An Advanced Partial Discharge Recognition Strategy of Power Cable

Bi, Xiaotian; Ren, Ang; Li, Simeng; Han, Min−Koo; Li, Qingquan

doi:10.1155/2015/174538

Cited by 5 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…ese imperfections will grow across fracture lines along the direction of the electric field giving water treeing defects. erefore, voltage transients can initiate partial discharge activity at these local defects on account of peak voltage, high dv/dt, and high frequency [4,45,46], which leads to early insulation deterioration. At the same time, mechanical abnormalities in motor operation may arise due to these cumulative transient effects [47].…”

Section: Discussionmentioning

confidence: 99%

Signatures of Transient Overvoltages in Low Voltage Power Systems in Tea Factories and Their Implications on Insulation Deterioration and Allied Power Quality Issues

Pannila

Edirisinghe

2021

Journal of Electrical and Computer Engineering

View full text Add to dashboard Cite

Electrical equipment and supply cables demand a better quality of supply, with the recent advancements in integrated sensitive solid-state controls. Divergently, proliferated heavy inductive motors and some performance additions based on power electronics have introduced power quality issues to the network. Thus, this study mainly investigates the impact of switching transients generated by electromechanical machines in industrial power systems on insulation deterioration while taking transient overvoltages due to capacitor bank switching also to support. Transients with a high rate of rise are likely to catalyze the degradation of the insulation quality and break down the insulating material through ionization. These steeply passing overvoltage stresses let partial discharges ensue, which can attack the insulation over long service. To unveil this danger, 314 common-mode transient waveforms were measured in the electrical machines of five tea factories in Sri Lanka, in a 50 ms measurement window, taken in 55 measuring attempts. Most of the transients observed are in the form of a damped oscillatory waveform tailed by fast exponential collapse. That correlates to insulation degradation having a very steep rise as 30.04 V/ns, the highest at the withering section. When machines are heavily loaded, situations tend to generate transients with high amplitudes. There were transient bursts that spread as 426.3 ms, while 14 ns fast rise times were recorded from withering motors. Unlike electrical resonance and power-frequency overvoltages, electromagnetic switching transients last even less than 100 ms. To underline this, an analysis of the frequency domain of transients was also presented, which proves high density of high-frequency components reaching 107 kHz range. Accepting the fact that frequency and amplitude are always under the influences of innumerable dynamics, the observational evidence of the study endorses that electrical stress built by the transient nature of the factories reduces the life expectancy of electrical insulation.

show abstract

Section: Discussionmentioning

confidence: 99%

Signatures of Transient Overvoltages in Low Voltage Power Systems in Tea Factories and Their Implications on Insulation Deterioration and Allied Power Quality Issues

Pannila

Edirisinghe

2021

Journal of Electrical and Computer Engineering

View full text Add to dashboard Cite

show abstract

“…La dimensión fractal es una expresión lógica de la complejidad espacial que mide la complejidad espacial y codifica el número (a menudo fraccionario) de grados de libertad necesarios para describir una curva o conjunto de datos en particular (Zhang et al, 2019b). La dimensión fractal, como caracterización cuantitativa y parámetro básico del fractal, es un principio importante de la teoría fractal (Bi et al, 2015). De forma general la dimensión fractal objeto geométrico, por ejemplo: un punto es de dimensión 0, línea (dimensión 1), plano (dimensión 2), un volumen (dimensión 3).…”

Section: Dimensión Fractalunclassified

La dimensión fractal como parte de un modelo computacional para predecir el espesor de películas delgadas de ZnO

Ruíz

Cortez

Pozos

et al. 2022

ICBI

View full text Add to dashboard Cite

Si bien es cierto, existen aplicaciones computacionales en el campo nanométrico, particularmente en el contexto de la manipulación de imágenes SEM (scanning electron microscopy), también es cierto que esta área de estudio, aun presenta oportunidades en la construcción del conocimiento. Particularmente, en el presente estudio, se aborda la relación aparentemente biunívoca que puede generarse entre el espesor de una película delgada y la dimensión fractal de su imagen SEM ya segmentada. A través del uso del módulo Keras® perteneciente a la librería de TensorFlow® mediate la programación del código en Colab® de Google®, el cual utiliza la versión de Python® 3.6.9, se obtuvieron las variables internas del modelo [86.4897&87.681694] que permite predicción del espesor con base en una dimensión fractal arbitraria (i.e. dimensión fractal = 1.99, espesor predicho = 259.7962 [nm]).

show abstract

“…For instance, Bi et al [5] extracted fractal features found from grayscale images of discharge signals such as box dimension and information dimension to distinguish different discharge patterns using a multi-SVM recognizer. Li et al [6] established two sub-networks for discharge recognition using BP neural network based on feature extraction of PRPD mode and time resolved partial discharge (TRPD) mode.…”

Section: Introductionmentioning

confidence: 99%

Recognition of Plasma Discharge Patterns Based on CNN and Visible Images

Yang

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Electrical discharge is a sign of insulation damage of power equipment and an essential part of power inspection. For the recognition of plasma discharge patterns, the accuracy rate of traditional manual inspection relies heavily on the experience of the staff, and misjudgment is inevitable. The emerging method based on manual feature extraction of discharge signals also has its limitations. Thus, a high-accurate recognition method based on convolutional neural network (CNN) and visible images is proposed in this paper. Under the deep learning framework-TensorFlow, CNN model is established and pre-trained weights are loaded through transfer learning. The visible image dataset used for training and evaluation includes four discharge patterns: arc discharge, corona discharge, creeping discharge and plasma jet. In data processing, data amplification and data enhancement are used to expand the sample. Besides, typical network models with fully connected layers are adopted and compared. Three optimization methods of ReLU, BN and Dropout are applied to solve the overfitting problem, and the corresponding effects are discussed in the model of VGG16 and ResNet152. The test accuracy of the optimized VGG16 reaches 99.6% without overfitting, which indicates the promising potential in the recognition of plasma discharge patterns in power inspection. INDEX TERMS electrical discharge, plasma discharge patterns, visible images, image recognition, convolutional neural network, transfer learningThis work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.

show abstract

An Advanced Partial Discharge Recognition Strategy of Power Cable

Cited by 5 publications

References 21 publications

Signatures of Transient Overvoltages in Low Voltage Power Systems in Tea Factories and Their Implications on Insulation Deterioration and Allied Power Quality Issues

Signatures of Transient Overvoltages in Low Voltage Power Systems in Tea Factories and Their Implications on Insulation Deterioration and Allied Power Quality Issues

La dimensión fractal como parte de un modelo computacional para predecir el espesor de películas delgadas de ZnO

Recognition of Plasma Discharge Patterns Based on CNN and Visible Images

Contact Info

Product

Resources

About