Transformer fault diagnosis based on autoassociative neural networks

Castro, Adriana; Miranda, Vladimiro; Lima, Shigeaki Leite de

doi:10.1109/isap.2011.6082196

Cited by 8 publications

(5 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Table 6 displays the results produced with the new Competitive Autoencoder Set, as well as the diagnosis obtained when applying IEC 60599 to the same data. A remarkable result emerges, not totally unexpected because it was already hinted in [36]: 100% accuracy in pinpointing the type of fault -or indicating a no fault condition. Notice that no errors or misclassification were produced by the new system (352 hits in 352 cases!).…”

Section: A Validation With Real Datamentioning

confidence: 77%

“…The model in [36], by the same authors as this paper, was devoted to discriminating the type of fault given that a faulty condition is assumed. The work reported now is an extension of previous preliminary results and, while keeping as we shall see an accuracy of 100%, it also allows the distinction between healthy and faulty states, as well as making a distinction between transformers with and without OLTC (online tap changing)..…”

Section: Dga Diagnosis Data In Power Transformersmentioning

confidence: 99%

See 1 more Smart Citation

Diagnosing Faults in Power Transformers With Autoassociative Neural Networks and Mean Shift

Miranda

Castro

Lima

2012

IEEE Trans. Power Delivery

Self Cite

View full text Add to dashboard Cite

This paper presents a new approach to incipient fault diagnosis in power transformers, based on the results of dissolved gas analysis. A set of autoassociative neural networks or autoencoders are trained, so that each becomes tuned with a particular fault mode or no fault condition. The scarce data available forms clusters that are densified using an Information Theoretic Mean Shift algorithm, allowing all real data to be used in the validation process. Then, a parallel model is built where the autoencoders compete with one another when a new input vector is entered and the closest recognition is taken as the diagnosis sought. A remarkable accuracy of 100% is achieved with this architecture, in a validation data set using all real information available. IndexTerms-Transformer fault diagnosis, Dissolved Gas Analysis, autoassociative neural networks, mean shift, information theoretic learning. I. INTRODUCTION his paper describes a new approach to the problem of fault detection and identification in power transformers, that reaches 100% accuracy: a diagnosis system based on a set of autoassociative neural networks. The new model gives indication of no-fault or normal condition of the transformer and, if a faulty condition is detected, it identifies the type of fault. This capacity has not been reached before. Power transformer incipient fault diagnosis based on dissolved gas [1] analysis (DGA) has been attempted many times, due to the economic importance of potential equipment failure. It is a problem prone to be addressed by researchers since the publication an IEC norm (IEC 60599 [2]) and a seminal paper [3] that included a data base for diagnosed failures denoted IEC TC10. A number of models have been proposed, adopting a diversity of techniques: expert systems [4], fuzzy set models [5], multi-layer feedforward artificial neural networks (ANN) [6][7], wavelet networks [8], hybrids fuzzy sets/ANN [9], radial basis function neural networks [10],

show abstract

Section: A Validation With Real Datamentioning

confidence: 77%

Section: Dga Diagnosis Data In Power Transformersmentioning

confidence: 99%

Diagnosing Faults in Power Transformers With Autoassociative Neural Networks and Mean Shift

Miranda

Castro

Lima

2012

IEEE Trans. Power Delivery

Self Cite

View full text Add to dashboard Cite

show abstract

“…If the output vector is equal to the input vector, all the information flows through the S' bottleneck and is recomposed into S. Therefore, the AANN learns the real data and stores it in the weights. An input vector thats is no consistent with the learned data will output a distinct vector (possibly with a larger error) because that vector does not correctly map in the nonlinear space S' and its reconstruction by f − 1 is not possible [25], [26].…”

Section: Autoassociative Neural Networkmentioning

confidence: 99%

Competitive Autoassociative Neural Networks for Electrical Appliance Identification for Non-Intrusive Load Monitoring

Morais

Castro

2019

IEEE Access

View full text Add to dashboard Cite

This paper presents a new approach to electrical appliance identification for non-intrusive load monitoring (NILM). In the proposed method a set of autoassociative neural networks is trained so that each one is tuned with the characteristics of a particular electrical appliance. Then, the autoassociative neural networks are set up in a competitive parallel arrangement in which they compete with one another when a new input vector is entered and the closest recognition is accepted to identify the given electrical appliance. The system is trained to recognize specific types of electrical appliances and use the transient power signal obtained from the on/off events for each electrical appliance. To test the proposed method, three public datasets were used, they are, the reference energy disaggregation dataset (REDD), the United Kingdom recording domestic appliance-level electricity (UK-DALE) and the Tracebase dataset containing real residential measurements are used. The accuracy and F-score obtained for the three datasets show the applicability of the proposed method for NILM systems. INDEX TERMS Autoassociative neural network (AANN), electrical appliance identification, non-intrusive load monitoring (NILM).

show abstract

“…Para que se possa realizar o processo de aprendizagem, é preciso primeiramente se ter um modelo do ambiente no qual a rede neural será inserida. A generalização, outra característica importante da MLP, é a capacidade de responder a situações que não foram apresentadas à rede neural na etapa de aprendizado [Castro, A. R. G., Miranda, V., & Lima 2011].…”

Section: Figura 1 Rede Neural Perceptron Multicamadasunclassified

Modelo de Previsão Hidrológica Utilizando Redes Neurais Artificiais: Um Estudo de Caso na Bacia do Rio Xingu - Altamira-PA

Silva¹,

Castro²,

Vieira³

2018

Anais Do Workshop De Computação Aplicada À Gestão Do Meio Ambiente E Recursos Naturais (WCAMA)

View full text Add to dashboard Cite

Knowledge about the extent of river bed overflow is extremely necessary for the determination of areas at risk. The City of Altamira-PA, located on the banks of the Xingu River, historically suffers from extreme events of floods that provoke floods, causing great damages to the population. Considering the problem, this paper presents a monthly level prediction system of the Xingu River based on neural networks perceptron of multiple layers. For the development of the system, precipitacion data were used in the basin and sub-basins of the Xingu River, and SST information (Sea Surface Temperature) from 1979 to 2016. The satisfactory results demonstrate the great applicability of the artificial neural networks to the problem. Resumo O conhecimento acerca da amplitude do transbordamento dos leitos fluviais é extremamente necessário para determinação deáreas de risco. A cidade de Altamira-PA, localizada às margens do rio Xingu, vem sofrendo com casos extremos de cheias que tendem a provocar inundações, resultando em severos prejuízos para a sua população. Considerando o problema, este artigo apresenta a proposta de um sistema de previsão de nível mensal do Rio Xingu baseado em Redes Neurais Artificiais Perceptron de múltiplas camadas. Para o desenvolvimento do sistema foram utilizados dados de precipitação na bacia e sub-bacias do Rio Xingu, e informações de Temperatura da Superfície do Mar (TSM) do período de 1979 a 2016. Os resultados satisfatórios obtidos demonstram a grande aplicabilidade das Redes Neurais Artificiais para o problema de previsão de cheias.

show abstract

Transformer fault diagnosis based on autoassociative neural networks

Cited by 8 publications

References 21 publications

Diagnosing Faults in Power Transformers With Autoassociative Neural Networks and Mean Shift

Diagnosing Faults in Power Transformers With Autoassociative Neural Networks and Mean Shift

Competitive Autoassociative Neural Networks for Electrical Appliance Identification for Non-Intrusive Load Monitoring

Modelo de Previsão Hidrológica Utilizando Redes Neurais Artificiais: Um Estudo de Caso na Bacia do Rio Xingu - Altamira-PA

Contact Info

Product

Resources

About