Open Access

ARTICLE

Transmission Facility Detection with Feature-Attention Multi-Scale Robustness Network and Generative Adversarial Network

Yunho Na¹, Munsu Jeon¹, Seungmin Joo¹, Junsoo Kim¹, Ki-Yong Oh^1,2,*, Min Ku Kim^1,2,*, Joon-Young Park³

1 Department of Mechanical Convergence Engineering, Hanyang University, 222 Wangsimni-ro, Seongdong-gu, Seoul, 04763, Republic of Korea
2 School of Mechanical Engineering, Hanyang University, 222 Wangsimni-ro, Seongdong-gu, Seoul, 04763, Republic of Korea
3 Power Transmission Laboratory, KEPCO Research Institute, Korea Electric Power Corporation, Daejeon, 105 Munji-ro, Yuseong-gu, Daejeon, Seoul, 34056, Republic of Korea

* Corresponding Authors: Ki-Yong Oh. Email: ; Min Ku Kim. Email:

(This article belongs to the Special Issue: Data-Driven and Physics-Informed Machine Learning for Digital Twin, Surrogate Modeling, and Model Discovery, with An Emphasis on Industrial Applications)

Computer Modeling in Engineering & Sciences 2025, 144(1), 1013-1044. https://doi.org/10.32604/cmes.2025.066447

Received 09 April 2025; Accepted 26 June 2025; Issue published 31 July 2025

Abstract

This paper proposes an automated detection framework for transmission facilities using a feature-attention multi-scale robustness network (FAMSR-Net) with high-fidelity virtual images. The proposed framework exhibits three key characteristics. First, virtual images of the transmission facilities generated using StyleGAN2-ADA are co-trained with real images. This enables the neural network to learn various features of transmission facilities to improve the detection performance. Second, the convolutional block attention module is deployed in FAMSR-Net to effectively extract features from images and construct multi-dimensional feature maps, enabling the neural network to perform precise object detection in various environments. Third, an effective bounding box optimization method called Scylla-IoU is deployed on FAMSR-Net, considering the intersection over union, center point distance, angle, and shape of the bounding box. This enables the detection of power facilities of various sizes accurately. Extensive experiments demonstrated that FAMSR-Net outperforms other neural networks in detecting power facilities. FAMSR-Net also achieved the highest detection accuracy when virtual images of the transmission facilities were co-trained in the training phase. The proposed framework is effective for the scheduled operation and maintenance of transmission facilities because an optical camera is currently the most promising tool for unmanned aerial vehicles. This ultimately contributes to improved inspection efficiency, reduced maintenance risks, and more reliable power delivery across extensive transmission facilities.

---

Keywords

---