Current Transformer Saturation Detection Bases On Artificial Neural Networks

Обнаружение насыщения трансформаторов тока на основе искусственных нейронных сетей
Begmurod Saidmurodov, Ismoil N. Odinaev
2023-12-26

artificial neural networksbinary classificationcurrent transformer saturationimbalanced classespower system protection
Protection and automation (PA) system is an integral part of electric power systems. The algorithms of the PA system operate based on the use of analysis of the electrical mode parameters - current and voltage - obtained from instrument transformers. As a rule, these transformers operate based on the electromagnetism laws. Operational experience shows that the current transformers (CT) core under fault conditions can be saturated. As a result, the shape of the measured current is distorted, which can lead to maloperation of the PA system. In this paper, a method for solving the problem of CT core saturation based on the use of artificial neural networks for classification problems is proposed. The saturation problem is reduced to a binary classification problem, a description of the synthesis of DATASET is given. Computational experiments were carried out for the cases of balanced (the number of CT modes with and without saturation are the same) and imbalanced classes. The experimental results show that the accuracy of the model can reach 99%.
1
A dataset synthesis procedure is described for training and evaluating neural-network-based saturation classifiers.
2
Computational experiments examine both balanced and imbalanced datasets containing saturated and unsaturated CT operating modes.
3
Detecting CT saturation is important because waveform distortion can cause protection and automation system maloperation.
4
The paper formulates current-transformer core saturation detection as a binary classification problem using artificial neural networks.
5
The proposed model achieves classification accuracy of up to 99% in the reported experiments.

current-transformer cores under fault conditions

detection and binary classification of core saturation from distorted measured-current waveforms

Publication Details
Publication Date
2023-12-26
Journal
Publisher
ISSN
Access Type
Author Information
Authors
Begmurod Saidmurodov
Ismoil N. Odinaev
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%