<![CDATA[Manual monitoring of Personal Protective Equipment (PPE) compliance in electric power distribution is prone to human error, limited supervision, and geographically dispersed work sites. This study proposes an automated PPE detection system using the YOLOv11 deep learning model to enhance safety monitoring at PT PLN (Persero) UP3 Banyuwangi. A dataset of 589 images containing 1,425 labeled PPE instances across seven categories was used to train the YOLOv11s model. The system was deployed via a web-based application with adjustable detection thresholds and validated through interviews with three OHS supervisors. It achieved 94.0% precision, 90.1% recall, and 92.8% mAP@50, with perfect detection for persons and near-perfect results for full-body harnesses. The application processed images in 2–3 seconds on standard CPU hardware, supporting automated documentation for compliance reporting. This is the first known YOLOv11-based PPE detection system tailored to electric power distribution settings. While results are promising, limitations include a small validation set and lower accuracy in detecting safety boots. Future work should explore real-time video analysis, system integration, and long-term studies on safety compliance improvements.]]>
Copyrights © 2025
