Orientador: Mauro Hugo Mathias / Banca: Alvaro Manoel Souza Soares / Banca: José Elias Tomazini / Banca: Francisco Carlos Parquet Bizarria / Banca: Carlos Henrique Netto Lahoz / Resumo: Um importante aspecto no processo produtivo é proporcionar o funcionamento das máquinas o maior tempo possível sem o comprometimento na qualidade final do produto. Nesse sentido, a utilização de uma política de manutenção adequada se torna necessária para o monitoramento do desgaste dos componentes das máquinas a fim de aumentar o tempo de sua utilização sem comprometer a qualidade do produto. A manutenção baseada em condição se apresenta como a abordagem mais apropriada para esse controle. Dentre as diversas abordagens utilizadas para o desenvolvimento de programas para esse tipo de manutenção, as técnicas baseadas em Inteligência Artificial vêm se destacando no que diz respeito ao seu desempenho. Diante desse contexto, essa tese propõe uma Rede Neural Artificial, a qual, devidamente parametrizada, possibilita sua aplicação tanto para análise de vibrações quanto análise de partículas de desgaste. Para tanto, foi implementado um protótipo denominado NEURALNET-CBM, subdividido em dois módulos, Vibrações e Partículas. Os resultados dos testes mostram a efetividade da rede proposta, com um índice de acerto acima de 90% na classificação e identificação de defeitos e partículas de desgaste. / Abstract: An important aspect in the production process is to ensure the operability of a machine as long as possible without interfering on the final quality product. In this way, the use of a suitable maintenance policy is critical for monitoring the wear of the machine components in order to increase your useful life without any compromise of the product quality. The Condition-Based Maintenance is presented as the most appropriate approach for this control. Among several methods used to develop systems for this type of maintenance, techniques Artificial Intelligence has been standing out in relation their performance. Therefore, this thesis proposes a Artificial Neural Network, which, properly parameterized, it makes possible its application for both vibration and wear particle analysis. For this, we implemented a prototype named NEURALNET-CBM, divided into two modules: Vibration and Particle. The test results show the effectiveness of the proposed network, with accuracy rate greater than 90% in classifying and identification of defects and wear particles. / Doutor

Simulations are widely used for analysis and design of complex systems. Real-world complex systems are often too complex to be expressed with tractable mathematical formulations. Therefore simulations are often used instead of mathematical formulations because of their flexibility and ability to model real-world complex systems in some detail. Simulation models can often be complex and slow which lead to the development of simulation meta-models that are simpler and faster models of complex simulation models. Artificial neural networks (ANNs) have been studied for use as simulation meta-models with different results. This final year project further studies the use of ANNs as simulation meta-models by comparing the predictability of five different neural network architectures: feed-forward-, generalized feed-forward-, modular-, radial basis- and Elman artificial neural networks where the underlying simulation is of complex production system. The results where that all architectures gave acceptable results even though it can be said that Elman- and feed-forward ANNs performed the best of the tests conducted here. The difference in accuracy and generalization was considerably small.

Conselho Nacional de Desenvolvimento CientÃfico e TecnolÃgico / Estimar o recalque em estacas à um problema muito complexo, incerto e ainda nÃo totalmente compreendido, devido Ãs muitas incertezas associadas aos fatores que afetam a magnitude desta deformaÃÃo. As RNA sÃo ferramentas que funcionam analogamente ao cÃrebro humano, e sua unidade principal, o neurÃnio artificial, trabalha de maneira semelhante ao neurÃnio biolÃgico. Esta ferramenta alternativa vem sendo aplicada com sucesso em muitos problemas de engenharia geotÃcnica, podendo, portanto ser utilizadas como uma ferramentas alternativas para avaliar recalques em estacas isoladas. Nessa pesquisa as RNA utilizadas foram do tipo perceptron de mÃltiplas camadas, empregando um treinamento supervisionado utilizando o algoritmo de retropropagaÃÃo do erro. O modelo desenvolvido relaciona o recalque em estacas isoladas com as propriedades geomÃtricas das estacas (diÃmetro e comprimento), a estratigrafia e as caracterÃsticas de compacidade, ou consistÃncia dos solos por meio dos resultados obtidos nos ensaios SPT, e a carga atuante, obtidas em provas de carga realizadas em estacas hÃlice contÃnua, cravada metÃlica e escavada. O conjunto de aprendizagem foi composto por 1947 exemplos de entrada e saÃda. Com auxilio do programa QNET2000 foram treinadas e validadas vÃrias arquiteturas de redes neurais. ApÃs comparar o desempenho da curva carga x recalque elaborada com os recalques estimados pelo modelo proposto com a curva carga x recalque resultante da prova de carga estÃtica e com a curva carga x recalque gerada pelo emprego do programa comercial baseado em elementos finitos tridimensionais PLAXIS 3D Foundation, constatou-se que as RNA foram capazes de entender o comportamento das fundaÃÃes profundas do tipo estacas hÃlice contÃnua, escavada e cravada metÃlica, possibilitando dentre outras coisas, a definiÃÃo das cargas de trabalho e cargas limites nas estacas. / Predicting the settlement in deep foundation is a very complex, uncertain and not yet fully understood, due to the many uncertainties associated with factors that affect the magnitude of this deformation. Artificial Neural Network (ANN) is a tool that works similarly to the human brain, its main unit, the artificial neuron, works in a similar way to the biological neuron. This alternative tool has been successfully applied in many geotechnical engineering problems and can therefore be used as an alternative tool to evaluate the behavior of settlement in isolated piles. In this paper, the ANN used were the multilayer perceptron type, employing a supervised training that uses the error back propagation algorithm. The model developed relates settlement in isolated piles with the type and the geometrical properties of the piles (diameter and length), the stratigraphy and characteristics of compactness or consistency of soils by means of the SPT tests results, and the load applied, obtained in static pile load tests performed in continuous helix, steel driven and excavated pile types. The data set used to model consisted of 1.947 samples of input and output. QNET 2000 was the program used to assist the training and validation of various architectures of neural networks. The architecture formed by 10 nodes in the input layer, 28 neurons distributed in 4 intermediate layers and one neuron in the output layer, corresponding to the measured discharge for cutting (A10: 14:8:4:2:1) was the one that showed the best performance, with the correlation coefficient between the estimated settlements and settlements measured during the validation phase of 0.94, such value can be considered satisfactory when considering the prediction of a complex phenomenon. After comparing the performance of the applied load x settlement estimated by model proposed curve with the applied load x settlement measured in static pile load test curve and the applied load x settlement estimated by an elasto-plastic model thru numerical simulation, it was found that the ANN were able to understand the behavior of deep foundations of continuous helix, steel driven and excavated piles type, allowing among other things, the definition of workloads and load limits at the pile.

Orientadores: Edson Bim, Fernando José Von Zuben / Dissertação (mestrado) - Universidade Estadual de Campinas, Faculdade de Engenharia Elétrica e de Computação / Made available in DSpace on 2018-08-18T01:48:41Z (GMT). No. of bitstreams: 1 Marchi_RodrigoAndreolide_M.pdf: 5160130 bytes, checksum: 8e043b48f5cd0e86cc078b3adc27f74b (MD5) Previous issue date: 2011 / Resumo: Neste trabalho é apresentada a estratégia de Controle Direto de Potência para o Gerador de Indução Duplamente Alimentado utilizando um controlador Perceptron de Múltiplas Camadas. O controlador tem a função de gerar os sinais das componentes de eixo direto e quadratura da tensão do rotor, sem a necessidade de controladores de corrente. A estratégia de controle apresentada permite operar o conversor de potência, conectado aos terminais do rotor, com frequência de chaveamento constante. A rede neural foi treinada off-line, a partir de um algoritmo de otimização de segunda ordem baseado no gradiente conjugado estendido, utilizando um conjunto de amostras obtido por meio da simulação digital de uma máquina de rotor bobinado de potência igual a 2 MW. Resultados de simulação digital com os dados dessa máquina, operando no modo gerador e com dupla alimentação, são apresentados para vários valores de potência ativa e reativa, e para velocidades fixas e variáveis, compreendidas na faixa de -15% a +15% da velocidade síncrona. Com o controlador implementado por uma rede neural artificial e treinada para uma máquina de 2 MW, testes de simulação digital e experimentais para uma máquina de 2,2 kW, operando na velocidade subsíncrona, são apresentados para validar a proposta / Abstract: This work presents a direct power control strategy for the doubly fed induction generator using a controller artificial neural networks, more specifically a multilayer perceptron. The controller has the role of generating the direct and quadrature-axis component signals of the rotor voltage, without the need of current controllers. The proposed control strategy allows to operate the converter, connected to the rotor terminals, with a fixed switching frequency. The multilayer perceptron was subject to an off-line training procedure using a second order algorithm based on an extend version of the conjugate gradient algorithm, using a set of samples produced by a 2 MW machine's digital simulation. Results of digital simulation for this machine are presented for several values of active and reactive power, with the generator operating on fixed and variable speed, in the range of -15% and +15% of the synchronous speed, considering the parameters of 2 MW machine. With the artificial neural network controller designed for this machine, digital simulation tests and experimental tests for a 2,2 kW machine, operating in a sub-synchronous speed, arc presented to validate the proposal / Mestrado / Energia Eletrica / Mestre em Engenharia Elétrica

Orientador: Daniel Barrera Arellano / Tese (doutorado) - Universidade Estadual de Campinas, Faculdade de Engenharia de Alimentos / Made available in DSpace on 2018-08-25T11:25:07Z (GMT). No. of bitstreams: 1 Garcia_RitadeKassiadeAlmeida_D.pdf: 2621947 bytes, checksum: 1a1aa809676a39c098a38069d013cf39 (MD5) Previous issue date: 2014 / Resumo: Óleos e gorduras são submetidos ao processo de blending para alcançar características específicas, visando sua aplicação em variados produtos. Redes neurais artificiais (RNA) têm sido utilizadas para otimizar o processo de formulação de gorduras baseado no conteúdo de gordura sólida (SFC). Além do SFC, a cinética de cristalização das gorduras ou blends influencia diretamente nas condições de processamento, bem como nas características e qualidade dos produtos elaborados. Nesse contexto, o objetivo deste trabalho foi construir e treinar RNAs capazes de prever parâmetros de cristalização de blends de gorduras. Foram treinadas duas RNAs usando blends contendo gorduras interesterificadas de soja, óleos de soja, palma e palmíste como matérias-primas. No treinamento, além dos dados de SFC, foram utilizados os parâmetros de cristalização tempo de indução (T1), tempo médio (T2), tempo final (T3) e SFC máximo (%), obtidos pelas isotermas de cristalização a 25°C. Além disso, como avaliação, foi verificada a capacidade das RNAs em predizer os parâmetros de cristalização de formulações sugeridas pelas RNAs para aplicação em recheio de biscoitos e uso geral. Como resultados, as RNAs se mostraram capazes de prever os parâmetros de cristalização para os blends elaborados com as diferentes matérias-primas, apresentando baixos valores de erros relativos (parâmetros preditos vs determinados). Quanto ao comportamento de cristalização, observou-se que as formulações que continham óleos de palma e/ou palmíste apresentaram menores valores de SFC máximo a 25°C. Adicionalmente, também verificou-se que para valores similares de SFC máximo, foram obtidos valores de T3 bastante variados, o que confirma a necessidade do conhecimento dos parâmetros de cristalização. Portanto, as RNAs demonstraram ser uma ferramenta útil na previsão dos parâmetros de cristalização, podendo ser utilizada na indústria para um melhor monitoramento das características dos blends formulados / Abstract: Oils and fats are submitted to the blending process to achieve specific characteristics for their application at various products. Artificial neural networks (ANN) have been used to optimize the process of fat formulation based on the solid fat content (SFC). In addition to the SFC, the crystallization kinetics of fats or blends influences directly the processing conditions, as well as the characteristics and quality of manufactured food products. In this context, the objective was to build and train ANNs that are able to predict the crystallization parameters of fat blends. Two ANNs were trained using blends containing soybean interesterified fats, soybean, palm and palm kernel oils as raw materials. At training, in addition to the SFC data were used the parameters of crystallization induction time (T1), medium time (T2), end time (T3) and maximum SFC (%), obtained by isothermal crystallization at 25 °C. Besides that, as an evaluation, it was verified the ANN ability to predict the crystallization parameters for a biscuit filling and general use formulations. As results, the ANNs showed ability to predict the crystallization parameters for the blends prepared with different raw materials, presenting low relative errors (predicted vs determined parameters). Regarding the crystallization behavior, it was observed that formulations containing palm and /or palm kernel oil showed lower values of maximum SFC at 25 ° C. In addition, it was also noted that for similar maximum SFC, various T3 values were obtained, confirming the need for knowledge of the crystallization parameters of fats. Therefore, ANNs proved to be a useful tool for predicting the crystallization parameters and can be used in food industry for better monitoring of characteristics of formulated blends / Doutorado / Tecnologia de Alimentos / Doutora em Tecnologia de Alimentos

Orientador: Pablo Siqueira Meirelles / Dissertação (mestrado) - Universidade Estadual de Campinas, Faculdade de Engenharia Mecanica / Made available in DSpace on 2018-07-25T06:06:38Z (GMT). No. of bitstreams: 1 Picado_RicardoMigueis_M.pdf: 5102567 bytes, checksum: cc783eef53f8e17d6dcb5ce204188210 (MD5) Previous issue date: 1998 / Resumo: Neste trabalho, será feito um estudo dos principais tipos de suspensões semi-ativas propostas até o presente. A viabilidade (econômica) de um sistema de suspensão semi-ativa depende da rapidez do algorítmo de controle, da capacidade de processamento do hardware disponível e dos custos para instalação e manutenção da suspensão. Para mostrar como estes fatores influenciam na concepção de um sistema de suspensão automotiva, foram reunidos vários algoritmos de controle e um método alternativo de controle semi-ativo baseado em redes neurais artificias foi proposto / Abstract: In this thesis, it was developed a study of the principal sorts of semi-active car suspensions. The possibility of a semi-active suspension system depends on the costs envolved, the hardware available, and the control algorithm. To show how this subjects influence the conception process of a car suspension, we compiled some algorithms and proposed an altemative one based in artificial neural networks / Mestrado / Mestre em Engenharia Mecânica

In this thesis I look into how one can train and run an artificial neural network using Compute Shader and what kind of performance can be expected. An artificial neural network is a computational model that is inspired by biological neural networks, e.g. a brain. Finding what kind of performance can be expected was done by creating an implementation that uses Compute Shader and then compare it to the FANN library, i.e. a fast artificial neural network library written in C. The conclusion is that you can improve performance by training an artificial neural network on the compute shader as long as you are using non-trivial datasets and neural network configurations.

Today one of the greatest aims within the area of bioinformatics is to gain a complete understanding of the functionality of genes and the systems behind gene regulation. Regulatory relationships among genes seem to be of a complex nature since transcriptional control is the result of complex networks interpreting a variety of inputs. It is therefore essential to develop analytical tools detecting complex genetic relationships. This project examines the possibility of the data mining technique artificial neural network (ANN) detecting regulatory relationships between genes. As an initial step for finding regulatory relationships with the help of ANN the goal of this project is to train an ANN to predict the expression of an individual gene. The genes predicted are the nuclear receptor PPAR-g and the insulin receptor. Predictions of the two target genes respectively were made using different datasets of gene expression data as input for the ANN. The results of the predictions of PPAR-g indicate that it is not possible to predict the expression of PPAR-g under the circumstances for this experiment. The results of the predictions of the insulin receptor indicate that it is not possible to discard using ANN for predicting the gene expression of an individual gene.

This dissertation evaluates the artificial neural technique for evolving a smart antenna system. The AI techniques pose a challenging research in the field of communication. As such the antennas help to communicate with the digital processor to choose the desired signals and reject the others. It makes its own decision even to find the level of interferences and noises to be discarded by amplitude elimination process through the use of perceptron optimization algorithms like LMS (Least Mean Squares). This method helps to enhance the performance of signal processing efficiently. The design of hardware and software are quite complex. This is due to the fact, that the behaviour of the system is not fully understood being a real-time dependent system. This research work is carried only on software with certain simulated activity on beam-formation algorithm and as well, the system responses before and after using the adaptive algorithm. In this report, we try to concentrate to work on the method of adaptivity to make antenna adaptable to a virtual form of real-time environment. For, this reason a two-element antenna is used for simulation testing, as it is the most commonly used antenna for all purposes in communication. It is also tested on various scanning levels of rotation to determine the learning rate (a parameter that has no effect on the radiation output after using LMS) mean-square error rates and convergence analysis. For the purpose of above mentioned tests, three hypotheses are framed in relation to side-lobe reduction level above 5 decibels, the narrowing of the beam after adaptivity and finally the response of the main beam output for varying values of learning rate, respectivelty. The given research work, may comprehend good practical use of this LMS algorithm and also to indicate antenna patterns and the responses to adaptivity conditions through clarity in graphical format. The method is influenced to reduce computational complexity and bring simplicity to the functionality of the antenna with more efficient and effective adaptivness. An effort to test theoretical concepts in practice is also been made in this thesis work. The results show that the antenna system can be made to evolve itself through the process of adaptation with simple behaviour by relying on artificial intelligence technique which ensures little supervision and human intereference. Eventually, it is understood that the reader should have possessed prior concepts, related to antennas, digital signal processing and its practical usage in artificially intelligent systems and as well the exceptions in it, since the work is explained in the direct level assuming so.

The aim of inverting artificial neural networks (ANNs) is to find input patterns that are strongly classified as a predefined class. In this project an ANN is inverted by an evolutionary algorithm. The network is retrained by using the patterns extracted by the inversion as counter-examples, i.e. to classify the patterns as belonging to no class, which is the opposite of what the network previously did. The hypothesis is that the counter-examples extracted by the inversion will cause larger updates of the weights of the ANN and create a better mapping than what is caused by retraining using randomly generated counter-examples. This hypothesis is tested on recognition of pictures of handwritten digits. The tests indicate that this hypothesis is correct. However, the test- and training errors are higher when retraining using counter-examples, than for training only on examples of clean digits. It can be concluded that the counter-examples generated by the inversion have a great impact on the network. It is still unclear whether the quality of the network can be improved using this method.