Aplicação de sistemas multi-classificadores no diagnóstico de falhas em motores de indução trifásicos

Equipment maintenance is the major cost factor in industrial plants, it is very important the development of fault predict techniques. Three-phase induction motors are key electrical equipments used in industrial applications mainly because presents low cost and large robustness, however, it isn t protected from other fault types such as shorted winding and broken bars. Several acquisition ways, processing and signal analysis are applied to improve its diagnosis. More efficient techniques use current sensors and its signature analysis. In this dissertation, starting of these sensors, it is to make signal analysis through Park s vector that provides a good visualization capability. Faults data acquisition is an arduous task; in this way, it is developed a methodology for data base construction. Park s transformer is applied into stationary reference for machine modeling of the machine s differential equations solution. Faults detection needs a detailed analysis of variables and its influences that becomes the diagnosis more complex. The tasks of pattern recognition allow that systems are automatically generated, based in patterns and data concepts, in the majority cases undetectable for specialists, helping decision tasks. Classifiers algorithms with diverse learning paradigms: k-Neighborhood, Neural Networks, Decision Trees and Naïves Bayes are used to patterns recognition of machines faults. Multi-classifier systems are used to improve classification errors. It inspected the algorithms homogeneous: Bagging and Boosting and heterogeneous: Vote, Stacking and Stacking C. Results present the effectiveness of constructed model to faults modeling, such as the possibility of using multi-classifiers algorithm on faults classification

Identificação de uma planta de corrente de um motor de indução utilizando redes de base radial

The present work describes the use of a mathematical tool to solve problems arising from control theory, including the identification, analysis of the phase portrait and stability, as well as the temporal evolution of the plant s current induction motor. The system identification is an area of mathematical modeling that has as its objective the study of techniques which can determine a dynamic model in representing a real system. The tool used in the identification and analysis of nonlinear dynamical system is the Radial Basis Function (RBF). The process or plant that is used has a mathematical model unknown, but belongs to a particular class that contains an internal dynamics that can be modeled.Will be presented as contributions to the analysis of asymptotic stability of the RBF. The identification using radial basis function is demonstrated through computer simulations from a real data set obtained from the plant

Desacoplamento de um gerador síncrono através de um controle adaptativo por modelo de referência baseado em funções de Base radial

An alternative nonlinear technique for decoupling and control is presented. This technique is based on a RBF (Radial Basis Functions) neural network and it is applied to the synchronous generator model. The synchronous generator is a coupled system, in other words, a change at one input variable of the system, changes more than one output. The RBF network will perform the decoupling, separating the control of the following outputs variables: the load angle and flux linkage in the field winding. This technique does not require knowledge of the system parameters and, due the nature of radial basis functions, it shows itself stable to parametric uncertainties, disturbances and simpler when it is applied in control. The RBF decoupler is designed in this work for decouple a nonlinear MIMO system with two inputs and two outputs. The weights between hidden and output layer are modified online, using an adaptive law in real time. The adaptive law is developed by Lyapunov s Method. A decoupling adaptive controller uses the errors between system outputs and model outputs, and filtered outputs of the system to produce control signals. The RBF network forces each outputs of generator to behave like reference model. When the RBF approaches adequately control signals, the system decoupling is achieved. A mathematical proof and analysis are showed. Simulations are presented to show the performance and robustness of the RBF network

Sistema para detecção e diagnóstico de falhas em motores elétricos de indução utilizando lógica fuzzy

Induction motors are one of the most important equipment of modern industry. However, in many situations, are subject to inadequate conditions as high temperatures and pressures, load variations and constant vibrations, for example. Such conditions, leaving them more susceptible to failures, either external or internal in nature, unwanted in the industrial process. In this context, predictive maintenance plays an important role, where the detection and diagnosis of faults in a timely manner enables the increase of time of the engine and the possibiity of reducing costs, caused mainly by stopping the production and corrective maintenance the motor itself. In this juncture, this work proposes the design of a system that is able to detect and diagnose faults in induction motors, from the collection of electrical line voltage and current, and also the measurement of engine speed. This information will use as input to a fuzzy inference system based on rules that find and classify a failure from the variation of thess quantities

Compressão auto-adaptativa de imagens coloridas

Image compress consists in represent by small amount of data, without loss a visual quality. Data compression is important when large images are used, for example satellite image. Full color digital images typically use 24 bits to specify the color of each pixel of the Images with 8 bits for each of the primary components, red, green and blue (RGB). Compress an image with three or more bands (multispectral) is fundamental to reduce the transmission time, process time and record time. Because many applications need images, that compression image data is important: medical image, satellite image, sensor etc. In this work a new compression color images method is proposed. This method is based in measure of information of each band. This technique is called by Self-Adaptive Compression (S.A.C.) and each band of image is compressed with a different threshold, for preserve information with better result. SAC do a large compression in large redundancy bands, that is, lower information and soft compression to bands with bigger amount of information. Two image transforms are used in this technique: Discrete Cosine Transform (DCT) and Principal Component Analysis (PCA). Primary step is convert data to new bands without relationship, with PCA. Later Apply DCT in each band. Data Loss is doing when a threshold discarding any coefficients. This threshold is calculated with two elements: PCA result and a parameter user. Parameters user define a compression tax. The system produce three different thresholds, one to each band of image, that is proportional of amount information. For image reconstruction is realized DCT and PCA inverse. SAC was compared with JPEG (Joint Photographic Experts Group) standard and YIQ compression and better results are obtain, in MSE (Mean Square Root). Tests shown that SAC has better quality in hard compressions. With two advantages: (a) like is adaptive is sensible to image type, that is, presents good results to divers images kinds (synthetic, landscapes, people etc., and, (b) it need only one parameters user, that is, just letter human intervention is required

Estudo avaliativo de um algoritmo genético auto-organizável e multiobjetivo utilizando aprendizado de máquina para aplicações de telecomunicações

This paper presents an evaluative study about the effects of using a machine learning technique on the main features of a self-organizing and multiobjective genetic algorithm (GA). A typical GA can be seen as a search technique which is usually applied in problems involving no polynomial complexity. Originally, these algorithms were designed to create methods that seek acceptable solutions to problems where the global optimum is inaccessible or difficult to obtain. At first, the GAs considered only one evaluation function and a single objective optimization. Today, however, implementations that consider several optimization objectives simultaneously (multiobjective algorithms) are common, besides allowing the change of many components of the algorithm dynamically (self-organizing algorithms). At the same time, they are also common combinations of GAs with machine learning techniques to improve some of its characteristics of performance and use. In this work, a GA with a machine learning technique was analyzed and applied in a antenna design. We used a variant of bicubic interpolation technique, called 2D Spline, as machine learning technique to estimate the behavior of a dynamic fitness function, based on the knowledge obtained from a set of laboratory experiments. This fitness function is also called evaluation function and, it is responsible for determining the fitness degree of a candidate solution (individual), in relation to others in the same population. The algorithm can be applied in many areas, including in the field of telecommunications, as projects of antennas and frequency selective surfaces. In this particular work, the presented algorithm was developed to optimize the design of a microstrip antenna, usually used in wireless communication systems for application in Ultra-Wideband (UWB). The algorithm allowed the optimization of two variables of geometry antenna - the length (Ls) and width (Ws) a slit in the ground plane with respect to three objectives: radiated signal bandwidth, return loss and central frequency deviation. These two dimensions (Ws and Ls) are used as variables in three different interpolation functions, one Spline for each optimization objective, to compose a multiobjective and aggregate fitness function. The final result proposed by the algorithm was compared with the simulation program result and the measured result of a physical prototype of the antenna built in the laboratory. In the present study, the algorithm was analyzed with respect to their success degree in relation to four important characteristics of a self-organizing multiobjective GA: performance, flexibility, scalability and accuracy. At the end of the study, it was observed a time increase in algorithm execution in comparison to a common GA, due to the time required for the machine learning process. On the plus side, we notice a sensitive gain with respect to flexibility and accuracy of results, and a prosperous path that indicates directions to the algorithm to allow the optimization problems with "η" variables

Viabilidade da Utilização de Máquinas de Indução Convencionais como Motores sem Mancais Mecânicos

Electrical Motors transform electrical energy into mechanic energy in a relatively easy way. In some specific applications, there is a need for electrical motors to function with noncontaminated fluids, in high speed systems, under inhospitable conditions, or yet, in local of difficult access and considerable depth. In these cases, the motors with mechanical bearings are not adequate as their wear give rise to maintenance. A possible solution for these problems stems from two different alternatives: motors with magnetic bearings, that increase the length of the machine (not convenient), and the bearingless motors that aggregate compactness. Induction motors have been used more and more in research, as they confer more robustness to bearingless motors compared to other types of machines building with others motors. The research that has already been carried out with bearingless induction motors utilized prototypes that had their structures of stator/rotor modified, that differ most of the times from the conventional induction motors. The goal of this work is to study the viability of the use of conventional induction Motors for the beringless motors applications, pointing out the types of Motors of this category that can be more useful. The study uses the Finite Elements Method (FEM). As a means of validation, a conventional induction motor with squirrel-cage rotor was successfully used for the beringless motor application of the divided winding type, confirming the proposed thesis. The controlling system was implemented in a Digital Signal Processor (DSP)

Controle vetorial para velocidade de um motor de indução trifásico utilizando estimador filtro de Kalman

This paper describes the study, computer simulation and feasibility of implementation of vector control speed of an induction motor using for this purpose the Extended Kalman Filter as an estimator of rotor flux. The motivation for such work is the use of a control system that requires no sensors on the machine shaft, thus providing a considerable cost reduction of drives and their maintenance, increased reliability, robustness and noise immunity as compared to control systems with conventional sensors

Contribuições a técnicas de agrupamento e visualização de dados multivariados utilizando mapas auto-organizáveis

Self-organizing maps (SOM) are artificial neural networks widely used in the data mining field, mainly because they constitute a dimensionality reduction technique given the fixed grid of neurons associated with the network. In order to properly the partition and visualize the SOM network, the various methods available in the literature must be applied in a post-processing stage, that consists of inferring, through its neurons, relevant characteristics of the data set. In general, such processing applied to the network neurons, instead of the entire database, reduces the computational costs due to vector quantization. This work proposes a post-processing of the SOM neurons in the input and output spaces, combining visualization techniques with algorithms based on gravitational forces and the search for the shortest path with the greatest reward. Such methods take into account the connection strength between neighbouring neurons and characteristics of pattern density and distances among neurons, both associated with the position that the neurons occupy in the data space after training the network. Thus, the goal consists of defining more clearly the arrangement of the clusters present in the data. Experiments were carried out so as to evaluate the proposed methods using various artificially generated data sets, as well as real world data sets. The results obtained were compared with those from a number of well-known methods existent in the literature

Protótipo de uma unidade com tri-geração de energia para utilizações remotas: aplicação de módulo secondutivo gerador termoelétrico

The generation for termoeletricity is characterized as a solid process of conversion of thermal energy (heat) in electric without the necessity of mobile parts. Although the conversion process is of low efficiency the system presents high degree of trustworthiness and low requisite of maintenance and durability. Its principle is based on the studies of termogeneration carried through by Thomas Seebeck in 1800. The frank development of the technologies of solid state for termoeletricity generation, the necessity of the best exploitation of the energy, also with incentive the cogeneration processes, the reduction of the ambient impact allies to the development of modules semiconductors of high efficiency, converge to the use of the thermoeletric generation through components of solid state in remote applications. The work presents the development, construction and performance evaluation of an prototype, in pilot scale, for energy tri-generation aiming at application in remote areas. The unit is composed of a gas lamp as primary source of energy, a module commercial semiconductor for thermoelectric generation and a shirt for production of the luminosity. The project of the device made compatible a headstock for adaptation in the gas lamp, a hot source for adaptation of the module, an exchanger of to be used heat as cold source and to compose first stage of cogeneration, an exchanger of tubular heat to compose second stage of cogeneration, the elaboration of a converter dc-dc type push pull, adequacy of a system of acquisition of temperature. It was become fullfilled assembly of the prototype in group of benches for tests and assay in the full load condition in order to evaluate its efficiency, had been carried through energy balance of the unit. The prototype presented an electric efficiency of 0,73%, thermal of 56,55%, illumination of 1,35% and global of 58,62%. The developed prototype, as the adopted methodology of assay had also taken care of to the considered objectives, making possible the attainment of conclusive results concerning to the experiment. Optimization in the system of setting of the semicondutor module, improvement in the thermal insulation and design of the prototype and system of protection to the user are suggestions to become it a commercial product

Ação de tinturas e óleos essenciais de plantas medicinais sobre o crestamento bacteriano comum do feijoeiro e na produção de proteínas de indução de resistência

A exploração da atividade biológica de compostos secundários presentes nas tinturas ou em óleos essenciais de plantas podem representar, ao lado da indução de resistência, mais uma forma potencial de controle de doenças em plantas cultivadas. O presente trabalho objetivou avaliar o potencial de tinturas de Lippia alba, Lippia sidoides, Mikania glomerata, Equisetum sp. e Hedera helix e óleos essenciais de Rosmarinus officinalis e Cinnamomum zeylanicum nas atividades in vitro, in vivo e na produção de proteínas na indução de resistência, em plantas de feijão vagem cultivar Bragança. Os resultados obtidos demonstraram que as tinturas de L. alba e L. sidoides e os óleos essenciais (R. officinalis e C. zeylanicum) apresentaram atividade in vitro aos isolados de Xanthomonas axonopodis pv. phaseoli. Todas as tinturas ensaiadas apresentaram menores valores do progresso da doença (AACPD), em relação à testemunha, merecendo destaque a tintura de L. alba, que estavam correlacionadas com os maiores teores de polifenoloxidase, peroxidase e proteínas solúveis totais, evidenciando uma possível indução de resistência. Os óleos essenciais não apresentaram diferença na AACPD e nem na indução de proteínas.

Análise da indução de fluxo de ar por convecção livre em chaminé solar

Experiments were performed to study the effect of surface properties of a vertical channel heated by a source of thermal radiation to induce air flow through convection. Two channels (solar chimney prototype) were built with glass plates, forming a structure of truncated pyramidal geometry. We considered two surface finishes: transparent and opaque. Each stack was mounted on a base of thermal energy absorber with a central opening for passage of air, and subjected to heating by a radiant source comprises a bank of incandescent bulbs and were performed field tests. Thermocouples were fixed on the bases and on the walls of chimneys and then connected to a data acquisition system in computer. The air flow within the chimney, the speed and temperature were measured using a hot wire anemometer. Five experiments were performed for each stack in which convective flows were recorded with values ranging from 17 m³ / h and 22 m³ / h and air flow velocities ranging from 0.38 m / s and 0.56 m / s for the laboratory tests and air velocities between 0.6 m/s and 1.1m/s and convective airflows between 650 m³/h and 1150 m³/h for the field tests. The test data were compared to those obtained by semi-empirical equations, which are valid for air flow induced into channels and simulated data from 1st Thermodynamics equation. It was found that the chimney with transparent walls induced more intense convective flows than the chimney with matte finish. Based on the results obtained can be proposed for the implementation of prototype to exhaust fumes, mists, gases, vapors, mists and dusts in industrial environments, to help promote ventilation and air renewal in built environments and for drying materials, fruits and seeds

Desenho e Construção de um protótipo gerador de jato de plasma frio a pressão atmosférica para aplicações biomédicas

Research for better performance materials in biomedical applications are constants. Thus recent studies aimed at the development of new techniques for modification of surfaces. The low pressure plasma has been highlighted for its versatility and for being environmentally friendly, achieving good results in the modification of physic chemical properties of materials. However, it is requires an expensive vacuum system and cannot able to generate superficial changes in specific regions. Furthermore, it is limits their use in polymeric materials and sensitive terms due to high process temperatures. Therefore, new techniques capable of generating cold plasma at atmospheric pressure (APPJ) were created. In order to perform surface treatments on biomaterials in specific regions was built a prototype capable of generating a cold plasma jet. The prototype plasma generator consists of a high voltage source, a support arm, sample port and a nozzle through which the ionized argon. The device was formed to a dielectric tube and two electrodes. This work was varied some parameters such as position between electrodes, voltage and electrical frequency to verify the behavior of glow discharges. The disc of titanium was polished and there was a surface modification. The power consumed, length, intensity and surface modifications of titanium were analyzed. The energy consumed during the discharges was observed by the Lissajous figure method. To check the length of the jets was realized with Image Pro Plus software. The modifications of the titanium surfaces were observed by optical microscopy (OM ) and atomic force microscopy (AFM ). The study showed that variations of the parameters such as voltage, frequency and geometric position between the electrodes influence the formation of the plasma jet. It was concluded that the plasma jet near room temperature and atmospheric pressure was able to cause modifications in titanium surface

Ineficiência de acibenzolar-S-methyl na indução de resistência de feijoeiro comum à murcha-de-Curtobacterium

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Estudo da influência de pré-tratamentos de dois resíduos lignocelulósicos (bagaço do pedúnculo de caju e casca de coco) utilizados como substrato na indução à síntese de enzimas celulolíticas

Nowadays generation ethanol second, that t is obtained from fermentation of sugars of hydrolyses of cellulose, is gaining attention worldwide as a viable alternative to petroleum mainly for being a renewable resource. The increase of first generation ethanol production i.e. that obtained from sugar-cane molasses could lead to a reduction of lands sustainable for crops and food production. However, second generation ethanol needs technologic pathway for reduce the bottlenecks as production of enzymes to hydrolysis the cellulose to glucose i.e. the cellulases as well as the development of efficient biomass pretreatment and of low-cost. In this work Trichoderma reesei ATCC 2768 was cultivated under submerged fermentation to produce cellulases using as substrates waste of lignocellulosic material such as cashew apple bagasse as well as coconut bagasse with and without pretreatment. For pretreatment the bagasses were treated with 1 M NaOH and by explosion at high pressure. Enzyme production was carried out in shaker (temperature of 27ºC, 150 rpm and initial medium pH of 4.8). Results showed that T.reesei ATCC 2768 showed the higher cellulase production when the cashew apple bagasse was treated with 1M NaOH (2.160 UI/mL of CMCase and 0.215 UI/mL of FPase), in which the conversion of cellulose, in terms of total reducing sugars, was of 98.38%, when compared to pretreatment by explosion at high pressure (0.853 UI/mL of CMCase and 0.172 UI/mL of Fpase) showing a conversion of 47.39% of total reducing sugars. Cellulase production is lower for the medium containing coconut bagasse treated with 1M NaOH (0.480 UI/mL of CMcase and 0.073 UI/mL of FPase), giving a conversion of 49.5% in terms of total reducing sugars. Cashew apple bagasse without pretreatment showed cellulase activities lower (0.535 UI/mL of CMCase and 0,152 UI/mL of FPase) then pretreated bagasse while the coconut bagasse without pretreatment did not show any enzymatic activity. Maximum cell concentration was obtained using cashew nut bagasse as well as coconut shell bagasse treated with 1M NaOH, with 2.92 g/L and 1.97 g/L, respectively. These were higher than for the experiments in which the substrates were treated by explosion at high pressure, 1.93 g/L and 1.17 g/L. Cashew apple is a potential inducer for cellulolytic enzymes synthysis showing better results than coconut bagasse. Pretreatment improves the process for the cellulolytic enzyme production