부산대학교 도서관

The construction industry faces significant challenges, including a high prevalence of occupational incidents, often involving fires, explosions, and burn-related accidents due to worker non-compliance with safety protocols. Adherence to safety guidelines and proper utilization of safety equipment are critical to preventing such incidents and safeguarding workers in hazardous work environments. Consequently, a monitoring system tailored for construction safety during welding operations becomes imperative to mitigate the risk of fire accidents. This paper conducts a brief analysis of OSHA rules pertaining to welding work and introduces the iSafe Welding system, an advanced real-time safety monitoring and compliance enforcement solution designed specifically for construction site welding operations. Harnessing the real-time object detection algorithm YOLOv7 in conjunction with rule-based scene classification, the system excels in identifying potential safety violations. Rigorous evaluation, encompassing precision, recall, mean Average Precision (mAP), accuracy, and the F1-Score, sheds light on its strengths and areas for improvement. The system showcases robust performance in rule-based scene classification, achieving high accuracy, precision, and recall rates. Notably, the iSafe Welding system demonstrates a formidable potential for enhancing construction site safety and regulatory compliance. Ongoing enhancements, including dataset expansion and model refinement, underscore its commitment to real-world deployment and its strength in ensuring worker safety