Segmentation of 220 kV Cable Insulation Layers Using WGAN-GP-Based Data Augmentation and the TransUNet Model

Luo, Liang; Qing, Song; Liu, Yingjie; Lu, Guoyuan; Zhang, Ziying; Xia, Yuhang; Ao, Yi; Wei, Fanbo; Chen, Xingang

doi:10.3390/en18174667

This is an early access version, the complete PDF, HTML, and XML versions will be available soon.

Open AccessArticle

Segmentation of 220 kV Cable Insulation Layers Using WGAN-GP-Based Data Augmentation and the TransUNet Model

by

Liang Luo

¹,

Song Qing

¹,

Yingjie Liu

¹,

Guoyuan Lu

^2,*,

Ziying Zhang

¹,

Yuhang Xia

¹,

Yi Ao

²,

Fanbo Wei

² and

Xingang Chen

^2,*

¹

Chengdu Power Supply Company, State Grid Sichuan Electric Power Company, Chengdu 610041, China

²

School of Electrical and Electronic Engineering, Chongqing University of Technology, Chongqing 400054, China

^*

Authors to whom correspondence should be addressed.

Energies 2025, 18(17), 4667; https://doi.org/10.3390/en18174667

Submission received: 28 July 2025 / Revised: 27 August 2025 / Accepted: 1 September 2025 / Published: 2 September 2025

(This article belongs to the Special Issue Fault Detection and Diagnosis of Power Distribution System)

Download Versions Notes

Abstract

This study presents a segmentation framework for images of 220 kV cable insulation that addresses sample scarcity and blurred boundaries. The framework integrates data augmentation using the Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP) and the TransUNet architecture. Considering the difficulty and high cost of obtaining real cable images, WGAN-GP generates high-quality synthetic data to expand the dataset and improve the model’s generalization. The TransUNet network, designed to handle the structural complexity and indistinct edge features of insulation layers, combines the local feature extraction capability of convolutional neural networks (CNNs) with the global context modeling strength of Transformers. This combination enables accurate delineation of the insulation regions. The experimental results show that the proposed method achieves mDice, mIoU, MP, and mRecall scores of 0.9835, 0.9677, 0.9840, and 0.9831, respectively, with improvements of approximately 2.03%, 3.05%, 2.08%, and 1.98% over a UNet baseline. Overall, the proposed approach outperforms UNet, Swin-UNet, and Attention-UNet, confirming its effectiveness in delineating 220 kV cable insulation layers under complex structural and data-limited conditions.

Keywords: 220 kV cable; insulation layer segmentation; data augmentation; WGAN-GP; TransUNet

Share and Cite

MDPI and ACS Style

Luo, L.; Qing, S.; Liu, Y.; Lu, G.; Zhang, Z.; Xia, Y.; Ao, Y.; Wei, F.; Chen, X. Segmentation of 220 kV Cable Insulation Layers Using WGAN-GP-Based Data Augmentation and the TransUNet Model. Energies 2025, 18, 4667. https://doi.org/10.3390/en18174667

AMA Style

Luo L, Qing S, Liu Y, Lu G, Zhang Z, Xia Y, Ao Y, Wei F, Chen X. Segmentation of 220 kV Cable Insulation Layers Using WGAN-GP-Based Data Augmentation and the TransUNet Model. Energies. 2025; 18(17):4667. https://doi.org/10.3390/en18174667

Chicago/Turabian Style

Luo, Liang, Song Qing, Yingjie Liu, Guoyuan Lu, Ziying Zhang, Yuhang Xia, Yi Ao, Fanbo Wei, and Xingang Chen. 2025. "Segmentation of 220 kV Cable Insulation Layers Using WGAN-GP-Based Data Augmentation and the TransUNet Model" Energies 18, no. 17: 4667. https://doi.org/10.3390/en18174667

APA Style

Luo, L., Qing, S., Liu, Y., Lu, G., Zhang, Z., Xia, Y., Ao, Y., Wei, F., & Chen, X. (2025). Segmentation of 220 kV Cable Insulation Layers Using WGAN-GP-Based Data Augmentation and the TransUNet Model. Energies, 18(17), 4667. https://doi.org/10.3390/en18174667

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

Segmentation of 220 kV Cable Insulation Layers Using WGAN-GP-Based Data Augmentation and the TransUNet Model

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI