Affiliation:
1. Henan University of Science and Technology
Abstract
Abstract
Detecting component defects and attaching tiny-scaled foreign objects to the overhead transmission lines are critical to the national grid’s safe operation and power distribution. The urgent task, however, faces challenges such as the complex working environment and the massive amount of workforce investment, for which we propose a deep-learning-aided object detection approach, YOLO-CSM, to address the issue. Combined with two attention mechanisms (Swin Transformer and CBAM) and an extra detection layer, the proposed model can effectively capture global information and key visual features and promote its ability to identify tiny-scaled defects and distant objects in the visual fields. In order to validate this model, this work consolidates a dataset composed of public images and our field-taken picture samples. The experiment verifies the YOLO-CSM as a suitable solution for small and distant object detection that over-performs several well-used algorithms, featuring a 16.3% faster detection speed than YOLOv5 and a 3.3% better detection accuracy than YOLOv7. Finally, this work conducts an interpretability experiment to reveal the similarity between YOLO-CSM’s attention patterns and that of our humans, aiming to explain YOLO-CSM’s advantages in detecting small objects and minor defects in the working environments of power transmission lines.
Publisher
Research Square Platform LLC
Reference58 articles.
1. Yu N (2018), December Study on Resource Management of Electric Oriented Fiber Cable. In 2018 IEEE International Conference of Safety Produce Informatization (IICSPI) (pp. 169–172). IEEE
2. Zhang K, Huang W (2020, September) Defect detection of anti-vibration hammer based on improved faster R-CNN. In 2020 7th International Forum on Electrical Engineering and Automation (IFEEA). IEEE, pp 889–893
3. Design and Application of a UAV Autonomous Inspection System for High-Voltage Power Transmission Lines;Li Z;Remote Sens,2023
4. Power transmission line inspection robots: A review, trends and challenges for future research;Alhassan AB;Int J Electr Power Energy Syst,2020
5. Automatic autonomous vision-based power line inspection: A review of current status and the potential role of deep learning;Jenssen R;Int J Electr Power Energy Syst,2018