Orientador: Secundino Soares Filho / Dissertação (mestrado) - Universidade Estadual de Campinas, Faculdade de Engenharia Eletrica e de Computação / Made available in DSpace on 2018-08-13T03:22:09Z (GMT). No. of bitstreams: 1 Monte_Bruno_M.pdf: 1808851 bytes, checksum: 7268c8ef4bb1363f9876841d3a0ce345 (MD5) Previous issue date: 2009 / Resumo: O planejamento energético de sistemas hidrotérmicos caracteriza-se pela otimização dos recursos hidráulicos através da maximização da operação hidrelétrica e da minimização da operação térmica. Seu objetivo é garantir um atendimento à carga de maneira econômica e confiável durante todo o horizonte de estudo. Este problema pode ser caracterizado como de natureza complexa, dado que suas características o definem como um problema de grande porte, dinâmico, estocástico e não-linear. Não obstante muitas técnicas já terem sido propostas para solução deste problema, não existe, ainda, uma metodologia unânime que aborde todas essas características com eficiência. A Programação Dinâmica, que é uma das técnicas mais populares utilizadas, tem sua aplicação limitada em sistemas reais, dado que exige um elevado esforço computacional. Neste trabalho, foi proposta uma metodologia alternativa para abordagem do planejamento da operação de médio prazo de sistemas hidrotérmicos. A metodologia proposta é baseada em um Sistema de Inferência Neural-Nebulosa Adaptativo atuando em paralelo com um modelo de otimização determinístico com perfeita previsão de vazão. A informação do otimizador determinístico é utilizada no treinamento da rede, que gera uma base de regra de inferência nebulosa que reproduzirá o comportamento ótimo da usina através da definição da vazão turbinada, em cada estágio, em função das varáveis de entrada estipuladas. A performance da metodologia Neural Nebulosa proposta foi comparada com outras modelagens, como a Programação Dinâmica Determinística, a Programação Dinâmica Estocástica e o Controle de Malha Aberta, através de simulações em cinco usinas hidrelétricas do parque gerador brasileiro considerando as vazões afluentes do histórico. Os resultados indicaram que a metodologia Neural Nebulosa proposta apresentou desempenho similar a abordagens mais tradicionais e que se configuram computacionalmente menos eficiente. / Abstract: The long term hydrothermal scheduling lies in the optimization of the water resource usage through the maximization of the hydroelectric production and the minimization of the thermal plants operation. Its goal is to assure an economic and reliable load supply throughout the study stages. This problem can be characterized by exhibiting a complex nature, since its characteristics define it as a large scale, dynamic, stochastic and nonlinear problem. Although many optimization approaches have already been proposed to answer the hydrothermal scheduling problem, until now, there is no unanimous approach that is able to cope efficiently with all the problem issues. Dynamic Programming, which is one of the most commonly used techniques to deal with this problem, is limited regarding its application on real systems since its computational requirements tend to be heavy. In this work we proposed an alternative approach to deal with the long term hydrothermal scheduling. The proposed technique is based on an Adaptive Neuro-Fuzzy Inference System working in parallel with a deterministic optimization model with perfect inflows forecasting. The optimal operation information is processed by the network that produces fuzzy rules describing the optimal decisions of the plant through the definition of the amount of discharge in each stage and depending on the chosen input variables. The performance of the proposed Neuro-Fuzzy approach was compared to other policies, including Deterministic Dynamic Programming, Stochastic Dynamic Programming and Open- Loop Feedback Control, by simulation using historical inflow records of five different Brazilian hydroelectric power plants. The results demonstrated that the Neuro-Fuzzy approach provided similar and competitive performance to less computationally efficient and commonly used policies. / Mestrado / Energia Eletrica / Mestre em Engenharia Elétrica

Quad-rotor helicopters are agile aircraft which are lifted and propelled by four rotors. Unlike traditional helicopters, they do not require a tail-rotor to control yaw, but can use four smaller fixed-pitch rotors. However, without an intelligent control system it is very difficult for a human to successfully fly and manoeuvre such a vehicle. Thus, most of recent research has focused on small unmanned aerial vehicles, such that advanced embedded control systems could be developed to control these aircrafts. Vehicles of this nature are very useful when it comes to situations that require unmanned operations, for instance performing tasks in dangerous and/or inaccessible environments that could put human lives at risk. This research demonstrates a consistent way of developing a robust adaptive controller for quad-rotor helicopters, using fuzzy-neural networks; creating an intelligent system that is able to monitor and control the non-linear multi-variable flying states of the quad-rotor, enabling it to adapt to the changing environmental situations and learn from past missions. Firstly, an analytical dynamic model of the quad-rotor helicopter was developed and simulated using Matlab/Simulink software, where the behaviour of the quad-rotor helicopter was assessed due to voltage excitation. Secondly, a 3-D model with the same parameter values as that of the analytical dynamic model was developed using Solidworks software. Computational Fluid Dynamics (CFD) was then used to simulate and analyse the effects of the external disturbance on the control and performance of the quad-rotor helicopter. Verification and validation of the two models were carried out by comparing the simulation results with real flight experiment results. The need for more reliable and accurate simulation data led to the development of a neural network error compensation system, which was embedded in the simulation system to correct the minor discrepancies found between the simulation and experiment results. Data obtained from the simulations were then used to train a fuzzy-neural system, made up of a hierarchy of controllers to control the attitude and position of the quad-rotor helicopter. The success of the project was measured against the quad-rotor’s ability to adapt to wind speeds of different magnitudes and directions by re-arranging the speeds of the rotors to compensate for any disturbance. From the simulation results, the fuzzy-neural controller is sufficient to achieve attitude and position control of the quad-rotor helicopter in different weather conditions, paving way for future real time applications.

This thesis focuses on fuzzy neural networks. The combination of the fuzzy logic and artificial neural networks leads to the development of more robust systems. These systems are used in various field of the research, such as artificial intelligence, machine learning and control theory. First, we provide a quick overview of underlying neural networks and fuzzy systems to explain fundamental ideas that form the basis of the fields, and follow with the introduction of the fuzzy neural network theory, classification and application. Then we describe a design and a realization of the fuzzy associative memory, as an example of these systems. Finally, we benchmark the realization using the pattern recognition and control tasks. The results are evaluated and compared against existing systems.