Modeling of optoelectronic devices through neuro-fuzzy architectures

The advantages offered by the electronic component LED (Light Emitting Diode) have caused a quick and wide application of this device in replacement of incandescent lights. However, in its combined application, the relationship between the design variables and the desired effect or result is very complex and it becomes difficult to model by conventional techniques. This work consists of the development of a technique, through comparative analysis of neuro-fuzzy architectures, to make possible to obtain the luminous intensity values of brake lights using LEDs from design data.

Sistema especialista fuzzy para dimensionamento de bombeio mecânico

Despite the emergence of other forms of artificial lift, sucker rod pumping systems remains hegemonic because of its flexibility of operation and lower investment cost compared to other lifting techniques developed. A successful rod pumping sizing necessarily passes through the supply of estimated flow and the controlled wear of pumping equipment used in the mounted configuration. However, the mediation of these elements is particularly challenging, especially for most designers dealing with this work, which still lack the experience needed to get good projects pumping in time. Even with the existence of various computer applications on the market in order to facilitate this task, they must face a grueling process of trial and error until you get the most appropriate combination of equipment for installation in the well. This thesis proposes the creation of an expert system in the design of sucker rod pumping systems. Its mission is to guide a petroleum engineer in the task of selecting a range of equipment appropriate to the context provided by the characteristics of the oil that will be raised to the surface. Features such as the level of gas separation, presence of corrosive elements, possibility of production of sand and waxing are taken into account in selecting the pumping unit, sucker-rod strings and subsurface pump and their operation mode. It is able to approximate the inferente process in the way of human reasoning, which leads to results closer to those obtained by a specialist. For this, their production rules were based on the theory of fuzzy sets, able to model vague concepts typically present in human reasoning. The calculations of operating parameters of the pumping system are made by the API RP 11L method. Based on information input, the system is able to return to the user a set of pumping configurations that meet a given design flow, but without subjecting the selected equipment to an effort beyond that which can bear

Design of a simplified neuro-fuzzy system based on CMAC Architectures

This work presents the design of a fuzzy controller with simplified architecture that use an artificial neural network working as the aggregation operator for several active fuzzy rules. The simplified architecture of the fuzzy controller is used to minimize the time processing used in the closed loop system operation, the basic procedures of fuzzification are simplified to maximum while all the inference procedures are computed in a private way. As consequence, this simplified architecture allows a fast and easy configuration of the simplified fuzzy controller. The structuring of the fuzzy rules that define the control actions is previously computed using an artificial neural network based on CMAC Cerebellar Model Articulation Controller. The operational limits are standardized and all the control actions are previously calculated and stored in memory. For applications, results and conclusions several configurations of this fuzzy controller are considered.

Multivalued adaptive neuro-fuzzy controller for robot vehicle - art. no. 1406

Robotic vehicle navigation in unstructured and uncertain environments is still a challenge. This paper presents the implementation of a multivalued neurofuzzy controller for autonomous ground vehicle (AGVs) in indoor environments. The control system consists of a hierarchy of mobile robot using multivalued adaptive neuro-fuzzy inference system behaviors.

Traffic flow breakdown prediction using feature reduction through Rough-Neuro fuzzy Networks

The prediction of the traffic behavior could help to make decision about the routing process, as well as enables gains on effectiveness and productivity on the physical distribution. This need motivated the search for technological improvements in the Routing performance in metropolitan areas. The purpose of this paper is to present computational evidences that Artificial Neural Network ANN could be use to predict the traffic behavior in a metropolitan area such So Paulo (around 16 million inhabitants). The proposed methodology involves the application of Rough-Fuzzy Sets to define inference morphology for insertion of the behavior of Dynamic Routing into a structured rule basis, without human expert aid. The dynamics of the traffic parameters are described through membership functions. Rough Sets Theory identifies the attributes that are important, and suggest Fuzzy relations to be inserted on a Rough Neuro Fuzzy Network (RNFN) type Multilayer Perceptron (MLP) and type Radial Basis Function (RBF), in order to get an optimal surface response. To measure the performance of the proposed RNFN, the responses of the unreduced rule basis are compared with the reduced rule one. The results show that by making use of the Feature Reduction through RNFN, it is possible to reduce the need for human expert in the construction of the Fuzzy inference mechanism in such flow process like traffic breakdown. © 2011 IEEE.

Avaliação de modelos neurais aplicados na estimação de parâmetros da retificação de cerâmicas avançadas

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Estimação do diâmetro de furos em processo de furação utilizando sistemas de inteligência artificial: uma análise comparativa entre diferentes técnicas

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Uso de engenharia de software no desenvolvimento de sistema especialista fuzzy para auxílio à manutenção preditiva em hidrogeradores

Os hidrogeradores são peças chaves no circuito brasileiro de energia, sua indisponibilidade e mau funcionamento podem causar multas altíssimas a concessionárias aplicadas pela ANEEL por não atenderem a demandas e até por paradas impróprias para efetivar manutenções, além de agravar confiabilidade na garantia do fornecimento aos consumidores finais. Para garantir que isso não venha acontecer, a manutenção preditiva fornece técnicas que podem apontar as falhas analisando os “sinais vitais” originados pelo próprio equipamento. Desta forma as condições mecânicas e operacionais são periodicamente monitoradas e quando as tendências são detectadas insalubres, as peças incômodas na máquina são identificadas e programadas para manutenção. Para que essa tendência seja encontrada, utiliza-se da lógica fuzzy para modelar o comportamento dos hidrogeradores, sendo mais especifico: mancais, estator e anel coletor, inferindo conclusões prováveis de falhas. Neste trabalho, mostra o processo de construção do sistema que auxilia no diagnóstico da manutenção preditiva, desde sua metodologia de desenvolvimento por macro-atividades, definição arquitetural, conformidade dos requisitos e análise do conhecimento inserido a inteligência do sistema. O sistema foi desenvolvido em plataforma labview para servir como ferramenta de apoio. Todo o conhecimento inserido no sistema foi obtido com o corpo especialista de Eletronorte e outra parte na literatura, foi necessário aplicar o conceito de regras ao maquina de inferência fuzzy, para uma forma linguística de fácil compreensão, para que os próprios especialistas ampliem e evolua o software.

Modelos computacionais fuzzy e neuro-fuzzy para avaliarem os efeitos da poluição do ar

Pós-graduação em Engenharia Mecânica - FEG

Auxílio a tomada de decisão na inclusão de sobressalentes de manutenção em estoque utilizando um sistema especialista fuzzy

In the current economic scenario of constant changes, industries seek to increase their profitability decreasing inventory levels. Maintenance and maintenance management, combined with the inventory management of spare parts, has assumed a position of competitive advantage in business. Stock only what you need has become a difficult decision for managers, who are faced with the lack of models and criteria to assist this decision-making. This work proposes a method which supports decision making, on a MATLAB modeling, using criteria established by an expert and his maintenance workers team, focusing on no regular demand of spare parts. The proposed model was adequate to the needs of the company and the maintenance manager in the decision on the storage

Desenvolvimento de uma rede neuro-fuzzy para a previsão da carga

Pós-graduação em Engenharia Elétrica - FEIS

Tool wear monitoring using neuro-fuzzy techniques: a comparative study in a turning process

Tool wear detection is a key issue for tool condition monitoring. The maximization of useful tool life is frequently related with the optimization of machining processes. This paper presents two model-based approaches for tool wear monitoring on the basis of neuro-fuzzy techniques. The use of a neuro-fuzzy hybridization to design a tool wear monitoring system is aiming at exploiting the synergy of neural networks and fuzzy logic, by combining human reasoning with learning and connectionist structure. The turning process that is a well-known machining process is selected for this case study. A four-input (i.e., time, cutting forces, vibrations and acoustic emissions signals) single-output (tool wear rate) model is designed and implemented on the basis of three neuro-fuzzy approaches (inductive, transductive and evolving neuro-fuzzy systems). The tool wear model is then used for monitoring the turning process. The comparative study demonstrates that the transductive neuro-fuzzy model provides better error-based performance indices for detecting tool wear than the inductive neuro-fuzzy model and than the evolving neuro-fuzzy model.

Vibration reduction for vision systems on board unmanned aerial vehicles using a neuro-fuzzy controller

In this paper, an intelligent control approach based on neuro-fuzzy systems performance is presented, with the objective of counteracting the vibrations that affect the low-cost vision platform onboard an unmanned aerial system of rotating nature. A scaled dynamical model of a helicopter is used to simulate vibrations on its fuselage. The impact of these vibrations on the low-cost vision system will be assessed and an intelligent control approach will be derived in order to reduce its detrimental influence. Different trials that consider a neuro-fuzzy approach as a fundamental part of an intelligent semi-active control strategy have been carried out. Satisfactory results have been achieved compared to those obtained by means of vibration reduction passive techniques.

Speed prediction for triggering vehicle activated signs

Accurate speed prediction is a crucial step in the development of a dynamic vehcile activated sign (VAS). A previous study showed that the optimal trigger speed of such signs will need to be pre-determined according to the nature of the site and to the traffic conditions. The objective of this paper is to find an accurate predictive model based on historical traffic speed data to derive the optimal trigger speed for such signs. Adaptive neuro fuzzy (ANFIS), classification and regression tree (CART) and random forest (RF) were developed to predict one step ahead speed during all times of the day. The developed models were evaluated and compared to the results obtained from artificial neural network (ANN), multiple linear regression (MLR) and naïve prediction using traffic speed data collected at four sites located in Sweden. The data were aggregated into two periods, a short term period (5-min) and a long term period (1-hour). The results of this study showed that using RF is a promising method for predicting mean speed in the two proposed periods.. It is concluded that in terms of performance and computational complexity, a simplistic input features to the predicitive model gave a marked increase in the response time of the model whilse still delivering a low prediction error.

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.