Bayesian Deep Neural Network to Compensate for Current Transformer Saturation

Current transformer saturation has a negative effect on the operation of IEDs, resulting in their malfunction. Here, we present a technique to compensate for saturated waveforms using Bayesian Deep Neural Network (BDNN) comprising Deep Neural Network (DNN) and Bayesian optimization (BO). DNN, that u...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Sopheap Key, Sang-Hee Kang, Nam-Ho Lee, Soon-Ryul Nam
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Current transformer saturation deep learning stacked denoising auto-encoders Bayesian Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/4147964eba1148ce94d3571bf1d32501
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:4147964eba1148ce94d3571bf1d32501
record_format	dspace
spelling	oai:doaj.org-article:4147964eba1148ce94d3571bf1d325012021-11-25T00:00:26ZBayesian Deep Neural Network to Compensate for Current Transformer Saturation2169-353610.1109/ACCESS.2021.3127542https://doaj.org/article/4147964eba1148ce94d3571bf1d325012021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9612180/https://doaj.org/toc/2169-3536Current transformer saturation has a negative effect on the operation of IEDs, resulting in their malfunction. Here, we present a technique to compensate for saturated waveforms using Bayesian Deep Neural Network (BDNN) comprising Deep Neural Network (DNN) and Bayesian optimization (BO). DNN, that utilizes stacked denoising autoencoder (SDAE) and Backpropagation (BP), is employed to optimize deep learning structure. Unlike the conventional neural network, which is a shallow network or random-initialize weights, the SDAE calculates optimal weights for each hidden layer and BP uses them to fine-tune which yields results with high performance for CT saturation compensation. To improve the empirical search of training hyperparameters, Bayesian optimization is adopted to decide training-related vectors such as batch size, learning rate, and number of neurons. Finally, the performance of the proposed approach was evaluated on an overhead transmission line which is imported from PSCAD/EMTDC with the different scenarios of fault inception angle, remnant flux, and voltage system. Therefore, numerical cases of saturation were comprehensively evaluated to demonstrate the performance of the proposed algorithm. A comparative analysis was shown to demonstrate that the proposed BDNN is superior to artificial neural network (ANN), and least square error (LES) technique.Sopheap KeySang-Hee KangNam-Ho LeeSoon-Ryul NamIEEEarticleCurrent transformersaturationdeep learningstacked denoising auto-encodersBayesianElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 154731-154739 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Current transformer saturation deep learning stacked denoising auto-encoders Bayesian Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Current transformer saturation deep learning stacked denoising auto-encoders Bayesian Electrical engineering. Electronics. Nuclear engineering TK1-9971 Sopheap Key Sang-Hee Kang Nam-Ho Lee Soon-Ryul Nam Bayesian Deep Neural Network to Compensate for Current Transformer Saturation
description	Current transformer saturation has a negative effect on the operation of IEDs, resulting in their malfunction. Here, we present a technique to compensate for saturated waveforms using Bayesian Deep Neural Network (BDNN) comprising Deep Neural Network (DNN) and Bayesian optimization (BO). DNN, that utilizes stacked denoising autoencoder (SDAE) and Backpropagation (BP), is employed to optimize deep learning structure. Unlike the conventional neural network, which is a shallow network or random-initialize weights, the SDAE calculates optimal weights for each hidden layer and BP uses them to fine-tune which yields results with high performance for CT saturation compensation. To improve the empirical search of training hyperparameters, Bayesian optimization is adopted to decide training-related vectors such as batch size, learning rate, and number of neurons. Finally, the performance of the proposed approach was evaluated on an overhead transmission line which is imported from PSCAD/EMTDC with the different scenarios of fault inception angle, remnant flux, and voltage system. Therefore, numerical cases of saturation were comprehensively evaluated to demonstrate the performance of the proposed algorithm. A comparative analysis was shown to demonstrate that the proposed BDNN is superior to artificial neural network (ANN), and least square error (LES) technique.
format	article
author	Sopheap Key Sang-Hee Kang Nam-Ho Lee Soon-Ryul Nam
author_facet	Sopheap Key Sang-Hee Kang Nam-Ho Lee Soon-Ryul Nam
author_sort	Sopheap Key
title	Bayesian Deep Neural Network to Compensate for Current Transformer Saturation
title_short	Bayesian Deep Neural Network to Compensate for Current Transformer Saturation
title_full	Bayesian Deep Neural Network to Compensate for Current Transformer Saturation
title_fullStr	Bayesian Deep Neural Network to Compensate for Current Transformer Saturation
title_full_unstemmed	Bayesian Deep Neural Network to Compensate for Current Transformer Saturation
title_sort	bayesian deep neural network to compensate for current transformer saturation
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/4147964eba1148ce94d3571bf1d32501
work_keys_str_mv	AT sopheapkey bayesiandeepneuralnetworktocompensateforcurrenttransformersaturation AT sangheekang bayesiandeepneuralnetworktocompensateforcurrenttransformersaturation AT namholee bayesiandeepneuralnetworktocompensateforcurrenttransformersaturation AT soonryulnam bayesiandeepneuralnetworktocompensateforcurrenttransformersaturation
_version_	1718414690017607680

Bayesian Deep Neural Network to Compensate for Current Transformer Saturation

Ejemplares similares