Detection of Current Transformer Saturation Based on Machine Learning
Обнаружение насыщения трансформаторов тока на основе методов машинного обучения
2024-01-25
SCID: 54.1/rt8axmf9
Discuss with AI
artificial neural networksbinary classificationcurrent transformer saturationmachine learningsupport vector machine
Figures from the paper
Abstract (AI)
One of the tasks in the operation of electric power systems is the correct functioning of the protection system and emergency automation algorithms. Instrument voltage and current transformers, operating in accordance with the laws of electromagnetism, are most often used for information support of the protection system and emergency automation algorithms. Magnetic core saturation of the specified current transformers can occur during faults. As a result, the correct functioning of the protection system and emergency automation algorithms is compromised. The consequences of current transformers saturation are mostly reflected in the main protections of network elements operating on a differential principle. This work aims to consider the analysis of current transformer saturation detection methods. The problem of identifying current transformer saturation is reduced to binary classification, and methods for solving the problem based on artificial neural networks, support vector machine, and decision tree algorithms are proposed. Computational experiments were performed, and their results were analyzed with imbalanced (dominance of the number of current transformer saturation modes over the number of modes with its normal operation) and balanced classes 0 (no current transformer saturation) and 1 (current transformer saturation).
Key Findings
1
Artificial neural networks, support vector machines, and decision tree algorithms are proposed for detecting current transformer saturation.
2
Computational experiments evaluate the proposed approaches under both imbalanced and balanced datasets representing nonsaturation and saturation modes.
3
Current transformer core saturation during faults can compromise protection and emergency automation, particularly differential protections.
4
The study formulates current transformer saturation identification as a binary classification problem distinguishing normal operation from saturation.
5
The work analyzes how class balance affects machine-learning-based current transformer saturation detection.
Research Object
Current transformers in electric power system protection and emergency automation
Research Subject
Detection and binary classification of magnetic-core saturation under fault conditions
Publication Details
Publication Date
2024-01-25
Journal
Publisher
ISSN
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest