Técnicas de inteligência artificial para a geração dinâmica de set points para uma coluna de destilação

Artificial Intelligence techniques are applied to improve performance of a simulated oil distillation system. The chosen system was a debutanizer column. At this process, the feed, which comes to the column, is segmented by heating. The lightest components become steams, by forming the LPG (Liquefied Petroleum Gas). The others components, C5+, continue liquid. In the composition of the LPG, ideally, we have only propane and butanes, but, in practice, there are contaminants, for example, pentanes. The objective of this work is to control pentane amount in LPG, by means of intelligent set points (SP s) determination for PID controllers that are present in original instrumentation (regulatory control) of the column. A fuzzy system will be responsible for adjusting the SP's, driven by the comparison between the molar fraction of the pentane present in the output of the plant (LPG) and the desired amount. However, the molar fraction of pentane is difficult to measure on-line, due to constraints such as: long intervals of measurement, high reliability and low cost. Therefore, an inference system was used, based on a multilayer neural network, to infer the pentane molar fraction through secondary variables of the column. Finally, the results shown that the proposed control system were able to control the value of pentane molar fraction under different operational situations

Técnicas inteligentes hídridas para o controle de sistemas não lineares

A neuro-fuzzy system consists of two or more control techniques in only one structure. The main characteristic of this structure is joining one or more good aspects from each technique to make a hybrid controller. This controller can be based in Fuzzy systems, artificial Neural Networks, Genetics Algorithms or rein forced learning techniques. Neuro-fuzzy systems have been shown as a promising technique in industrial applications. Two models of neuro-fuzzy systems were developed, an ANFIS model and a NEFCON model. Both models were applied to control a ball and beam system and they had their results and needed changes commented. Choose of inputs to controllers and the algorithms used to learning, among other information about the hybrid systems, were commented. The results show the changes in structure after learning and the conditions to use each one controller based on theirs characteristics

Estratégias baseadas em aprendizado para coordenação de uma frota de robôs em tarefas cooperativas

In multi-robot systems, both control architecture and work strategy represent a challenge for researchers. It is important to have a robust architecture that can be easily adapted to requirement changes. It is also important that work strategy allows robots to complete tasks efficiently, considering that robots interact directly in environments with humans. In this context, this work explores two approaches for robot soccer team coordination for cooperative tasks development. Both approaches are based on a combination of imitation learning and reinforcement learning. Thus, in the first approach was developed a control architecture, a fuzzy inference engine for recognizing situations in robot soccer games, a software for narration of robot soccer games based on the inference engine and the implementation of learning by imitation from observation and analysis of others robotic teams. Moreover, state abstraction was efficiently implemented in reinforcement learning applied to the robot soccer standard problem. Finally, reinforcement learning was implemented in a form where actions are explored only in some states (for example, states where an specialist robot system used them) differently to the traditional form, where actions have to be tested in all states. In the second approach reinforcement learning was implemented with function approximation, for which an algorithm called RBF-Sarsa($lambda$) was created. In both approaches batch reinforcement learning algorithms were implemented and imitation learning was used as a seed for reinforcement learning. Moreover, learning from robotic teams controlled by humans was explored. The proposal in this work had revealed efficient in the robot soccer standard problem and, when implemented in other robotics systems, they will allow that these robotics systems can efficiently and effectively develop assigned tasks. These approaches will give high adaptation capabilities to requirements and environment changes.

Inferência fuzzy para o problema de corte de estoque com sobras aproveitáveis de material

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

A multiagent architecture for supervisory and control system

Supervising and controlling the many processes involved in petroleum production is both dangerous and complex. Herein, we propose a multiagent supervisory and control system for handle continuous processes like those in chemical and petroleum industries In its architeture, there are agents responsible for managing data production and analysis, and also the production equipments. Fuzzy controllers were used as control agents. The application of a fuzzy control system to managing an off-shore installation for petroleum production onto a submarine separation process is described. © 2008 IEEE.

Risk prediction for weed infestation using classification rules

This paper proposes a fuzzy classification system for the risk of infestation by weeds in agricultural zones considering the variability of weeds. The inputs of the system are features of the infestation extracted from estimated maps by kriging for the weed seed production and weed coverage, and from the competitiveness, inferred from narrow and broad-leaved weeds. Furthermore, a Bayesian network classifier is used to extract rules from data which are compared to the fuzzy rule set obtained on the base of specialist knowledge. Results for the risk inference in a maize crop field are presented and evaluated by the estimated yield loss. © 2009 IEEE.

Classificação da curvatura de vertentes em perfil via Thin Plate Spline e Inferência Fuzzy

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Classificação fuzzy de vertentes por krigagem e TPS com agregação de regiões via diagrama de Voronoi

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Controle automático de adição de AlF3 em cubas de redução de alumínio, usando lógica fuzzy

Este trabalho descreve um sistema de análise de dados com a finalidade de gerar um sistema de controle utilizando técnica inteligente para adição de fluoreto de alumínio (AlF3) em fornos de redução de alumínio. O projeto baseia-se nos conceitos de lógica fuzzy, nos quais o conhecimento acumulado pelo especialista do processo é traduzido de maneira qualitativa em um conjunto de regras linguísticas do tipo SE ENTÃO. A utilização desta técnica inteligente para o controle de adição de fluoreto busca representar explicitamente um conhecimento qualitativo, detido pelos operadores de cubas eletrolíticas. Devido o sistema convencional não contemplar as variações dos fenômenos que envolvem a dinâmica do processo, um controlador fuzzy foi implmentado no sistema real para tomadas de decisões, utilizando o modelo mínimo de Mandani. Baseado neste modelo, as variáveis de processo para a entrada do sistema fuzzy, tais como temperatura de banho e percentual de fluoreto foram manipuladas para estimar a tendência de subida e descida, respectivamente, através do método mínimos quadrados(MMQ). O controlador fuzzy é aplicado para calcular a quantidade de fluoreto de alumínio (AlF3) a ser adicionado na cuba eletrolítica de forma automática sem a necessidade da intervenção do especialista do processo. A motivação para o uso de um sistema de controle fuzzy se deve ao fato de não se ter disponível um modelo dinâmico do processo de adição do fluoreto na cuba eletrolítica. Esta falta de modelagem se deve ao fato de grande complexidade dos fenômenos envolvidos em uma cuba que são processos termodinâmicos e eletromagnéticos acoplados.

Contribuições aos estudo da compensação de harmônicos em sistemas de energia elétrica

Esta tese enfoca o estudo de métodos para compensação de harmônicos em sistemas de energia elétrica e aborda diversos aspectos relacionados à presença de harmônicos nos mesmos, como a apresentação de conceitos e definições em sistemas não-senoidais e estratégias de compensação de potência. Enfatiza-se neste estudo, exemplificado por meio de medições e simulações realizadas, a influência da forma de onda de alimentação sobre cargas não-lineares; a interação harmônica entre a tensão de suprimento e a corrente das cargas, devido à impedância série do sistema; e a influência mútua entre cargas não-lineares em paralelo, como possível forma de atenuação de harmônicos. Para simular e predizer o impacto causado por cargas não-lineares em um sistema, assim como a implementação de ações para mitigar esses impactos, visando à melhoria da qualidade da energia, é necessário o conhecimento das respostas das mesmas. Como produto do presente trabalho, destacam-se as técnicas desenvolvidas para a modelagem de cargas nãolineares sob diferentes condições de alimentação, em especial o uso de técnicas de inteligência computacional, como o sistema neuro-fuzzy e as redes neurais artificiais; assim como o emprego da série de Volterra para predição do comportamento das cargas.

Análise de um regulador de velocidade digital para a Usina Hidroelétrica de Curuá-Una

Analisa uma proposta de um controlador digital para o regulador de velocidade da Usina Hidroelétrica de Curuá-Una, utilizando duas estratégias de projeto, a estratégia indireta com o projeto do controlador sendo feito no plano contínuo e depois discretizado e a estratégia direta, em que o controlador é projetado inteiramente no plano discreto. O conhecimento gerado no simulador é de grande importância, pois é uma das grandes ferramentas para avaliar o comportamento dos controladores digitais propostos, em ambiente seguro. O estudo dos controladores também permite uma substituição de equipamentos antigos, com produção descontinuada, por equipamentos novos que permitem a confecção de controladores modernos, digitais e inteligentes, que proporcionam uma substituição de técnicas antigas de controle por estratégias avançadas de controle, maximizando o rendimento do sistema em condições adversas de operação. O trabalho levanta as diferenças, vantagens e desvantagens de cada controlador, com o objetivo de auxiliar na escolha do controlador mais adequado para projetos de controladores avançados: tipo um controle adaptativo, controle fuzzy ou controle neural. As dificuldades de projeto e os resultados das simulações foram os principais indicadores na avaliações dos dois RV digitais projetados. De uma forma geral o RV digital direto apresentou melhor desempenho, estabilidade e menor esforço computacional, entretanto, o RV digital indireto mostrou desempenho similar, menor degradação devido às não linearidades e ao menor esforço de projeto.

Fuzzy Index for Public Supply Water Quality

Human population growth and increased industrial activity in recent decades have contributed to a range of environmental problems, including the contamination of groundwater and surface water. In order to help in the management of these resources, water quality indices are used as tools to summarize multiple parameters and express them in the form of a single number. The ability to provide both an integrated assessment of changes in environmental variables, as well as performance tracking, has resulted in such indices being increasingly employed in surface water monitoring programs. The aim of this study was to develop an Index for Public Supply Water Quality (IPS) using a fuzzy inference methodology. Linguistic systems generally provide satisfactory tools for qualitative purposes, enabling the inclusion of descriptive variables with reduced loss of individual information. Validation of the technique was achieved by analysis of measurement data obtained for the Sorocaba River, provided by CETESB. The new procedure proved more rigorous, compared to classical IPS. It could be readily applied in the evaluation of other water bodies, or be adjusted to incorporate additional parameters also considered important for the assessment of water quality.

Aplicação da teoria fuzzy no controle de sistemas de geração de energias alternativas

This paper presents the application and use of a methodology based on fuzzy theory and simulates its use in intelligent control of a hybrid system for generating electricity, using solar energy, photovoltaic and wind. When using a fuzzy control system, it reached the point of maximum generation of energy, thus shifting all energy generated from the alternative sources-solar photovoltaic and wind, cargo and / or batteries when its use not immediately. The model uses three variables used for entry, which are: wind speed, solar radiation and loading the bank of batteries. For output variable has to choose which of the batteries of the battery bank is charged. For the simulations of this work is used MATLAB software. In this environment mathematical computational are analyzed and simulated all mathematical modeling, rules and other variables in the system described fuzzy. This model can be used in a system of control of hybrid systems for generating energy, providing the best use of energy sources, sun and wind, so we can extract the maximum energy possible these alternative sources without any prejudice to the environment.

A New Control Architecture for Robust Controllers in Rear Electric Traction Passenger HEVs

It is well known that control systems are the core of electronic differential systems (EDSs) in electric vehicles (EVs)/hybrid HEVs (HEVs). However, conventional closed-loop control architectures do not completely match the needed ability to reject noises/disturbances, especially regarding the input acceleration signal incoming from the driver's commands, which makes the EDS (in this case) ineffective. Due to this, in this paper, a novel EDS control architecture is proposed to offer a new approach for the traction system that can be used with a great variety of controllers (e. g., classic, artificial intelligence (AI)-based, and modern/robust theory). In addition to this, a modified proportional-integral derivative (PID) controller, an AI-based neuro-fuzzy controller, and a robust optimal H-infinity controller were designed and evaluated to observe and evaluate the versatility of the novel architecture. Kinematic and dynamic models of the vehicle are briefly introduced. Then, simulated and experimental results were presented and discussed. A Hybrid Electric Vehicle in Low Scale (HELVIS)-Sim simulation environment was employed to the preliminary analysis of the proposed EDS architecture. Later, the EDS itself was embedded in a dSpace 1103 high-performance interface board so that real-time control of the rear wheels of the HELVIS platform was successfully achieved.

Classification of the severity of diabetic neuropathy: a new approach taking uncertainties into account using fuzzy logic

OBJECTIVE: This study proposes a new approach that considers uncertainty in predicting and quantifying the presence and severity of diabetic peripheral neuropathy. METHODS: A rule-based fuzzy expert system was designed by four experts in diabetic neuropathy. The model variables were used to classify neuropathy in diabetic patients, defining it as mild, moderate, or severe. System performance was evaluated by means of the Kappa agreement measure, comparing the results of the model with those generated by the experts in an assessment of 50 patients. Accuracy was evaluated by an ROC curve analysis obtained based on 50 other cases; the results of those clinical assessments were considered to be the gold standard. RESULTS: According to the Kappa analysis, the model was in moderate agreement with expert opinions. The ROC analysis (evaluation of accuracy) determined an area under the curve equal to 0.91, demonstrating very good consistency in classifying patients with diabetic neuropathy. CONCLUSION: The model efficiently classified diabetic patients with different degrees of neuropathy severity. In addition, the model provides a way to quantify diabetic neuropathy severity and allows a more accurate patient condition assessment.