A New Transmission Line Protection Approach Using Cumulants and Artificial Neural Networks

Carvalho, J. R. de; Coury, Denis Vinicius; Duque, Carlos A.; Paula, Bruno F.

doi:10.1007/s40313-013-0101-7

Cited by 5 publications

(4 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Assim a acurácia média obtida pelo modelo foi de 89.59% com desvio padrão de 1.24%. O melhor modelo foi salvo durante o treinamento e utilizado posteriormente com o conjunto de testes na classificação de dados não vistos, e dessa maneira, foi obtida a matriz de confusão apresentada na Dessa forma, comparando-se os resultados com trabalhos realizados anteriormente como em R. de Carvalho et al (2014) e Almeida et al (2017), o projeto aqui proposto possui uma etapa de pré-processamento computacionalmente mais eficiente tendo em vista que utilizou-se o filtro notch que possui menor custo computacional do que estatística de ordem superior e análise de componentes independentes que foram utilizados nos trabalhos citados. No entanto, visando a melhoria da acurácia na classificação desses dados, futuramente pretende-se realizar um comparativo entre o uso do filtro notch com outras técnicas no préprocessamento dos sinais.…”

Section: Resultados E Discussõesunclassified

“…Uma técnica amplamente utilizada no processo de classificação de faltas em linhas de transmissãoé a rede neural. Dentre os autores que fizeram uso dela, pode-se citar R. de Carvalho et al (2014) que utilizaram os sinais de tensão com uma etapa de pré-processamento com estatística de ordem superior (higher-order statistics -HOS). Após isso os sinais foram apresentadosà uma rede neural com 3 entradas, 40 neurônios na camada oculta e 10 saídas, obtendo uma acurácia de 99% na classificação com dados simulados.…”

Section: Introductionunclassified

See 1 more Smart Citation

Classificação de faltas em linhas de transmissão utilizando métodos de inteligência computacional

Ferreira

Fonseca

Almeida

2020

Anais Do Simpósio Brasileiro De Sistemas Elétricos 2020

View full text Add to dashboard Cite

Sistemas de transmissão de energia elétrica externos estão altamente susceptíveis a falhas. Alguns pesquisadores já investigaram o uso de técnicas de inteligência computacional como redes neurais artificiais e lógica fuzzy com etapas de pré-processamento que compreendem o uso de transformada wavelet, Fourier ou estatística de ordem superior. Esse trabalho visa mostrar o uso do método de florestas aleatórias e redes neurais artificiais com uma etapa de pré-processamento com filtro notch para classificação de faltas em linhas de transmissão. Foi utilizada a validação cruzada k-fold e como resultado a acurácia média obtida pelo modelo de rede neural foi de 89,59% enquanto a técnica de florestas aleatórias obteve 91,96%.

show abstract

Section: Resultados E Discussõesunclassified

Section: Introductionunclassified

Classificação de faltas em linhas de transmissão utilizando métodos de inteligência computacional

Ferreira

Fonseca

Almeida

2020

Anais Do Simpósio Brasileiro De Sistemas Elétricos 2020

View full text Add to dashboard Cite

show abstract

“…They have utilized the magnitudes of resistance and reactance as inputs for classifying unknown patterns. A novel distance protection approach for detection and classification stages based on cumulants and neural networks was developed by Carvalho et al [32].…”

Section: Distance Protection By Annmentioning

confidence: 99%

An Overview of Transmission Line Protection by Artificial Neural Network: Fault Detection, Fault Classification, Fault Location, and Fault Direction Discrimination

Yadav

Dash

2014

Advances in Artificial Neural Systems

View full text Add to dashboard Cite

Contemporary power systems are associated with serious issues of faults on high voltage transmission lines. Instant isolation of fault is necessary to maintain the system stability. Protective relay utilizes current and voltage signals to detect, classify, and locate the fault in transmission line. A trip signal will be sent by the relay to a circuit breaker with the purpose of disconnecting the faulted line from the rest of the system in case of a disturbance for maintaining the stability of the remaining healthy system. This paper focuses on the studies of fault detection, fault classification, fault location, fault phase selection, and fault direction discrimination by using artificial neural networks approach. Artificial neural networks are valuable for power system applications as they can be trained with offline data. Efforts have been made in this study to incorporate and review approximately all important techniques and philosophies of transmission line protection reported in the literature till June 2014. This comprehensive and exhaustive survey will reduce the difficulty of new researchers to evaluate different ANN based techniques with a set of references of all concerned contributions.

show abstract

“…Common classification techniques include support vector machines, decision trees, neural networks and k-nearest neighbour. Applications include classification of faults in power distribution networks (Lazzaretti et al 2013), classification of power quality disturbances (Barbosa and Ferreira 2013) and transmission line protection (Carvalho et al 2014).…”

Section: Adaptation As Classificationmentioning

confidence: 99%

A k-Nearest Neighbour Technique for Experience-Based Adaptation of Assembly Stations

Scrimieri

Ratchev

2014

J Control Autom Electr Syst

View full text Add to dashboard Cite

We present a technique for automatically acquiring operational knowledge on how to adapt assembly systems to new production demands or recover from disruptions. Dealing with changes and disruptions affecting an assembly station is a complex process which requires deep knowledge of the assembly process, the product being assembled and the adopted technologies. Shop-floor operators typically perform a series of adjustments by trial and error until the expected results in terms of performance and quality are achieved. With the proposed approach, such adjustments are captured and their effect on the station is measured. Adaptation knowledge is then derived by generalising from individual cases using a variant of the k-nearest neighbour algorithm. The operator is informed about potential adaptations whenever the station enters a state similar to one contained in the experience base, that is, a state on which adaptation information has been captured. A case study is presented, showing how the technique enables to reduce adaptation times. The general system architecture in which the technique has been implemented is described, including the role of the different software components and their interactions.

show abstract

A New Transmission Line Protection Approach Using Cumulants and Artificial Neural Networks

Cited by 5 publications

References 24 publications

Classificação de faltas em linhas de transmissão utilizando métodos de inteligência computacional

Classificação de faltas em linhas de transmissão utilizando métodos de inteligência computacional

An Overview of Transmission Line Protection by Artificial Neural Network: Fault Detection, Fault Classification, Fault Location, and Fault Direction Discrimination

A k-Nearest Neighbour Technique for Experience-Based Adaptation of Assembly Stations

Contact Info

Product

Resources

About