4.6 Article

A Novel Signal Localized Convolution Neural Network for Power Transformer Differential Protection

Journal

IEEE TRANSACTIONS ON POWER DELIVERY
Volume 37, Issue 2, Pages 1242-1251

Publisher

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TPWRD.2021.3080927

Keywords

Power transformers; Convolution; Time-frequency analysis; Feature extraction; Wavelet transforms; Circuit faults; Relays; Power transformer differential protection; convolutional neural network; wavelet transform

Funding

  1. Ministry of Electronics and Information Technology, Government of India [Phd-MLA/4(16)/2015-16]

Ask authors/readers for more resources

This paper introduces a novel signal localized convolution neural network (SLCNN) for power transformer differential protection. Signal localization is achieved by sequentially performing convolution on frequency and time coefficients obtained from wavelet decomposition, and the SLCNN is trained with a modified back-propagation algorithm based on its architecture. Evaluation is carried out on three power transformer test systems, with training patterns generated for various operating conditions for each transformer.
This paper presents a novel signal localized convolution neural network (SLCNN) for the power transformer differential protection. The distinct signal localization is performed with the convolution process sequentially on the frequency and time coefficients which are obtained from the wavelet decomposition of the differential current signal. The SLCNN is trained with a modified back-propagation algorithm according to SLCNN's architecture. Three power transformer test systems are considered for evaluation of the proposed SLCNN. The training patterns of each transformer are generated for various operating conditions. The SLCNN for each transformer is trained, validated and tested using its corresponding patterns. Then the performance of SLCNN is evaluated through confusion matrix analysis and is also compared with long short-term memory (LSTM) deep neural network, support vector machine (SVM), conventional back-propagation neural network (CBPNN) and conventional biased restraint second harmonic (CBSH) blocking method.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.6
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available