An envelope detector as a trading cost technique for radiometric partial discharge detection

Neto, José; Neto, José Sérgio da Rocha; Macedo, E C; Glover, Ian; Judd, M.D.

doi:10.1109/i2mtc.2014.6861013

Cited by 6 publications

(8 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Envoltórias O detector de envoltória é um demodulador de amplitude ideal, que permite reduzir a frequência de amostragem exigida para detectar a envoltória de um sinal [8]. Tal ferramenta se torna útil, em particular, na detecção de fontes de DP, que exigem equipamentos de medição com altas taxas de amostragem.…”

Section: Fundamentação Teóricaunclassified

Avaliação de técnicas de inteligência artificial na classificação de descargas parciais

Silva

Carvalho

Nobrega

et al. 2021

View full text Add to dashboard Cite

A detecção de sinais de Descargas Parciais (DP) na faixa da Ultra Alta Frequência (UHF) permite identificar e classificar, de forma minimamente invasiva, defeitos em equipamentos de alta tensão, bem como estimar o grau de urgência da realização de manutenções preventivas. Neste artigo, técnicas de machine learning foram utilizadas para realizar o reconhecimento automático dos padrões obtidos a partir de envoltórias de sinais UHF de DP. Para tanto, foi elaborado um arranjo experimental para emular diferentes fontes de DP: uma cuba de óleo com eletrodos ponta-plano, a barra de um hidrogerador e um transformador de potencial. A partir dos sinais obtidos nesse arranjo, geraram-se envoltórias, a partir das quais foi realizada a extração de uma série de atributos no domínio do tempo, tais como: curtose, amplitude máxima e tempo de subida. Em seguida, realizou-se a seleção dos atributos por meio de uma associação de algoritmos, dentre eles o k-means, de forma a reduzir a dimensionalidade dos dados para aumentar a eficiência do algoritmo classificador. Por fim, fez-se a classificação dos sinais de DP a partir de uma rede neural artificial, decision tree e random forest. Os resultados mostraram que os atributos extraídos das envoltórias foram efetivos na classificação dos sinais de DP, com valores de acurácia média superiores a 95% quando foi utilizado o banco de dados otimizado.

show abstract

Section: Fundamentação Teóricaunclassified

Avaliação de técnicas de inteligência artificial na classificação de descargas parciais

Silva

Carvalho

Nobrega

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The replacement of oscilloscopes with high bandwidths and sampling rates by cheaper and more robust acquisition systems prepared for field acquisition is possible with the addition of a signal conditioning system based on envelope sensing circuitry [16]. Moreover, the signal-to-noise ratio tends to be improved, since a low noise amplifier (LNA) could be used to improve the sensitivity of the system.…”

Section: Introductionmentioning

confidence: 99%

Classification of Partial Discharge Sources in Ultra-High Frequency Using Signal Conditioning Circuit Phase-Resolved Partial Discharges and Machine Learning

Santos Júnior,

Serres,

Xavier

et al. 2024

Electronics

View full text Add to dashboard Cite

This work presents a methodology for the generation and classification of phase-resolved partial discharge (PRPD) patterns based on the use of a printed UHF monopole antenna and signal conditioning circuit to reduce hardware requirements. For this purpose, the envelope detection technique was applied. In addition, test objects such as a hydrogenerator bar, dielectric discs with internal cavities in an oil cell, a potential transformer and tip–tip electrodes immersed in oil were used to generate partial discharge (PD) signals. To detect and classify partial discharges, the standard IEC 60270 (2000) method was used as a reference. After the acquisition of conditioned UHF signals, a digital signal filtering threshold technique was used, and peaks of partial discharge envelope pulses were extracted. Feature selection techniques were used to classify the discharges and choose the best features to train machine learning algorithms, such as multilayer perceptron, support vector machine and decision tree algorithms. Accuracies greater than 84% were met, revealing the classification potential of the methodology proposed in this work.

show abstract

“…Techniques have been described previously that alleviate the requirement of synchronization between sensor nodes by using incoherent detection that relies on received signal strength (RSS) only [31]- [34], thereby alleviating the restrictions on scalability and allowing for inclusion of any number of nodes. Some RSS-based approaches also employ an envelope detector within the sensor to greatly reduce the required sample-rate [35], [36] whilst reducing the measurement accuracy. A technique involving the use of an op-amp based transistor-reset integrator (TRI) has been previously reported [37]- [41], which completely removes the requirement for high-speed sampling by integrating the radiometrically received envelope detected PD signal.…”

Section: Introductionmentioning

confidence: 99%

Gated Pipelined Folding ADC-Based Low Power Sensor for Large-Scale Radiometric Partial Discharge Monitoring

et al. 2020

View full text Add to dashboard Cite

Partial discharge is a well-established metric for condition assessment of high-voltage plant equipment. Traditional techniques for partial discharge detection involve physical connection of sensors to the device under observation, limiting sensors to monitoring of individual apparatus, and therefore, limiting coverage. Wireless measurement provides an attractive low-cost alternative. The measurement of the radiometric signal propagated from a partial discharge source allows for multiple plant items to be observed by a single sensor, without any physical connection to the plant. Moreover, the implementation of a large-scale wireless sensor network for radiometric monitoring facilitates a simple approach to high voltage fault diagnostics. However, accurate measurement typically requires fast data conversion rates to ensure accurate measurement of faults. The use of high-speed conversion requires continuous high-power dissipation, degrading sensor efficiency and increasing cost and complexity. Thus, we propose a radiometric sensor which utilizes a gated, pipelined, sample-and-hold based folding analogue-todigital converter structure that only samples when a signal is received, reducing the power consumption and increasing the efficiency of the sensor. A proof of concept circuit has been developed using discrete components to evaluate the performance and power consumption of the system.

show abstract

An envelope detector as a trading cost technique for radiometric partial discharge detection

Cited by 6 publications

References 9 publications

Avaliação de técnicas de inteligência artificial na classificação de descargas parciais

Avaliação de técnicas de inteligência artificial na classificação de descargas parciais

Classification of Partial Discharge Sources in Ultra-High Frequency Using Signal Conditioning Circuit Phase-Resolved Partial Discharges and Machine Learning

Gated Pipelined Folding ADC-Based Low Power Sensor for Large-Scale Radiometric Partial Discharge Monitoring

Contact Info

Product

Resources

About