In night-time construction scenarios of under-construction nuclear power plants, some yellow lights and open flames exhibit highly similar visual characteristics, resulting in frequent false alarms of fire sources. Such false alarm information tends to drown out real fire alarm signals, which not only severely disrupts construction operations but also endangers fire safety. To address this problem, this paper proposes an intelligent fire risk identification method based on an enhanced YOLOv8n (named YOLO-Fire). Specifically, shallow convolutional layers embedded with a coordinate attention mechanism are integrated into the Backbone of YOLOv8n; the Neck is optimised to improve the efficiency of multi-scale feature fusion; and the Head is enhanced to strengthen the localization and classification branches. Additionally, a composite loss function combining classification loss, regression loss, and similarity loss is designed, coupled with night-scene-specific data augmentation techniques and a two-stage progressive training strategy. Experimental results show that YOLO-Fire reduces the false alarm rate by 14.3%, increases the mean average precision (mAP@0.5) for open flames by 11.3% to 75.2%, and maintains an inference speed of over 85 frames per second (FPS). This study achieves an optimal balance between false alarm control, small object detection accuracy, and real-time processing efficiency, effectively resolving the misclassification issue between open flames and lights in night-time construction scenarios, and providing precise and efficient intelligent technical support for fire risk prevention and control during the construction phase of nuclear power plants.
Li et al. (Tue,) studied this question.