Abstract: In response to the problems of slow detection speed and low automation control level in traditional PLC-based mine air door monitoring technologies, a mine air door monitoring system based on PLC and an improved YOLOv11 model was proposed, which embedded the improved YOLOv11 model into the conventional PLC-based air door monitoring system to realize real-time and accurate recognition of underground personnel and vehicles and intelligent linkage control of air door opening and closing. Taking YOLOv11 as the base model, an EAW-YOLO model was proposed. The exponential moving average (EMA) attention mechanism was integrated into the C3k2 module to form a C3k2-EMA module to enhance the model's feature extraction capability. Then, ADown convolution was introduced to retain key information while performing channel dimensionality reduction. Finally, the WIoU loss function was introduced to enhance the regression convergence speed of the model by dynamically adjusting the weighting of different anchor boxes based on their importance. Experimental results showed that: ① compared with YOLOv11, the EAW-YOLO model improved accuracy by 1.6% and mAP@0.5 by 1.9%, reduced the number of model parameters by 19.2%, and increased inference speed by 9.7% to reach 86.7 frames/s. ② Compared with YOLOv11, Faster-CNN, EfficientDet, and RT-DETR, the EAW-YOLO model improved accuracy by 1.6%, 0.6%, 2.0%, and 0.2%, respectively, improved mAP@0.5 by 1.9%, 0.7%, 1.6%, and 1.1%, respectively, reduced the number of parameters by 0.5×10⁶, 135.0×10⁶, 1.8×10⁶, and 40.7×10⁶, respectively, increased inference speed by 7.7, 51.2, 9.8, and 35.1 frames/s, respectively, and reduced model size by 0.4, 102.9, 11.1, and 80.9 MiB, respectively. ③ For different vehicles with large targets at close range, the EAW-YOLO model showed higher detection accuracy. For different vehicles with small targets at long distance, the detection accuracy of the EAW-YOLO model was slightly improved. For small personnel targets at long distance with blurred edge features, the EAW-YOLO model showed a larger improvement in detection accuracy and effectively identified correct personnel targets. In scenes with occlusion and strong backlighting, the EAW-YOLO11 model achieved higher detection accuracy. To verify the feasibility of the mine air door monitoring system based on PLC and the improved YOLOv11 model, laboratory validation was conducted, and the results showed that when the camera captured a vehicle model, the recognition signal was transmitted to the PLC in real time, thereby accurately controlling the opening and closing actions of the air door device.