação de redes percéptron multicamada e redes com função de base radial e então implementados no algoritmo de avaliação de confiabilidade desenvolvido por Shao et al(1997). Em geral, observou-se que as técnicas de simulação tem desempenho bastante baixo em problemas mais complexos, sobressaindo-se a técnica de primeira ordem FORM e as técnicas aproximadas da Superfície de Resposta e de Redes Neurais Artificiais, embora com precisão prejudicada devido às aproximações presentes.

ONNIS-GI: uma rede neural oscilatória para segmentação de imagens implementada em arquitetura maciçamente paralela

A presente tese apresenta a concepção de uma rede neural oscilatória e sua realização em arquitetura maciçamente paralela, a qual é adequada à implementação de chips de visão digitais para segmentação de imagens. A rede proposta, em sua versão final, foi denominada ONNIS-GI (Oscillatory Neural Network for Image Segmentation with Global Inhibition) e foi inspirada em uma rede denominada LEGION (Locally Excitatory Globally Inhibitory Oscillator Network), também de concepção recente. Inicialmente, é apresentada uma introdução aos procedimentos de segmentação de imagens, cujo objetivo é o de situar e enfatizar a importância do tema abordado dentro de um contexto abrangente, o qual inclui aplicações de visão artificial em geral. Outro aspecto abordado diz respeito à utilização de redes neurais artificiais em segmentação de imagens, enfatizando as denominadas redes neurais oscilatórias, as quais têm apresentado resultados estimulantes nesta área. A implementação de chips de visão, integrando sensores de imagens e redes maciçamente paralelas de processadores, é também abordada no texto, ressaltando o objetivo prático da nova rede neural proposta. No estudo da rede LEGION, são apresentados resultados de aplicações originais desenvolvidas em segmentação de imagens, nos quais é verificada sua propriedade de separação temporal dos segmentos. A versão contínua da rede, um arranjo paralelo de neurônios baseados em equações diferenciais, apresenta elevada complexidade computacional para implementação em hardware digital e muitos parâmetros, com procedimento de ajuste pouco prático. Por outro lado, sua arquitetura maciçamente paralela apresenta-se particularmente adequada à implementação de chips de visão analógicos com capacidade de segmentação de imagens. Com base nos bons resultados obtidos nas aplicações desenvolvidas, é proposta uma nova rede neural, em duas versões, ONNIS e ONNIS-GI, as quais suplantam a rede LEGION em diversos aspectos relativos à implementação prática. A estrutura dos elementos de processamento das duas versões da rede, sua implementação em arquitetura maciçamente paralela e resultados de simulações e implementações em FPGA são apresentados, demonstrando a viabilidade da proposta. Como resultado final, conclui-se que a rede ONNIS-GI apresenta maior apelo de ordem prática, sendo uma abordagem inovadora e promissora na solução de problemas de segmentação de imagens, possuindo capacidade para separar temporalmente os segmentos encontrados e facilitando a posterior identificação dos mesmos. Sob o ponto de vista prático, a nova rede pode ser utilizada para implementar chips de visão digitais com arquitetura maciçamente paralela, explorando a velocidade de tais topologias e apresentando também flexibilidade para implementação de procedimentos de segmentação de imagens mais sofisticados.

Application of multivariable control using artificial neural networks in a debutanizer distillation column

LOPES, Jose Soares Batista et al. Application of multivariable control using artificial neural networks in a debutanizer distillation column.In: INTERNATIONAL CONGRESS OF MECHANICAL ENGINEERING - COBEM, 19, 5-9 nov. 2007, Brasilia. Anais... Brasilia, 2007

Controle preditivo neural aplicado à processos petroquímicos

A pesquisa tem como objetivo desenvolver uma estrutura de controle preditivo neural, com o intuito de controlar um processo de pH, caracterizado por ser um sistema SISO (Single Input - Single Output). O controle de pH é um processo de grande importância na indústria petroquímica, onde se deseja manter constante o nível de acidez de um produto ou neutralizar o afluente de uma planta de tratamento de fluidos. O processo de controle de pH exige robustez do sistema de controle, pois este processo pode ter ganho estático e dinâmica nãolineares. O controlador preditivo neural envolve duas outras teorias para o seu desenvolvimento, a primeira referente ao controle preditivo e a outra a redes neurais artificiais (RNA s). Este controlador pode ser dividido em dois blocos, um responsável pela identificação e outro pelo o cálculo do sinal de controle. Para realizar a identificação neural é utilizada uma RNA com arquitetura feedforward multicamadas com aprendizagem baseada na metodologia da Propagação Retroativa do Erro (Error Back Propagation). A partir de dados de entrada e saída da planta é iniciado o treinamento offline da rede. Dessa forma, os pesos sinápticos são ajustados e a rede está apta para representar o sistema com a máxima precisão possível. O modelo neural gerado é usado para predizer as saídas futuras do sistema, com isso o otimizador calcula uma série de ações de controle, através da minimização de uma função objetivo quadrática, fazendo com que a saída do processo siga um sinal de referência desejado. Foram desenvolvidos dois aplicativos, ambos na plataforma Builder C++, o primeiro realiza a identificação, via redes neurais e o segundo é responsável pelo controle do processo. As ferramentas aqui implementadas e aplicadas são genéricas, ambas permitem a aplicação da estrutura de controle a qualquer novo processo

A Learning Function for Parameter Reduction in Spiking Neural Networks with Radial Basis Function

Spiking neural networks - networks that encode information in the timing of spikes - are arising as a new approach in the artificial neural networks paradigm, emergent from cognitive science. One of these new models is the pulsed neural network with radial basis function, a network able to store information in the axonal propagation delay of neurons. Learning algorithms have been proposed to this model looking for mapping input pulses into output pulses. Recently, a new method was proposed to encode constant data into a temporal sequence of spikes, stimulating deeper studies in order to establish abilities and frontiers of this new approach. However, a well known problem of this kind of network is the high number of free parameters - more that 15 - to be properly configured or tuned in order to allow network convergence. This work presents for the first time a new learning function for this network training that allow the automatic configuration of one of the key network parameters: the synaptic weight decreasing factor.

Identificação fuzzy-multimodelos para sistemas não lineares

This paper presents a new multi-model technique of dentification in ANFIS for nonlinear systems. In this technique, the structure used is of the fuzzy Takagi-Sugeno of which the consequences are local linear models that represent the system of different points of operation and the precursors are membership functions whose adjustments are realized by the learning phase of the neuro-fuzzy ANFIS technique. The models that represent the system at different points of the operation can be found with linearization techniques like, for example, the Least Squares method that is robust against sounds and of simple application. The fuzzy system is responsible for informing the proportion of each model that should be utilized, using the membership functions. The membership functions can be adjusted by ANFIS with the use of neural network algorithms, like the back propagation error type, in such a way that the models found for each area are correctly interpolated and define an action of each model for possible entries into the system. In multi-models, the definition of action of models is known as metrics and, since this paper is based on ANFIS, it shall be denominated in ANFIS metrics. This way, ANFIS metrics is utilized to interpolate various models, composing a system to be identified. Differing from the traditional ANFIS, the created technique necessarily represents the system in various well defined regions by unaltered models whose pondered activation as per the membership functions. The selection of regions for the application of the Least Squares method is realized manually from the graphic analysis of the system behavior or from the physical characteristics of the plant. This selection serves as a base to initiate the linear model defining technique and generating the initial configuration of the membership functions. The experiments are conducted in a teaching tank, with multiple sections, designed and created to show the characteristics of the technique. The results from this tank illustrate the performance reached by the technique in task of identifying, utilizing configurations of ANFIS, comparing the developed technique with various models of simple metrics and comparing with the NNARX technique, also adapted to identification

Modelagem e medições de ondas de rádio para predição de perda de propagação em ambientes urbanos

In this dissertation new models of propagation path loss predictions are proposed by from techniques of optimization recent and measures of power levels for the urban and suburban areas of Natal, city of Brazilian northeast. These new proposed models are: (i) a statistical model that was implemented based in the addition of second-order statistics for the power and the altimetry of the relief in model of linear losses; (ii) a artificial neural networks model used the training of the algorithm backpropagation, in order to get the equation of propagation losses; (iii) a model based on the technique of the random walker, that considers the random of the absorption and the chaos of the environment and than its unknown parameters for the equation of propagation losses are determined through of a neural network. The digitalization of the relief for the urban and suburban areas of Natal were carried through of the development of specific computational programs and had been used available maps in the Statistics and Geography Brazilian Institute. The validations of the proposed propagation models had been carried through comparisons with measures and propagation classic models, and numerical good agreements were observed. These new considered models could be applied to any urban and suburban scenes with characteristic similar architectural to the city of Natal

Especificação de um bloco funcional implementando rede neural para redes industriais foundations fieldbus

This work proposes the specification of a new function block according to Foundation Fieldbus standards. The new block implements an artificial neural network, which may be useful in process control applications. The specification includes the definition of a main algorithm, that implements a neural network, as well as the description of some accessory functions, which provide safety characteristics to the block operation. Besides, it also describes the block attributes emphasizing its parameters, which constitute the block interfaces. Some experimental results, obtained from an artificial neural network implementation using actual standard functional blocks on a laboratorial FF network, are also shown, in order to demonstrate the possibility and also the convenience of integrating a neural network to Fieldbus devices

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

Contribuição para o estudo do embarque de uma rede neural artificial em field programmable gate array (FPGA)

This study shows the implementation and the embedding of an Artificial Neural Network (ANN) in hardware, or in a programmable device, as a field programmable gate array (FPGA). This work allowed the exploration of different implementations, described in VHDL, of multilayer perceptrons ANN. Due to the parallelism inherent to ANNs, there are disadvantages in software implementations due to the sequential nature of the Von Neumann architectures. As an alternative to this problem, there is a hardware implementation that allows to exploit all the parallelism implicit in this model. Currently, there is an increase in use of FPGAs as a platform to implement neural networks in hardware, exploiting the high processing power, low cost, ease of programming and ability to reconfigure the circuit, allowing the network to adapt to different applications. Given this context, the aim is to develop arrays of neural networks in hardware, a flexible architecture, in which it is possible to add or remove neurons, and mainly, modify the network topology, in order to enable a modular network of fixed-point arithmetic in a FPGA. Five synthesis of VHDL descriptions were produced: two for the neuron with one or two entrances, and three different architectures of ANN. The descriptions of the used architectures became very modular, easily allowing the increase or decrease of the number of neurons. As a result, some complete neural networks were implemented in FPGA, in fixed-point arithmetic, with a high-capacity parallel processing

Desacoplamento de um gerador síncrono através de um controle adaptativo por modelo de referência baseado em funções de Base radial

An alternative nonlinear technique for decoupling and control is presented. This technique is based on a RBF (Radial Basis Functions) neural network and it is applied to the synchronous generator model. The synchronous generator is a coupled system, in other words, a change at one input variable of the system, changes more than one output. The RBF network will perform the decoupling, separating the control of the following outputs variables: the load angle and flux linkage in the field winding. This technique does not require knowledge of the system parameters and, due the nature of radial basis functions, it shows itself stable to parametric uncertainties, disturbances and simpler when it is applied in control. The RBF decoupler is designed in this work for decouple a nonlinear MIMO system with two inputs and two outputs. The weights between hidden and output layer are modified online, using an adaptive law in real time. The adaptive law is developed by Lyapunov s Method. A decoupling adaptive controller uses the errors between system outputs and model outputs, and filtered outputs of the system to produce control signals. The RBF network forces each outputs of generator to behave like reference model. When the RBF approaches adequately control signals, the system decoupling is achieved. A mathematical proof and analysis are showed. Simulations are presented to show the performance and robustness of the RBF network

Análise de um controlador baseado no Jacobiano estimado da planta através de uma rede neural

This work presents an analysis of the control law based on an indirect hybrid scheme using neural network, initially proposed for O. Adetona, S. Sathanathan and L. H. Keel. Implementations of this control law, for a level plant of second order, was resulted an oscillatory behavior, even if the neural identifier has converged. Such results had motivated the investigation of the applicability of that law. Starting from that, had been made stability mathematical analysis and several implementations, with simulated plants and with real plants, for analyze the problem. The analysis has been showed the law was designed being despised some components of dynamic of the plant to be controlled. Thus, for plants that these components have a significant influence in its dynamic, the law tends to fail

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

Multidimensional polynomial powers of sigmoid (PPS) Wavelet neural networks

Wavelet functions have been used as the activation function in feedforward neural networks. An abundance of R&D has been produced on wavelet neural network area. Some successful algorithms and applications in wavelet neural network have been developed and reported in the literature. However, most of the aforementioned reports impose many restrictions in the classical backpropagation algorithm, such as low dimensionality, tensor product of wavelets, parameters initialization, and, in general, the output is one dimensional, etc. In order to remove some of these restrictions, a family of polynomial wavelets generated from powers of sigmoid functions is presented. We described how a multidimensional wavelet neural networks based on these functions can be constructed, trained and applied in pattern recognition tasks. As an example of application for the method proposed, it is studied the exclusive-or (XOR) problem.