Identificação não linear usando uma rede fuzzy wavelet neural network modificada

In last decades, neural networks have been established as a major tool for the identification of nonlinear systems. Among the various types of networks used in identification, one that can be highlighted is the wavelet neural network (WNN). This network combines the characteristics of wavelet multiresolution theory with learning ability and generalization of neural networks usually, providing more accurate models than those ones obtained by traditional networks. An extension of WNN networks is to combine the neuro-fuzzy ANFIS (Adaptive Network Based Fuzzy Inference System) structure with wavelets, leading to generate the Fuzzy Wavelet Neural Network - FWNN structure. This network is very similar to ANFIS networks, with the difference that traditional polynomials present in consequent of this network are replaced by WNN networks. This paper proposes the identification of nonlinear dynamical systems from a network FWNN modified. In the proposed structure, functions only wavelets are used in the consequent. Thus, it is possible to obtain a simplification of the structure, reducing the number of adjustable parameters of the network. To evaluate the performance of network FWNN with this modification, an analysis of network performance is made, verifying advantages, disadvantages and cost effectiveness when compared to other existing FWNN structures in literature. The evaluations are carried out via the identification of two simulated systems traditionally found in the literature and a real nonlinear system, consisting of a nonlinear multi section tank. Finally, the network is used to infer values of temperature and humidity inside of a neonatal incubator. The execution of such analyzes is based on various criteria, like: mean squared error, number of training epochs, number of adjustable parameters, the variation of the mean square error, among others. The results found show the generalization ability of the modified structure, despite the simplification performed

Ambiente para desenvolvimento de aplicações fuzzy industriais

This paper describes the design, implementation and enforcement of a system for industrial process control based on fuzzy logic and developed using Java, with support for industrial communication protocol through the OPC (Ole for Process Control). Besides the java framework, the software is completely independent from other platforms. It provides friendly and functional tools for modeling, construction and editing of complex fuzzy inference systems, and uses these logical systems in control of a wide variety of industrial processes. The main requirements of the developed system should be flexibility, robustness, reliability and ease of expansion

Aplicação de técnicas de aprendizado de máquina no reconhecimento de classes estruturais de proteínas

Nowadays, classifying proteins in structural classes, which concerns the inference of patterns in their 3D conformation, is one of the most important open problems in Molecular Biology. The main reason for this is that the function of a protein is intrinsically related to its spatial conformation. However, such conformations are very difficult to be obtained experimentally in laboratory. Thus, this problem has drawn the attention of many researchers in Bioinformatics. Considering the great difference between the number of protein sequences already known and the number of three-dimensional structures determined experimentally, the demand of automated techniques for structural classification of proteins is very high. In this context, computational tools, especially Machine Learning (ML) techniques, have become essential to deal with this problem. In this work, ML techniques are used in the recognition of protein structural classes: Decision Trees, k-Nearest Neighbor, Naive Bayes, Support Vector Machine and Neural Networks. These methods have been chosen because they represent different paradigms of learning and have been widely used in the Bioinfornmatics literature. Aiming to obtain an improvment in the performance of these techniques (individual classifiers), homogeneous (Bagging and Boosting) and heterogeneous (Voting, Stacking and StackingC) multiclassification systems are used. Moreover, since the protein database used in this work presents the problem of imbalanced classes, artificial techniques for class balance (Undersampling Random, Tomek Links, CNN, NCL and OSS) are used to minimize such a problem. In order to evaluate the ML methods, a cross-validation procedure is applied, where the accuracy of the classifiers is measured using the mean of classification error rate, on independent test sets. These means are compared, two by two, by the hypothesis test aiming to evaluate if there is, statistically, a significant difference between them. With respect to the results obtained with the individual classifiers, Support Vector Machine presented the best accuracy. In terms of the multi-classification systems (homogeneous and heterogeneous), they showed, in general, a superior or similar performance when compared to the one achieved by the individual classifiers used - especially Boosting with Decision Tree and the StackingC with Linear Regression as meta classifier. The Voting method, despite of its simplicity, has shown to be adequate for solving the problem presented in this work. The techniques for class balance, on the other hand, have not produced a significant improvement in the global classification error. Nevertheless, the use of such techniques did improve the classification error for the minority class. In this context, the NCL technique has shown to be more appropriated

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.

Controle Robusto Aplicado a Conversor Buck-Boost em Sistemas Fotovoltaicos

The need to implement a software architecture that promotes the development of a SCADA supervisory system for monitoring industrial processes simulated with the flexibility of adding intelligent modules and devices such as CLP, according to the specifications of the problem, it was the motivation for this work. In the present study, we developed an intelligent supervisory system on a simulation of a distillation column modeled with Unisim. Furthermore, OLE Automation was used as communication between the supervisory and simulation software, which, with the use of the database, promoted an architecture both scalable and easy to maintain. Moreover, intelligent modules have been developed for preprocessing, data characteristics extraction, and variables inference. These modules were fundamentally based on the Encog software

Sistema Especialista para Supressão Online de Alarmes em Processos Industriais

Operating industrial processes is becoming more complex each day, and one of the factors that contribute to this growth in complexity is the integration of new technologies and smart solutions employed in the industry, such as the decision support systems. In this regard, this dissertation aims to develop a decision support system based on an computational tool called expert system. The main goal is to turn operation more reliable and secure while maximizing the amount of relevant information to each situation by using an expert system based on rules designed for a particular area of expertise. For the modeling of such rules has been proposed a high-level environment, which allows the creation and manipulation of rules in an easier way through visual programming. Despite its wide range of possible applications, this dissertation focuses only in the context of real-time filtering of alarms during the operation, properly validated in a case study based on a real scenario occurred in an industrial plant of an oil and gas refinery

Controle fuzzy espacialmente diferenciado para um sistema de irrigação

Traditional irrigation projects do not locally determine the water availability in the soil. Then, irregular irrigation cycles may occur: some with insufficient amount that leads to water deficit, other with excessive watering that causes lack of oxygen in plants. Due to the nonlinear nature of this problem and the multivariable context of irrigation processes, fuzzy logic is suggested to replace commercial ON-OFF irrigation system with predefined timing. Other limitation of commercial solutions is that irrigation processes either consider the different watering needs throughout plant growth cycles or the climate changes. In order to fulfill location based agricultural needs, it is indicated to monitor environmental data using wireless sensors connected to an intelligent control system. This is more evident in applications as precision agriculture. This work presents the theoretical and experimental development of a fuzzy system to implement a spatially differentiated control of an irrigation system, based on soil moisture measurement with wireless sensor nodes. The control system architecture is modular: a fuzzy supervisor determines the soil moisture set point of each sensor node area (according to the soil-plant set) and another fuzzy system, embedded in the sensor node, does the local control and actuates in the irrigation system. The fuzzy control system was simulated with SIMULINK® programming tool and was experimentally built embedded in mobile device SunSPOTTM operating in ZigBee. Controller models were designed and evaluated in different combinations of input variables and inference rules base

Predição da incrustação em um trocador de calor baseada em redes neurais artificiais

A serious problem that affects an oil refinery s processing units is the deposition of solid particles or the fouling on the equipments. These residues are naturally present on the oil or are by-products of chemical reactions during its transport. A fouled heat exchanger loses its capacity to adequately heat the oil, needing to be shut down periodically for cleaning. Previous knowledge of the best period to shut down the exchanger may improve the energetic and production efficiency of the plant. In this work we develop a system to predict the fouling on a heat exchanger from the Potiguar Clara Camarão Refinery, based on data collected in a partnership with Petrobras. Recurrent Neural Networks are used to predict the heat exchanger s flow in future time. This variable is the main indicator of fouling, because its value decreases gradually as the deposits on the tubes reduce their diameter. The prediction could be used to tell when the flow will have decreased under an acceptable value, indicating when the exchanger shutdown for cleaning will be needed

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

"Tudo" em Natal : definitude, implicaturas e contribuições para o ensino de língua materna

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior

Interpretação e análise do problema da indução sob uma visão fundamentada em teorias de conjuntos e teoria de probabilidades

The following work is to interpret and analyze the problem of induction under a vision founded on set theory and probability theory as a basis for solution of its negative philosophical implications related to the systems of inductive logic in general. Due to the importance of the problem and the relatively recent developments in these fields of knowledge (early 20th century), as well as the visible relations between them and the process of inductive inference, it has been opened a field of relatively unexplored and promising possibilities. The key point of the study consists in modeling the information acquisition process using concepts of set theory, followed by a treatment using probability theory. Throughout the study it was identified as a major obstacle to the probabilistic justification, both: the problem of defining the concept of probability and that of rationality, as well as the subtle connection between the two. This finding called for a greater care in choosing the criterion of rationality to be considered in order to facilitate the treatment of the problem through such specific situations, but without losing their original characteristics so that the conclusions can be extended to classic cases such as the question about the continuity of the sunrise

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

Estudo geológico e geofísico da falha de carnaubais, Bacia Potiguar-RN, e implicações neotectônicas

The segment of Carnaubais Fault located in the southeasthern portion of Guamaré Graben (Potiguar Basin) was studied. Several structures were detected and some of them strongly suggest that the last movements in Carnaubais Fault are of Neotectonic age. The study comprises an integrated interpretation of geologic, geomorphologic and geophysical data (gravimetry, magnetometry, resistivity, and self potential methods). According to the size of the studied areas, two approaches were used in this research. The first approach is of a regional nature and was conducted in an area, hereafter named Regional Area, having approximately 6,000 km2 and localized in the northern portion of Rio Grande do Norte state, around Macau city. The second approach comprises detailled studies of two small areas inside the Regional Area: the Camurupim and São Bento areas. Gravimetric and topographic data were used in the Regional Area. A separation into regional and residual components were conducted both on gravimetric and topographic data. The interpretation of the residual component of the gravimetric data allows a precise mapping of the borders of the Guamaré Graben. The regional component features of the topographic data are controlled by the pair of conjugate faults composed by the Carnaubais Fault (NE direction) and the Afonso Bezerra Fault (NW direction). On the other hand, the residual component of the topographic data shows that river valleis of NW direction are sharply interrupted where they intersect Carnaubais Fault. This fact is interpreted as an evidency that the last significant moviments occured in the Carnaubais Fault. Geologic, geomorphologic and geophysical data (magnetometry, resistivity, and self potential methods) were used in the Camurupim Area. The geologic mapping allows to identify five lithophacies unities. The first two unities (from base to top) were interpreted as composing a marine (or transitional) depositional sequency while the other were interpreted is composing a continental depositional sequence. The two sequences are clearly separated of an erosional discordance. The unities grouped in the marine sequence are composed by calcarenites (Unity A) and mudstones (Unity B). Unity A was deposited in a shalow plataform while Unity B, in a tidal flat. The unities grouped in the continental sequence are composed of conglomerate (Unity C) and sandstones (Unities D and E). Unities C and D are fluvial deposits while unity E is an eolian deposit. Unities A and B can be stratigraphycally correlated with Guamaré Formation. Unities C and D present three possible correlations. They may be correlated with Tibau Formation; or with Barreiras Formation; or with a clastic sediment deposit, commonly found in some rivers of Rio Grande do Norte state, and statigraphycally positioned above Barreiras Formation. Based on the decrease of the grain sizes from base to top both on unities C and D, it is proposed that these unities are correlated with the clastic sediment above mentioned. In this case, these unities would have, at least, Pleistocenic age. Finally, it is proposed that Unity E represent an eolian deposit that sufferred recent changes (at least in the Quaternary). The integrated interpretation of hydrographic, morphologic and geophysical data from Camurupim Area shows that Carnaubais Fault is locally composed by a system of several paralel subvertical faults. The fault presenting the larger vertical slip controls the valley of Camurupim river and separates the area in two blocks; in the nothern block the top of the Jandaira limestone is deeper than in the southern block. In addition, at least one of the faults in the northern block is cutting the whole sedimentary section. Because unities C , D, and/or E may be of Quaternary age, tectonic moviments possibly occured in Carnaubais Fault during this period. Detailled geologic mapping were conducted in beachrocks found in São Bento Area. This area is located at the intersection of the coast line with the Carnaubais Fault. The detected structures in the beachrocks are very similar to those caused by fragile deformations. The structures mapped in the beachrocks are consistent with a stress field with maximun compressional stress in E-W direction and extensional stress in the N-S direction. Since the Carnaubais Fault has a NE direction, it is optimally positioned to suffer tectonic movements under the action of such stress field. In addition, the shape of the coastal line appear to be controlled by the Carnaubais Fault. Furthemore, the observed structures in Camurupim Área are consistent with this stress field. These facts are interpreted as evidences that Carnaubais Fault and beachrocks suffered coupled tectonic movements. These moviments are of Neotectonic age because the beachrocks present ages less than 16,000 years

Arquitetura, litofácies e evolução tectonoestratigráfica da bacia do rio do peixe, nordeste do Brasil

The Rio do Peixe Basin is located in the border of Paraíba and Ceará states, immediately to the north of the Patos shear zone, encompassing an area of 1,315 km2. This is one of the main basins of eocretaceous age in Northeast Brazil, associated to the rifting event that shaped the present continental margin. The basin can be divided into four sub-basins, corresponding to Pombal, Sousa, Brejo das Freiras and Icozinho half-grabens. This dissertation was based on the analysis and interpretation of remote sensing products, field stratigraphic and structural data, and seismic sections and gravity data. Field work detailed the lithofacies characterization of the three formations previously recognised in the basin, Antenor Navarro, Sousa and Rio Piranhas. Unlike the classical vertical stacking, field relations and seismostratigraphic analysis highlighted the interdigitation and lateral equivalency between these units. On bio/chrono-stratigraphic and tectonic grounds, they correlate with the Rift Tectonosequence of neocomian age. The Antenor Navarro Formation rests overlies the crystalline basement in non conformity. It comprises lithofacies originated by a braided fluvial system system, dominated by immature, coarse and conglomeratic sandstones, and polymict conglomerates at the base. Its exposures occur in the different halfgrabens, along its flexural margins. Paleocurrent data indicate source areas in the basement to the north/NW, or input along strike ramps. The Sousa Formation is composed by fine-grained sandstones, siltites and reddish, locally grey-greenish to reddish laminated shales presenting wavy marks, mudcracks and, sometimes, carbonate beds. This formation shows major influence of a fluvial, floodplain system, with seismostratigraphic evidence of lacustrine facies at subsurface. Its distribution occupies the central part of the Sousa and Brejo das Freiras half-grabens, which constitute the main depocenters of the basin. Paleocurrent analysis shows that sediment transport was also from north/NW to south/SE

Análise da deformação pós-Rifte na Bacia do Araripe, Nordeste do Brasil

The Araripe Basin is located over Precambrian terrains of the Borborema Province, being part of Northeast Brazil inner basins. Its origin is related to the fragmentation of the Gondwana supercontinent and consequently opening of South Atlantic during early Cretaceous. The basin has a sedimentary infill encompassing four distinct evolution stages, comprising Paleozoic syneclisis, pre-rift, rift and post-rift. The target of this study comprises the post-rift section of the basin focusing deformational styles which affect evaporates from Ipubi Member of the Santana Formation, which is composed by gypsum and anidrite layers interbedded with shales. These units occur widespread across the basin. In the central part of the basin, near Nova Olinda-Santana do Cariri, evaporites are affected by an essentialy brittle deformation tipified by fibrous gypsum filled fractures, cutting massive layers of gypsum and anidrite. Veins with variable orientations and dips are observed in the region distributed over three main populations: i) a dominant NWSE with shallow to moderate NE dipping population, consisting of gypsum filled veins in which fibers are normal to vein walls; i) NE-SW veins with moderate SE dips containing subhorizontal growth fibers; and iii) N-S veins with shallow E-W dips with fibers oblique to vein walls. In the west portion of the basin, near Trindade-Ipubi-Araripina towns, evaporate layers are dominantly constituted by gypsum/anidrite finely stratified, showing a minor density of veins. These layers are affected by a unique style of deformation, more ductile, typified by gentle to open horizontal normal folding with several tens of meters length and with double plunging NW-SE or NE-SW hinges, configuring domic features. In detail, gypsum/anidrite laminae are affected by metre to decimeter scale close to tight folding, usually kinked, with broken hinges, locally turning into box folds. Veins show NE-SW main directions with shallow NE dips, growth fibers are parallel to vein walls, constituting slickenfibers. This region is marked by faults that affect Araripina Formation with NW-SE, NE-SW and E-W directions. The main structural styles and general orientations of structures which affected the post-rift section of Araripe Basin yielded important kinematic information analysis which led us to infer a E-W to NE-SW extension direction to the northeastern part of the Basin, whereas in the southeastern part, extension occurred in N-S direction. Thus, it was possible to determine a regional kinematic setting, through this analysis, characterizing a NE-SW to ENE-WSW system for the post-rift section, which is compatible with the tension settings for the Sout American Plate since Albian. Local variations at the fluid pressure linked (or not) to sedimentary overload variation define local tension settings. This way, at the northeastern portion of the basin, the post-rift deformation was governed by a setting which σ 1 is sub-horizontal trending NE-SW and, σ 3 is sub-vertical, emphasizing a reverse fault situation. At the southwestern portion however there was characterized a strike slip fault setting, featuring σ 1 trending ENEWSW and σ3 trending NNW-SSE