Search research articles

Search research articles

Related Experiment Video

Updated: Jul 16, 2026

A Computer Vision System for the Assessment of Ice Cream Melting Behavior

A Computer Vision System for the Assessment of Ice Cream Melting Behavior

Published on: October 4, 2024

Leakage Current Analysis of Glass, Porcelain, and Silicone Insulators Under Icing Conditions Using Spectrogram-Based

Muhammed Buğracan Özküçük¹, Ömer Faruk Alçin², Muhsin Tunay Gençoğlu³

¹Department of Electrical and Electronics Engineering, Faculty of Engineering and Natural Sciences, Malatya Turgut Ozal University, 44210 Malatya, Türkiye.

Sensors (Basel, Switzerland)

|July 15, 2026

Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Deep learning model developed by multiparametric MRI in differential diagnosis of parotid gland tumors.

European archives of oto-rhino-laryngology : official journal of the European Federation of Oto-Rhino-Laryngological Societies (EUFOS) : affiliated with the German Society for Oto-Rhino-Laryngology - Head and Neck Surgery·2022

See all related articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

This study introduces a spectrogram-based convolutional neural network (CNN) model to accurately detect ice on high-voltage insulators. The developed CNN model significantly outperforms existing methods in identifying icing conditions, ensuring reliable power transmission.

Area of Science:

Electrical Engineering
Materials Science
Artificial Intelligence

Background:

Outdoor insulators are crucial for high-voltage transmission lines but susceptible to environmental factors like icing.
Ice accumulation degrades insulator performance, increasing leakage currents and leading to power outages.

Purpose of the Study:

To develop and evaluate a spectrogram-based convolutional neural network (CNN) model for identifying icing conditions on glass, porcelain, and silicone insulators.
To compare the performance of the developed CNN model against established architectures like AlexNet, GoogLeNet, and ResNet-50 for icing detection.

Main Methods:

Leakage current signals from insulators under varying icing conditions (ice-free, slightly iced, iced) and high voltage (10-50 kV) were recorded.
Signals were filtered and transformed into spectrogram images using Fourier transform for input into CNN architectures.

Keywords:

CNN iced insulator leakage current signal processing spectrogram

More Related Videos

Fluid-cell Raman Spectroscopy for operando Studies of Reaction and Transport Phenomena during Silicate Glass Corrosion

Fluid-cell Raman Spectroscopy for operando Studies of Reaction and Transport Phenomena during Silicate Glass Corrosion

Published on: May 9, 2025

A High Performance Impedance-based Platform for Evaporation Rate Detection

A High Performance Impedance-based Platform for Evaporation Rate Detection

Published on: October 17, 2016

Related Experiment Videos

Last Updated: Jul 16, 2026

A Computer Vision System for the Assessment of Ice Cream Melting Behavior

A Computer Vision System for the Assessment of Ice Cream Melting Behavior

Published on: October 4, 2024

Fluid-cell Raman Spectroscopy for operando Studies of Reaction and Transport Phenomena during Silicate Glass Corrosion

Fluid-cell Raman Spectroscopy for operando Studies of Reaction and Transport Phenomena during Silicate Glass Corrosion

Published on: May 9, 2025

A High Performance Impedance-based Platform for Evaporation Rate Detection

A High Performance Impedance-based Platform for Evaporation Rate Detection

Published on: October 17, 2016

A novel CNN model was developed and compared with AlexNet, GoogLeNet, and ResNet-50 using the spectrogram images.

Main Results:

The developed CNN model achieved high accuracy rates (97.78%–100%) for glass and silicone insulators and (82.22%–100%) for porcelain insulators.
Established models showed reduced accuracy (as low as 73%) on porcelain insulator data, highlighting the developed model's superiority.
The model demonstrated proficiency in differentiating icing conditions across various insulator types and operating scenarios.

Conclusions:

The spectrogram-based CNN model is highly effective for detecting icing on high-voltage insulators.
The developed model offers superior performance compared to existing deep learning architectures for this specific application.
This research contributes to enhancing the reliability of power transmission by improving ice detection on critical infrastructure.