Visually inspired power quality disturbances recognition via Gramian Angular Difference Field, swin transformer and temporal–frequency–symmetry attention

Lin, Jiajian and Tavalaei, Jalal and Ektesabi, Mehran Motamed and Afrouzi, Hadi Nabipour (2025) Visually inspired power quality disturbances recognition via Gramian Angular Difference Field, swin transformer and temporal–frequency–symmetry attention. Electric Power Systems Research, 252. p. 112352. ISSN 0378-7796

Preview

Text 1-s2.0-S0378779625009393-main.pdf - Published Version Available under License Creative Commons Attribution Non-commercial No Derivatives. Download (6MB)

Abstract

Accurate and real-time identification of power quality disturbances (PQDs) remains a pressing challenge in modern power systems, especially with the increased penetration of renewable energy sources and the resulting complexity of electrical networks. This study proposed a novel hybrid framework for PQD recognition, integrating Gramian Angular Difference Field (GADF) image encoding, the Swin Transformer for hierarchical local feature extraction, and a Temporal-Frequency-Symmetry Enhanced Global Attention Mechanism (TFSGAM) for capturing global and domain-specific features. The one-dimensional PQD signals are first converted into two-dimensional images using GADF, effectively preserving temporal dependencies. The Swin Transformer exploits local contextual information, while TFSGAM further enhances feature representation by incorporating temporal position encoding, frequency-domain awareness, and symmetry-based spatial attention. Experimental results on synthetic and real-world datasets demonstrated that the proposed framework achieved classification accuracy exceeding 98 % under most noise conditions, while maintaining strong robustness across 25 PQD types and ensuring real-time applicability with an average inference time of 169 ms/sample. Comparative studies with state-of-the-art methods and extensive ablation analyses confirmed that this approach exhibits strong robustness in noise scenarios with SNR = 20/30/40 dB.

Item Type:	Article
Identification Number:	10.1016/j.epsr.2025.112352
Dates:	Date Event 6 October 2025 Accepted 15 October 2025 Published Online
Uncontrolled Keywords:	Power quality disturbance, Deep learning, Gram matrix, Swin transformer, Attention mechanism
Subjects:	CAH10 - engineering and technology > CAH10-01 - engineering > CAH10-01-08 - electrical and electronic engineering
Divisions:	Architecture, Built Environment, Computing and Engineering > Engineering
Depositing User:	Gemma Tonks
Date Deposited:	06 Feb 2026 15:09
Last Modified:	06 Feb 2026 15:09
URI:	https://www.open-access.bcu.ac.uk/id/eprint/16842

Actions (login required)

View Item