Condition Monitoring of Transmission Line Vibration Dampers using YOLOv12 Model

Vibration dampers play a crucial role in maintaining the structural stability of overhead transmission lines by mitigating mechanical oscillations caused by wind and other environmental factors. Detecting defects, such as broken components, is essential to prevent failures that may compromise the integrity of power systems. This study proposes an advanced single-stage deep learning model for the condition monitoring of vibration dampers. A public dataset was utilized and expanded using image augmentation techniques to address the challenge of limited data availability. The YOLOv12 model was employed for defect localization, leveraging its real-time detection capabilities and high accuracy. Experimental results demonstrate that the model achieved an accuracy of $\mathbf{9 4. 7 \%}$ in identifying and localizing defective dampers. Additionally, a web application was developed to assist the maintenance crew, facilitating efficient and automated inspections. The proposed solution enhances the reliability of defect detection while streamlining the inspection process.