[pt] Os equipamentos elétricos de alta tensão são peças fundamentais na produção industrial. Porém, os sistemas de isolamento são os que mais apresentam problemas ao longo da vida útil dos nossos equipamentos. Suas propriedades dielétricas são alteradas ao longo do tempo e, desta forma devem ser monitoradas. Dentre as principais anomalias acometidas aos sistemas de isolamento, estão as Descargas Parciais (DP).Elas são resultado do rompimento da rigidez dieétrica do material isolante submetido a um intensivo campo elétrico . Até alguns anos atrás, em virtude da existência dos mecanismos de medição que possibilitassem o armazernamento de dados, muito pouco se efetuava para o acompanhamento das condições apresentadas pelos sistemas de isolamento.Com advento de sistemas digitais,esta limitação foi vencida. No entanto, a obtenção de dados reais e sua posterior avaliação são mecanismos que ainda carecem de um bom número de anos de experiência para sua elucidação. Esse fato advém,principalmente, da dificuldade em obtê-los .Como forma de contornar problema de falta de dados reais, foram desenvolvidas as célualas que têm como características simular os principais tipos de defeitos existentesnos sistemas de isolamento de alta tensão.Essas células são isoladas por materiais dielétricos idênticos ao que são usados em equipamentos elétricos reais. Dessa forma, foi possível a simulação de defeitos e a posterior aquisição, através do método eletromagnético de medição de DP, de um número suficiente de dados. Esses dados foram,então, aplicados no ajuste do sistema de reconhecimento de padrões de DP, onde se faz uso da teoria fractal, como um mecanismo de compactação de dados, por meio das grandezas fractais denominadas de dimensão fractal e lacunaridade, e também das redes neurais artificiais, com a utilização de um algoritmo supervisionado através do modo de treinamento back-propagation.Essa etapa,denominada de laboratorial, foi de fundamental importância para obtenção de conhecimento experimental bastante útil para a aplicação em ambientes reais.Outra fonte de informação também foi disponibilizada e se refere aos níveis de gases encontrados nas amostras de óleo colhidas junto aos transformadores de potência. Esta análise, conhecida como análise cromatográfica,baseia-se na existência de determinados tipos de gases para apontar o tipo de anomalia acometida ao sistema de isolamento do equipamento elétrico.Embora existam alguns métodos capazes de realizar tal diagnóstico, a tese fez uso das informações de um especialista.Essas afirmações foram então empregadas em um sistema neuro-fuzzy hierárquico, que tem como fundamento a extração de regras que relacionam os níveis de gases obtidos pela cromatografia gasosa com o tipo de anomalia existente no sistema de isolamento .Após esse processo um conjunto de transformadores de potência reais foi monitorado através de técnicas de cromatografia e do método eletromagnético.As duas técnicas, portanto, são usadas para estimar a ocorrência de DP nos sistemas de isolamento e, cosequentemente, o nível de degradação dos mesmos.Desta forma, a tese apresenta um sistema de diagnóstico que se utilizada de dados internos ao sistema de isolamento dos equipamentos elétricos baseados na ocorrência de DP. Esse sistema indica, ao seu final, um conceito sobre o atual estado operativo do mesmo, podendo este ser utilizado em um planejamento mais adequado que previna perdas intempestivas. A avaliação de desempenho do modelo, tanto laboratorial quanto em campo, apresentou ídices elevados, culminando em uma confirmação visual interna de um equipamento real, que comprova a eficiência e a importãncia do sistema. / [en] High voltage (HV) power apparatus are fundamental parts in the industrial process. It is also well Known that electrical insulation systems are the parts that present more problems through the life cycle of an HV apparatus. The dielectric properties of materials are altered during operation time and for this reason they should be monitored. Among the main anomalies that can affect the insulation systems are the Partial Discharges (PD). They are result of a partial failure of the dielectric rigidity of the insulating material submitted to an intense electric field.Until recently, probably due to the inexistence of measurement mechanisms that made possible the storage of data, very a little could be done to accompany the actual condition of insulation systems. With the coming of digital systems, this limitation was overcome.However, the obtention of real data and their subsequent evaluation are mechanisms that still will demand a good number of years of experience to perfect . This fact occurs, mainly, due to the difficulty in obtaining those data .As a way to the problem of lack of real data, special cells development with the purpose of simulating the principal types of defects that occur in HV insulation equipment . In that way, it was possible to do both the simulation of the defects and the measurement and acquisition, through the electromagnetic measurement method, of an expressive number of data. Those data were used to adjust a system of pattern recognition of PD, using artificial neural networks, where it is also made use of the fractal theory, as a mechanism of data compression, by measures of fractal dimension and lacunarity. That stage, denomited laboratory, was of fundamental importance to the obtention of experimental . Knowledge very useful to the development of real operating systems .Another source of information that was also available refers to the levels of gases found in oil samples from the interior of power transformers. This analysis, known as analysis of dissolved gases or chromatography, is based on the existence of certain types of gases as an indication of the type of anomaly on the electrical insulation system. Although some mehods exist, capable of accomplishing such diagnosis, the thesis made use of a specialist`s information. Those statements were used then in a hierarchical neuro-fuzzy model, designed method, with the type of anomaly existent in the insulation system. After that process, a real sample of operating HV power apparatus was monitored using the two analysis techniques, the chromatography and the electromagnetic method of PD measurement.Therefore these two techniques, are used to estimate the PD activity in the insulation systems and, consequently, their level of degradation . In resume the thesis presents a diagnosis system that makes use of internal data from the electrical insulation system with base in the PD occurrence. That system indicates, at the end, a concept of its current operative state, being able to be used in a more appropriate planning in order to prevent inopportune losses. The evaluation of the model, as much of simulating as in field, present high indexes and a visual confirmation intern of a real equipment, that proves the efficiency and the importance of system.

Dans la perspective de l’aéronef « plus électrique », l’augmentation de puissance électrique embarquée se traduit par une augmentation de tension. Les tensions envisagées aujourd’hui sont inférieures à 1000 V DC. Mais des valeurs plus élevées peuvent être considérées pour le futur. Il est donc indispensable d’étudier les dégradations prématurées induites par cette élévation de tension sur les équipements existants. Ce travail de thèse, portant spécifiquement sur les câbles aéronautiques, constitue une contribution à cette étude. Les câbles examinés, constitués d’une âme multibrins sur laquelle sont rubanées des couches de PTFE et PI, ont subi différents vieillissements accélérés thermiques statiques et dynamiques, sous humidité, et ce sans ou avec contrainte électrique. Certains vieillissements ont été effectués sur une durée supérieure à 9000 heures. Les décharges partielles (DP) ont été étudiées sur ces câbles en termes de tension d’apparition PDIV et RPDIV. Ces DP peuvent intervenir à l’extérieur ducâble mais également à l’intérieur (pour des tensions plus élevées) dans les interstices d’air entre l’isolant et les brins conducteurs. Cette localisation a été confirmée par un modèle électrostatique. L’effet du vieillissement n’a pu être constaté que sur les décharges internes, avec dans certains cas une réduction significative des valeurs de RPDIV.Des analyses physicochimiques du système d’isolation électrique ont été effectuées ainsi que des radiographies par rayons X. Des modifications chimiques des interfaces du système d’isolation interviennent au cours des vieillissements. Pour les vieillissements les plus poussés (après 9000h sous contrainte thermique à 240°C), ces modifications résultent en la formation de cavités où des DP peuvent prendre place. Enfin, des mesures électrostatiques de potentiel de surface (déclin et retour après neutralisation) ont mis en évidence, bien avant l’observation de cavités, une augmentation de conductivité d’une des couches de l’isolation. / In future "more electric" aircraft, the increase in on board electrical power will result in an increase in voltage. The voltages envisaged today are lower than 1000 V DC, but higher values can be considered in the medium to long term. It is therefore essential to study possible premature degradation of existing equipment induced by this rise in voltage. This thesis work, specifically on aeronautical cables, is a contribution to this goal. The examined cables, consisting of a multi-stranded core on which PTFE and PI layers are wound, have undergone various static and dynamic accelerated thermal aging, under humidity, without or with electrical stress. Aging has been carried out in some cases for more than 9000 hours. Partial discharges (DP) were studied on these cables in terms of the appearance voltage PDIV and RPDIV. These DPs can occur outside the cable but alsoinside (for higher voltages) in the air gaps between the insulation and the conductive strands. This location has been confirmed by an electrostatic model. The effect of aging was only found in the case of internal discharges, with in some cases a significant reduction in RPDIV values.Physicochemical analyses of the electrical insulation system were carried out as well as x-ray radiography. Chemical modifications of the interfaces of the insulation system occur during aging. For the most advanced aging (after 9000h under thermal stress at 240°C), these changes result in the formation of cavities where DP can then take place. Finally, electrostatic measurements of surface potential (decline and return after neutralization) have shown, well before the observation of cavities, an increase in conductivity of one of the layers of the insulation.

[pt] O Monitoramento do Sistema de Isolamento em Máquinas Elétricas de Alta Tensão representa um avanço no que diz respeito ao planejamento operacional de uma indústria. Com posse de dados on-line referentes às condições apresentadas pelos isolamentos, as devidas precauções podem ser tomadas, evitando danos maiores. O trabalho apresentado tem como objetivo principal analisar um sistema de monitoramento desenvolvido pela CEA (Canadian Electrical Association), com suporte técnico da Ontario Hydro. O sistema chamado PDA (Partial Discharge Analyzer) mede, através de acopladores permanentes ou portáteis (capacitores), as Descargas Parciais nos enrolamentos estatóricos de grande máquinas de alta tensão. A quantificação exata das Descargas Parciais são indicadas das reais condições do isolamento. A análise do aparelho foi realizada em conjunção aos dados obtidos, tendo como referência a Companhia Siderúrgica Nacional (CSN). A partir de tais dados, é possível demostrar em que estágio atual de aproveitamento estamos em relação à utilização de tal aparelho e quais são os passos futuros para melhor compreensão das medidas. / [en] The Monitoring of te Isolation System in High Tension Electrical Machines represents na advance in what concerns the operational planning of na industry. Knowing the on- line data referring to the conditions presented by the isolations, the necessary cautions can be taken, avoiding bigger damages. This work has as the main aim to analyze a monitoring system developed by the CEA (Canadian Electrical Association). The system is called PDA ( Partial Discharge Analyzer) and measures, through permanent or portable couplers (capacitors), the Partial Discharges is indicator of the isolation real conditions. The appliance analyses was made with the obtained data, having as reference the CSN. With this data, it is possible to show in what profiting stage of appliance and which are the future steps for a better comprehension of the measures.

Os equipamentos elétricos instalados em linhas de transmissão e distribuição de energia são normalmente submetidos a condições anormais e intensos campos elétricos, que, eventualmente, levam, entre outros fenômenos, as descargas parciais (DPs). Estas descargas têm sido apontadas como uma das principais causas de falhas de equipamentos e envelhecimento precoce. Portanto, detectar DPs se tornou uma questão importante na busca de uma energia elétrica eficiente e confiável. No que se refere a detecção de DPs existem vários sensores que podem ser aplicados, a exemplos: óptico, magnético ou acústico, e cada um deles apresentando vantagens particulares e limitações. Uma das desvantagens de tais sensores é o custo elevado, o que restringe o monitoramento de DPs no âmbito da distribuição de energia mais especificamente em transformadores de potência. Embora, se o foco do monitoramento é apenas detectar a ocorrência de DPs, uma nova classe de sensores acústicos implementados com piezoeletretos pode ser uma alternativa econômica viável. Deste modo, nesta dissertação, foi investigado o comportamento acústico de tais transdutores expostos a diferentes condições de DPs, onde o sensor piezoelétrico foi utilizado na detecção de DPs produzidas por uma configuração de eletrodos ponta - ponta separados por diferentes gaps de ar (único ou múltiplo) e excitado por altas tensões alternadas. As amplitudes dos sinais registrados foram correlacionadas com a distância do gap e com a amplitude da tensão aplicada. A partir dos resultados obtidos foi possível observar que a intensidade do som das DPs, capturado com o transdutor piezoelétrico, está relacionada com o tamanho do gap e da amplitude da tensão, como relatado na literatura. / Electrical equipment installed in power transmission and distribution lines are usually subjected to abnormal conditions and intense electric fields, which eventually lead, among others phenomena, to partial discharges (PDs). These discharges have been pointed as one of the main causes of equipment failures and premature aging. Therefore, detect PDs became an important issue in the prospect of efficient and reliable electric energy. Concerning PD detection there are several sensors that can be employed e.g. optical, magnetic or acoustic, and each of them presenting particular advantages and limitations. One of the drawback of such sensors is their elevated cost, which restricts the PD monitoring within the distribution of energy more specifically in power transformers. Although, if the intention of monitoring is only to detect the PD occurrence a new class of acoustic sensors implemented with piezoelectrets may be a feasible economic alternative. Therefore, in this work was investigated the acoustic behavior of such transducers exposed to different PD conditions, for instance, the piezoelectret sensor was employed on the detection of PD produced by a single or multiple point-to-point electrode setup with different air gaps excited by high AC voltages. The recorded signals amplitudes were correlated with the gap distance and voltage amplitude applied. Based on the results obtained it was observed that the intensity of the DPs sound, captured with the piezoelectric transducer, is related to the size of the gap and voltage amplitude, as reported in the literature.

Os equipamentos elétricos instalados em linhas de transmissão e distribuição de energia são normalmente submetidos a condições anormais e intensos campos elétricos, que, eventualmente, levam, entre outros fenômenos, as descargas parciais (DPs). Estas descargas têm sido apontadas como uma das principais causas de falhas de equipamentos e envelhecimento precoce. Portanto, detectar DPs se tornou uma questão importante na busca de uma energia elétrica eficiente e confiável. No que se refere a detecção de DPs existem vários sensores que podem ser aplicados, a exemplos: óptico, magnético ou acústico, e cada um deles apresentando vantagens particulares e limitações. Uma das desvantagens de tais sensores é o custo elevado, o que restringe o monitoramento de DPs no âmbito da distribuição de energia mais especificamente em transformadores de potência. Embora, se o foco do monitoramento é apenas detectar a ocorrência de DPs, uma nova classe de sensores acústicos implementados com piezoeletretos pode ser uma alternativa econômica viável. Deste modo, nesta dissertação, foi investigado o comportamento acústico de tais transdutores expostos a diferentes condições de DPs, onde o sensor piezoelétrico foi utilizado na detecção de DPs produzidas por uma configuração de eletrodos ponta - ponta separados por diferentes gaps de ar (único ou múltiplo) e excitado por altas tensões alternadas. As amplitudes dos sinais registrados foram correlacionadas com a distância do gap e com a amplitude da tensão aplicada. A partir dos resultados obtidos foi possível observar que a intensidade do som das DPs, capturado com o transdutor piezoelétrico, está relacionada com o tamanho do gap e da amplitude da tensão, como relatado na literatura. / Electrical equipment installed in power transmission and distribution lines are usually subjected to abnormal conditions and intense electric fields, which eventually lead, among others phenomena, to partial discharges (PDs). These discharges have been pointed as one of the main causes of equipment failures and premature aging. Therefore, detect PDs became an important issue in the prospect of efficient and reliable electric energy. Concerning PD detection there are several sensors that can be employed e.g. optical, magnetic or acoustic, and each of them presenting particular advantages and limitations. One of the drawback of such sensors is their elevated cost, which restricts the PD monitoring within the distribution of energy more specifically in power transformers. Although, if the intention of monitoring is only to detect the PD occurrence a new class of acoustic sensors implemented with piezoelectrets may be a feasible economic alternative. Therefore, in this work was investigated the acoustic behavior of such transducers exposed to different PD conditions, for instance, the piezoelectret sensor was employed on the detection of PD produced by a single or multiple point-to-point electrode setup with different air gaps excited by high AC voltages. The recorded signals amplitudes were correlated with the gap distance and voltage amplitude applied. Based on the results obtained it was observed that the intensity of the DPs sound, captured with the piezoelectric transducer, is related to the size of the gap and voltage amplitude, as reported in the literature.

High voltage testing of the stator winding insulation is one of the most recognized methods used to determine the state of degradation in the insulation. HV tests performed at 0.1 Hz do have potential advantages compared to more traditional 50 Hz tests. This thesis therefore aims to perform and compare tan delta, capacitance and partial discharge measurements on stator windings when using a 0.1 Hz voltage source and a more traditional 50 Hz voltage supply. Several associated test parameters with considerable influence on the test results were varied during the tests. An associated data analysis followed that was focused on the differences and similarities of the analyzed parameters and the results due to the differences in frequency. The results show that there are substantial levels of noise present in the partial discharge measurements when utilizing the VLF voltage source. There are also more numerous partial discharges for VLF measurements than for regular power frequency measurements if the same amount of voltage cycles is considered. The generated patterns show similarities with those generated at 50 Hz, but a larger sample base is probably needed for more thorough conclusions. The tan delta/capacitance part of the test do indicate potential advantages compared to power frequency measurements regarding the sensitivity in the measurements.

L'évolution de l'électronique de puissance ces dernières années a entraîné une augmentation de la densité de puissance et une diminution du coût des onduleurs de tension à modulation de largeur d'impulsion (MLI). Ces évolutions ont répandu l'utilisation de convertisseurs de puissance pour les applications de variateurs de vitesse ce qui a permis le développement du concept d' " avion plus électrique ". Ce concept consiste à remplacer un des vecteurs énergétiques (pneumatique ou hydraulique) par l'énergie électrique. Cependant, le développement du réseau électrique a entraîné une augmentation de la tension embarquée, ce qui a conduit à un vieillissement prématuré des équipements électriques embarqués. La forme de tension appliquée, appelée "modulation de largeur d'impulsion" (MLI), est constituée de trains d'impulsions. Avec l'application de ces impulsions, la tension n'est plus distribuée de manière homogène le long du bobinage. Dans ce cas, on pourra observer d'importantes différences de potentiel entre les spires d'une même phase voire entre deux phases du bobinage. En outre, un autre paramètre important provient du type d'enroulement des moteurs utilisés par l'industrie. L'enroulement aléatoire est la technique de bobinage la plus courante pour les moteurs basses tensions car cette méthode présente un faible coût. Le risque induit par ce type d'enroulement est que la première et une des dernières spires de la première bobine peuvent être proches l'une de l'autre. Dans ce cas, jusqu'à 80% de la tension sera supportée par quelques dizaines de microns d'émail, et les systèmes d'isolation existants ne sont pas dimensionnés pour résister à de telles contraintes. L'utilisation de longs câbles reliant l'onduleur au moteur peut aussi provoquer des surtensions importantes aux bornes du moteur. Ce phénomène s'explique par le fait que le câble se comporte comme une ligne de transmission qui n'est pas adaptée en termes d'impédance au bobinage du moteur. De plus, ces importantes différences de potentiel associées à de faibles pressions, présentes dans les zones dépressurisées de l'aéronef, peuvent entraîner l'apparition de décharges partielles. Les décharges partielles sont des décharges électriques qui court-circuitent partiellement l'intervalle entre deux conducteurs. Il existe de nombreuses méthodes de détection bien connues pour les tensions AC et DC, cependant, la détection sous tension de type MLI dans des moteurs basse tension est beaucoup plus complexe. Les signaux de décharge partielle sont en effet intégrés dans le bruit électromagnétique généré par la commutation. Le but de cette thèse est donc de développer un procédé de détection et un procédé de filtrage permettant une détection non intrusive et en fonctionnement (on-line) des décharges partielles dans le domaine aéronautique afin de qualifier les systèmes d'isolation électrique utilisés dans les aéronefs. / The development of power electronics in recent years has led to increase power density and to decrease pulse width modulation (PWM) voltage inverter cost. These developments have expanded the use of power converters for variable speed drive applications which enabled the development of the concept of "more electric aircraft". This concept consists in replacing one of energy carriers (pneumatic or hydraulic) with electrical energy. However, the deployment of electrical energy has increased the onboard voltage, which leads to premature aging of onboard electrical equipment. The shape of the PWM voltage consists of pulse trains. With the application of these pulses, the voltage is no longer homogeneously distributed along the coil. In this case, large differences in potential between the strands are present. In addition, another important parameter derived from the winding type motor used in industry. The random winding is the most common technique for low voltage motors due to its lower cost. The risk generated by this type of winding is that the first and the last turns of the first coil can be facing one another. In this case, up to 80% of the voltage will be supported by a few tens of microns of enamel, and existing insulation systems are not designed to withstand such severe constraints. The use of long cable connecting the inverter to the motor can also cause significant overvoltage at the motor terminals. This phenomenon is explained by the fact that the cable behaves as a transmission line to which the motor coils is not adapted in terms of impedance. In addition, these large potential differences associated with low pressures in the depressurized areas of the aircraft, may cause the occurrence of partial discharge. Partial discharges are electrical discharges that short-circuited partially the gap between two conductors. There are many detection methods well known under AC and DC voltage, however, in the case of the detection under PWM like voltage in low-voltage motors, the detection is much more complex. Partial discharge signals are embedded in the electromagnetic noise generated by the switching. The aim of this thesis is to develop a detection method and filtering method enabling a non-intrusive and an "on-line" partial discharges detection in the aeronautical field in order to qualify the electrical insulation systems used in aircraft.

Submitted by DANILO DE MELO BRUNINI null (dbrunini@gmail.com) on 2017-07-14T02:28:32Z No. of bitstreams: 1 Dissertacao_Final_DaniloBrunini.pdf: 4098580 bytes, checksum: f552cf864fb92ba3889ebf437d9c11d7 (MD5) / Approved for entry into archive by Monique Sasaki (sayumi_sasaki@hotmail.com) on 2017-07-14T19:08:26Z (GMT) No. of bitstreams: 1 brunini_dm_me_bauru.pdf: 4098580 bytes, checksum: f552cf864fb92ba3889ebf437d9c11d7 (MD5) / Made available in DSpace on 2017-07-14T19:08:26Z (GMT). No. of bitstreams: 1 brunini_dm_me_bauru.pdf: 4098580 bytes, checksum: f552cf864fb92ba3889ebf437d9c11d7 (MD5) Previous issue date: 2017-05-31 / Os transformadores são equipamentos importantes do sistema elétrico de potência, possuem alto custo e suas falhas tem influência direta na qualidade da energia entregue aos consumidores. Uma das principais causas de falhas em transformadores imersos em líquido isolante, as descargas parciais, advém da degradação física e química do sistema de isolação devido à diversos fatores tais como sobrecarga, cargas não-lineares, chaveamento e superaquecimento. Essas descargas parciais aceleram a degradação do dielétrico do transformador e podem levar à destruição do equipamento, ocasionando elevado prejuízo financeiro. Dessa forma, são necessárias ações de prevenção de falhas causadas por descargas parciais em transformadores, através de métodos de monitoramento e localização. Este trabalho teve por objetivo apresentar um método de localização de descargas parciais em transformadores de potência imersos em óleo mineral isolante utilizando o método de emissão acústica e sistemas inteligentes do tipo redes neurais artificiais e algoritmos genéticos. Foram aplicadas métricas de processamento de sinais aos sinais acústicos gerados a partir de descargas parciais e obtidos através de sensores piezelétricos de baixo custo instalados no lado externo do tanque do transformador. Estas métricas foram utilizadas para treinamento das redes neurais a fim de obter a distância euclidiana entre os sensores e as descargas parciais. Essas distâncias euclidianas foram utilizadas em um sistema não-linear de localização o qual foi solucionado através de um algoritmo genético a fim de obter as coordenadas tridimensionais da descarga parcial. A análise dos resultados obtidos nas etapas de treinamento das redes neurais e execução do algoritmo genético foi realizada através de critérios estatísticos como erro absoluto médio, erro relativo percentual, desvio padrão e coeficiente de correlação. Esta técnica de localização mostrou resultados promissores uma vez que as coordenadas tridimensionais de duas descargas parciais, escolhidas para validação, apresentaram erros absolutos médios inferiores a 3 cm. / Transformers are important devices of the electric power system, which have high cost and their failures have a direct influence on the power quality delivered to the consumers. One of the main causes of failures in oil-immersed transformers, the partial discharges, comes from the physical and chemical degradation of the insulation system due to several factors such as overload, non-linear loads, switching and overheating. These partial discharges accelerate the degradation of the transformer dielectric and they can lead to the destruction of the equipment, causing high financial losses. Thus, actions are necessary to prevent faults caused by partial discharges in transformers, through monitoring and locating methods. The aim of this work was to present a method for locating partial discharges in oil-immersed power transformers using the acoustic emission method and intelligent systems such as artificial neural networks and genetic algorithms. Signal processing metrics were applied to the acoustic signals generated from partial discharges and obtained by low-cost piezoelectric sensors installed on the external side of the transformer tank. These metrics were used to train the neural networks in order to obtain the euclidean distance between the sensors and the partial discharges. These euclidean distances were used in a nonlinear location system, which was solved through a genetic algorithm in order to obtain the three-dimensional coordinates of the partial discharge. The analysis of the results obtained from the stages of neural networks training and genetic algorithm execution was performed through statistical criteria such as mean absolute error, percentage relative error, standard deviation and correlation coefficient. This localization technique showed promising results since the three-dimensional coordinates of two partial discharges, chosen for validation, presented mean absolute errors of less than 3 cm.

No description available.

No description available.