SE-Attention Augmented Hybrid CNN–BiLSTM Model for Leakage Current-Based Detection of Cracked and Broken High-Voltage Porcelain Insulators
Biomimetics · 01.07.2026 · 11 (7) · 457
DOI: 10.3390/biomimetics11070457 ↗Kurz gefasst
Fachartikel in der Zeitschrift Biomimetics, online erschienen am 01.07.2026. Verfasst von Ömer Faruk Alçin und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Software Engineering, Faculty of Engineering, Inonu University, 44210 Malatya, Türkiye. Die Arbeit nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Inonu University, Inonu University Scientific Research Projects Coordination Unit.
Abstract (Originalsprache)
Extreme and sudden temperature fluctuations observed as a result of global climate change increase the environmental pressure on energy transmission infrastructure. These meteorological changes significantly increase the risk of failure for porcelain insulators, which exhibit low thermal resistance and are susceptible to sudden arcing and surface deformations. In this study, a hybrid CNN–BiLSTM–SE architecture augmented with the Squeeze-and-Excitation attention mechanism is proposed using surface leakage current signals to diagnose healthy, cracked, and broken structural conditions in three-unit porcelain insulators. The SE block in the architecture dynamically rescales feature maps from CNN layers on a channel-by-channel basis. Thus, it highlights the signal characteristic that is dominant for fault diagnosis just before the BiLSTM units learn temporal dependencies. Leakage current data were obtained under an experimental setup at 60 kV for 15 different conditions covering all possible combinations of healthy, cracked, and broken insulator units. The raw signals were preprocessed with the Savitzky–Golay filter to suppress noise while preserving the diagnostic waveform morphology. 24 features covering time-domain statistics, frequency-domain spectral characteristics, and wavelet-domain energy components were extracted and used as model inputs. The CNN–BiLSTM–SE architecture achieved a classification accuracy of 93.83%, surpassing the standalone CNN (88.89%), BiLSTM (87.65%), and CNN–BiLSTM (91.36%) models, as well as classical machine-learning baselines (SVM: 87.65%, Random Forest: 90.12%, Boosted Trees: 87.65%).
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Software Engineering, Faculty of Engineering, Inonu University, 44210 Malatya, Türkiye.
- Department of Electrical and Electronics Engineering, Faculty of Engineering and Natural Sciences, Malatya Turgut Ozal University, 44210 Malatya, Türkiye.
- Department of Electrical and Electronics Engineering, Faculty of Engineering, Firat University, 23119 Elazığ, Türkiye.
ORCID-Profile: Ömer Faruk Alçin, Muhammed Buğracan Özküçük, Muhsin Tunay Gençoğlu
Förderung
- Inonu University
- Inonu University Scientific Research Projects Coordination Unit
Zitieren
APA
Alçin, Ö. F., Özküçük, M. B., & Gençoğlu, M. T. (2026). SE-Attention Augmented Hybrid CNN–BiLSTM Model for Leakage Current-Based Detection of Cracked and Broken High-Voltage Porcelain Insulators. Biomimetics, 11(7), 457. https://doi.org/10.3390/biomimetics11070457
Vancouver
Alçin ÖF, Özküçük MB, Gençoğlu MT. SE-Attention Augmented Hybrid CNN–BiLSTM Model for Leakage Current-Based Detection of Cracked and Broken High-Voltage Porcelain Insulators. Biomimetics. 2026;11(7):457. doi:10.3390/biomimetics11070457
BibTeX
@article{Alin2026,
author = {Alçin, Ömer Faruk and Özküçük, Muhammed Buğracan and Gençoğlu, Muhsin Tunay},
title = {SE-Attention Augmented Hybrid CNN–BiLSTM Model for Leakage Current-Based Detection of Cracked and Broken High-Voltage Porcelain Insulators},
journal = {Biomimetics},
year = {2026},
volume = {11},
number = {7},
pages = {457},
doi = {10.3390/biomimetics11070457}
}
EUVIMED