No contexto metodológico desse trabalho, foram desenvolvidas as tecnologias lógicas, baseadas em arquiteturas de sistemas inteligentes, que auxiliem nos diagnósticos de avarias em transformadores de transmissão. O sistema desenvolvido tem como dados de entrada os resultados de ensaios de isolação, de relação de transformação, do fator de potência da isolação, de ensaios de tensão induzida, além de outros e, por meio de técnicas de inferência, indicarão a existência de possíveis avarias que devem ser averiguadas (de forma mais detalhada) antes de se retornar o transformador ao serviço. A particularidade que caracteriza a inovação sobre este assunto está justamente na elaboração de um novo ferramental, a ser disponibilizado por meio de um software inteligente de suporte à decisão, o qual produzirá respostas que permitirão o completo diagnóstico de falhas e avarias em transformadores de transmissão submetidos a esforços eletromagnéticos severos. As respostas serão produzidas a partir da análise integrada de resultados advindos de módulos inteligentes incumbidos de apoiar os diversos ensaios a serem realizados no equipamento. Assim, será possível estimar, inclusive, qual o momento de se proceder com a manutenção preventiva no equipamento. / In methodological context of this work, the logical technologies were developed based on smart systems architectures, which help in diagnosis of faults in transmission transformers. The developed system has as data input the results of insulation tests, the transformation ratio of the insulation power factor of induced voltage test, and others, and by inference techniques, indicate the existence of possible faults that must be ascertained (in more detail) before the processor returns to service. The special featuring innovation on this subject is exactly in the drafting of a new tooling, to be made available through intelligent decision support software, which will produce answers that will allow the full fault diagnosis and failure in transmission submitted transformers the severe electromagnetic efforts. The answers will be produced from the integrated analysis of results arising from intelligent modules responsible for assisting the various tests to be performed on the equipment. Thus, you can estimate, even when it\'s time to proceed with preventive maintenance on the equipment.

No contexto metodológico desse trabalho, foram desenvolvidas as tecnologias lógicas, baseadas em arquiteturas de sistemas inteligentes, que auxiliem nos diagnósticos de avarias em transformadores de transmissão. O sistema desenvolvido tem como dados de entrada os resultados de ensaios de isolação, de relação de transformação, do fator de potência da isolação, de ensaios de tensão induzida, além de outros e, por meio de técnicas de inferência, indicarão a existência de possíveis avarias que devem ser averiguadas (de forma mais detalhada) antes de se retornar o transformador ao serviço. A particularidade que caracteriza a inovação sobre este assunto está justamente na elaboração de um novo ferramental, a ser disponibilizado por meio de um software inteligente de suporte à decisão, o qual produzirá respostas que permitirão o completo diagnóstico de falhas e avarias em transformadores de transmissão submetidos a esforços eletromagnéticos severos. As respostas serão produzidas a partir da análise integrada de resultados advindos de módulos inteligentes incumbidos de apoiar os diversos ensaios a serem realizados no equipamento. Assim, será possível estimar, inclusive, qual o momento de se proceder com a manutenção preventiva no equipamento. / In methodological context of this work, the logical technologies were developed based on smart systems architectures, which help in diagnosis of faults in transmission transformers. The developed system has as data input the results of insulation tests, the transformation ratio of the insulation power factor of induced voltage test, and others, and by inference techniques, indicate the existence of possible faults that must be ascertained (in more detail) before the processor returns to service. The special featuring innovation on this subject is exactly in the drafting of a new tooling, to be made available through intelligent decision support software, which will produce answers that will allow the full fault diagnosis and failure in transmission submitted transformers the severe electromagnetic efforts. The answers will be produced from the integrated analysis of results arising from intelligent modules responsible for assisting the various tests to be performed on the equipment. Thus, you can estimate, even when it\'s time to proceed with preventive maintenance on the equipment.

A power supply is an essential part of all electronic devices. A switching mode power supply is a light weight power solution for most modern electronic equipment. The high frequency transformer is the backbone of modern switched mode power supplies. The skin effect and proximity effects are major problems in high frequency transformer design, because of induced eddy currents. These effects can result in transformers being destroyed and losing their power transferring function at high frequencies. Therefore, eddy currents are unwanted currents in high frequency transformers. Leakage inductance and the unbalanced magnetic flux distribution are two further obstacles for the development of high frequency transformers. Winding structures of power transformers are also a critical part of transformer design and manufacture, especially for high frequency applications. A new planar transformer with a helical winding structure has been designed and can maintain the advantages of existing planar transformers and significantly reduce the eddy currents in the windings. The maximum eddy current density can be reduced to 27% of the density of the planar transformer with meander type winding structure and 33% of the density of the transformer with circular spiral winding structure at an operating frequency of 1MHz. The voltage ratio of the transformer with helical winding structure is effectively improved to 150% of the voltage ratio of the planar transformer with circular spiral coils. With the evenly distributed magnetic flux around the winding, the planar transformer with helical winding structure is excellent for high frequency switching mode power supplies in the 21st Century.

No description available.

Frequency response analysis (FRA) of transformers is universally accepted as a highly sensitive tool to detect deformations in its windings. This is evident from the fact that customized commercial equipment (popularly called FRA or SFRA instruments) are used and recently the IEEE has issued a draft trial-use guide. Nevertheless, use of FRA is still limited to only detection and there is little progress towards its use for localization of winding deformation. Toward this end, a possible approach would be to compare the healthy and deformed systems in a suitable domain, e.g., their respective models could be compared. In this context, the mutually-coupled ladder network is ideally suited because not only does it map the length of the winding to sections of the ladder network, but, also inherently captures all subtle intricacies of winding behaviour under lightning impulse excitations insofar as the terminal response, internal oscillations and voltage distributions are concerned. The task of constructing a ladder network from frequency response is not trivial, and so exploration of newer methods is imperative. A system can comprehensively be characterized by its frequency response. With this as the starting point, many approaches exist to construct the corresponding rational function (in s-domain). But, the subsequent step of converting this rational function into a physically-realizable mutually-coupled ladder network has, as yet, remained elusive. A critical analysis of the circuit synthesis literature reveals that there exists no analytical procedure to achieve this task, a fact unequivocally stated by Guillemin in his seminal book "Synthesis of Passive Networks". In recent years, use of iterative methods to synthesize such ladder networks has also been attempted with some degree of success. However, there exists a lot of scope for improvement. Based on this summary, the objectives of this thesis are as follows- _ Development of an analytical procedure, if possible, to synthesize a mutually-coupled ladder network starting from the s-domain representation of the frequency response _ Construction of a nearly-unique, mutually-coupled ladder network employing constrained optimization technique and using frequency response as input, with time-efficiency, physical realizability and repeatability as its features In Chapter 2, analytical solution is presented to convert a given driving-point impedance function (in s-domain) into a physically-realizable ladder network with inductive couplings (between any two sections) and losses considered. The number of sections in the ladder network can vary, but, its topology is assumed fixed. A study of the coefficients of the numerator and denominator polynomials of the driving-point impedance function of the ladder network, for increasing number of sections, led to the identification of certain coefficients, which exhibit very special properties. Generalized expressions for these specific coefficients have also been derived. Exploiting their properties, it is demonstrated that the synthesis method essentially turns out to be an exercise of solving a set of linear, simultaneous, algebraic equations, whose solution directly yields the ladder network elements. The proposed solution is novel, simple, and guarantees a unique network. Presently, the formulation can synthesize a unique ladder network up to 6-sections. Although it is an analytical solution, there are issues which prevent its implementation with actual FRA data. Keeping the above aspect in mind, the second part of the thesis presents results of employing an artificial bee colony search algorithm for synthesizing a mutuallycoupled lumped-parameter ladder network representation of a transformer winding, starting from its measured magnitude frequency response. The bee colony algorithm is modified by defining constraints and bounds to restrict the search-space and thus ensure synthesis of a nearly-unique ladder network, corresponding to each frequency response. Ensuring near-uniqueness while constructing the reference circuit (i.e., a uniform healthy winding) is the objective. The proposed method is easy to implement, time-efficient, ensures physical realizability and problem associated with supply of initial guess in existing methods is circumvented. Experiments were performed on two types of actual, single, isolated transformer windings (continuous-disc and interleaveddisc) and the results are encouraging. Further details are presented in the thesis.

With the rapid advancements in the field of Natural Language Processing and Artificial Intelligence, several aspects of its use cases and impact on productivity are largely unexplored. Many of the recent machine learning models are based on an architecture called Transformers that allows for faster computation and for more context to be preserved. At the same time, tech companies face the dilemmas of how to navigate their code bases, spanning over millions of lines of code. The aim of this thesis is to investigate whether the implementation and fine-tuning of a Transformers-based model can be utilised to improve the code search process in a tech company, leading to improvements in developer productivity. Specifically, the thesis will evaluate the effectiveness of such implementation from a productivity perspective in terms of velocity, quality, and satisfaction. The research uses a mixed method design consisting of two distinct methodologies as well as analyses of quantitative and qualitative data. To assess the level of accuracy that can be obtained by optimising a Transformers-based model on internal data, an evaluative experiment with various internal datasets was conducted. The second methodology applied was a usability test, investigating potential impacts on velocity, quality, and satisfaction by testing a contextual code-search prototype with developers. Data from the tests was analysed through a heat map-, trade-off- and template analysis. Results indicate that a Transformers-based modes can be optimised for code search on internal data and has the potential to improve code search from the aspects of velocity, quality, and satisfaction. / Den snabba utvecklingen inom områdena för Språlteknologi och Artificiell Intelligens har visat på stora framgångar men också lämnat utrymme för ytterligare forskning på dess användningsområden och inverkan på produktivitet. Många av de senaste maskininlärningsmodellerna använder sig av en arkitektur kallad Transformers. Denna arkitektur möjliggör snabbare bearbetning av data och är bättre på att ta hänsyn till kontext. Samtidigt står tech-bolagen inför stora utmaningar i att navigera sina kodbaser, vilka består av flera miljoner rader kod. Målet med denna uppsats är att undersöka huruvida implementering och fine-tuning av en Transformers-baserad modell kan användas för att förbättra kodsökningsprocessen i ett tech-bolag och därmed leda till förbättring av utvecklares produktivitet. Mer specifikt utvärderar uppsatsen en sådan implementation från ett produktivitetsperspektiv med hänsyn till dimensioner såsom hastighet, kvalitet och tillfredställelse. Uppsatsen använder sig av en mixad metodologi bestående av två distinkta metoder samt analys av både kvalitativ och kvantitativ data. För att utvärdera nivån av noggrannhet som kan uppnås genom implementation och optimering av en Transformers-baserad modell på intern data, genomfördes experiment på olika interna dataset. Den andra metoden består av ett usability test för att undersöka potentiella effekter på hastighet, kvalitet och tillfredställelse genom att testa en kontextuell kodsökningsprototyp med utvecklare. Data från testen analyserades genom en heat map, trade-off och template analys. Resultaten indikerar att en Transformers-baserad modell kan optimeras för kodsökningpå intern data och har möjlighet att förbättra kodsökning från perspektiven hastighet, kvalitet och tillfredställelse.

As our lives become more and more digital, our exposure to certain phenomena increases, one of which is hate speech. Thus, automatic hate speech identification is needed. This thesis explores three strategies for hate speech detection for cross­-domain scenarios: using a model trained on annotated data for a previous domain, a model trained on data from a novel methodology of automatic data derivation (with cross­-domain scenarios in mind), and using ChatGPT as a domain-­agnostic classifier. Results showed that cross-­domain scenarios remain a challenge for hate speech detection, results which are discussed out of both technical and ethical considera­tions. / I takt med att våra liv blir allt mer digitala ökar vår exponering för vissa fenomen, varav ett är näthat. Därför behövs automatisk identifikation av näthat. Denna uppsats utforskar tre strategier för att upptäcka hatretorik för korsdomänscenarion: att använda inferenserna av en modell trä­nad på annoterad data för en tidigare domän, att använda inferenserna av en modell tränad på data från en ny metodologi för automatisk dataderivatisering som föreslås (för denna avhandling), samt att använda ChatGPT som klassifierare. Resultaten visade att korsdomänscenarion fort­farande utgör en utmaning för upptäckt av näthat, resultat som diskuteras utifrån både tekniska och etiska överväganden.

Having computer systems capable of answering questions has been a goal within Natural Language Processing research for many years. Machine Learning systems have recently become increasingly proficient at this task with large language models obtaining state-of-the-art performance. Retriever-reader architectures have become a powerful approach for building systems that enable users to enter questions and get factual answers from a corpus of documents. This architecture uses a retriever component that fetches the most relevant documents and a reader which in turn extracts the answer from the documents. These systems commonly use transformer-based models for both components, which have been fine-tuned on a general domain of documents, such as Wikipedia. However, the performance of such systems on new domains, with different vocabularies, can be lacking. Furthermore, new domains of, for instance, company-specific documents often lack annotated data which makes training new models cumbersome. This thesis investigated how a retriever-reader-based architecture can be adapted to a corpus of Telecom documents by generating question-answer data using a large generative language model, GPT3.5. Also, it compared the usage of a dense retriever using BERT to a BM25-based retriever on the domain. Findings suggest that generating training data can be an effective approach for fine-tuning a dense retriever, increasing the Top-K retrieval accuracy by 20 points for k = 10, compared to a dense retriever fine-tuned on Wikipedia. Additionally, it is found that the sparse retriever outperforms the best dense retriever, although, there is reason to believe that the structure of the test dataset could influence this. Finally, the results also indicate that the performance of the reader is not improved by the generated data although future work is needed to draw better conclusions. / Datorsystem som kan svara på frågor har varit ett mål inom forskningsfältet naturlig språkbehandling i många år. System som använder sig av maskininlärning, så som stora språkmodeller har under de senaste åren uppnått hög prestanda. Att använda sig av en så kallad retriever-reader arkitektur har blivit ett kraftfullt tillvägagångssätt för att bygga system som gör det möjligt för användare att ställa frågor och få faktabaserade svar hämtade från en korpus av dokument. Denna arkitektur använder en retriever som hämtar den mest relevanta informationen och en reader som sedan extraherar ett svar från den hämtade informationen. Dessa system använder vanligtvis transformer-baserade modeller för båda komponenterna, som har tränats på en allmän domän som t.ex., Wikipedia. Dock kan prestandan hos dessa system vara bristfällig när de appliceras på mer specifika domäner med andra ordförråd. Dessutom saknas ofta annoterad data för mer specifika domäner, som exempelvis företagsdokument, vilket gör det svårt att träna modeller på dessa områden. I denna avhandling undersöktes hur en retriever-reader arkitektur kan appliceras på en korpus telekomdokument genom att generera data bestående av frågor och tillhörande svar, genom att använda en stor generativ språkmodell, GPT3.5. Rapporten jämförde även användandet av en BERT-baserad retriever med en BM25-baserad retriever för denna domän. Resultaten tyder på att generering av träningsdata kan vara ett effektivt tillvägagångssätt för att träna en BERT-baserad retriever. Den tränade modellen hade 20 poäng högre noggranhet för måttet Top-K retrieval vid k = 10 jämfört med samma model tränad på data från Wikipedia. Resultaten visade även att en BM25-baserad retriever hade högre noggranhet än den bästa BERT-baserade retrievern som tränats. Dock kan detta bero på datasetets utformning. Slutligen visade resultaten även att prestandan hos en tränad reader inte blev bättre genom att träna på genererad data men denna slutsats kräver framtida arbete för att undersökas mer noggrant.

[pt] O desenvolvimento de técnicas de aprendizado auto-supervisionado vem ganhando muita visibilidade na área de Visão Computacional pois possibilita o pré-treinamento de redes neurais profundas sem a necessidade de dados anotados. Em alguns domínios, as anotações são custosas, pois demandam muito trabalho especializado para a rotulação dos dados. Esse problema é muito comum no setor de Óleo e Gás, onde existe um vasto volume de dados não interpretados. O presente trabalho visa aplicar a técnica de aprendizado auto-supervisionado denominada Masked Autoencoders para pré-treinar modelos Vision Transformers com dados sísmicos. Para avaliar o pré-treino, foi aplicada a técnica de transfer learning para o problema de segmentação de fácies sísmicas. Na fase de pré-treinamento foram empregados quatro volumes sísmicos distintos. Já para a segmentação foi utilizado o dataset Facies-Mark e escolhido o modelo da literatura Segmentation Transformers. Para avaliação e comparação da performance da metodologia foram empregadas as métricas de segmentação utilizadas pelo trabalho de benchmarking de ALAUDAH (2019). As métricas obtidas no presente trabalho mostraram um resultado superior. Para a métrica frequency weighted intersection over union, por exemplo, obtivemos um ganho de 7.45 por cento em relação ao trabalho de referência. Os resultados indicam que a metodologia é promissora para melhorias de problemas de visão computacional em dados sísmicos. / [en] The development of self-supervised learning techniques has gained a lot of visibility in the field of Computer Vision as it allows the pre-training of deep neural networks without the need for annotated data. In some domains, annotations are costly, as they require a lot of specialized work to label the data. This problem is very common in the Oil and Gas sector, where there is a vast amount of uninterpreted data. The present work aims to apply the self-supervised learning technique called Masked Autoencoders to pre-train Vision Transformers models with seismic data. To evaluate the pre-training, transfer learning was applied to the seismic facies segmentation problem. In the pre-training phase, four different seismic volumes were used. For the segmentation, the Facies-Mark dataset was used and the Segmentation Transformers model was chosen from the literature. To evaluate and compare the performance of the methodology, the segmentation metrics used by the benchmarking work of ALAUDAH (2019) were used. The metrics obtained in the present work showed a superior result. For the frequency weighted intersection over union (FWIU) metric, for example, we obtained a gain of 7.45 percent in relation to the reference work. The results indicate that the methodology is promising for improving computer vision problems in seismic data.

Data pertaining to the number of failed high voltage current transformers installed in / Thesis (M.Sc.Eng.)-University of KwaZulu-Natal, Durban, 2006. / Thesis (M.Sc.)-University of KwaZulu-Natal, Durban, 2006.