In the complex environment of fully mechanized mining faces, the current object detection algorithms face significant challenges in achieving optimal accuracy and real-time detection of mine personnel and safety helmets. This difficulty arises from factors such as uneven lighting conditions and equipment obstructions, which often lead to missed detections. Consequently, these limitations pose a considerable challenge to effective mine safety management. This article presents an enhanced algorithm based on YOLOv11n, referred to as GCB-YOLOv11. The proposed improvements are realized through three key aspects: Firstly, the traditional convolution is replaced with GSConv, which significantly enhances feature extraction capabilities while simultaneously reducing computational costs. Secondly, a novel C3K2_FE module was designed that integrates Faster_block and ECA attention mechanisms. This design aims to improve detection accuracy while also accelerating detection speed. Finally, the introduction of the Bi FPN mechanism in the Neck section optimizes the efficiency of multi-scale feature fusion and addresses issues related to feature loss and redundancy. The experimental results demonstrate that GCB-YOLOv11 exhibits strong performance on the dataset concerning mine personnel and safety helmets, achieving a mean average precision of 93.6%. Additionally, the frames per second reached 90.3 f·s⁻¹, representing increases of 3.3% and 9.4%, respectively, compared to the baseline model. In addition, when compared to models such as YOLOv5s, YOLOv8s, YOLOv3 Tiny, Fast R-CNN, and RT-DETR, GCB-YOLOv11 demonstrates superior performance in both detection accuracy and model complexity. This highlights its advantages in mining environments and offers a viable technical solution for enhancing the safety of mine personnel.

The current methods for detecting coal gangue face several challenges, including low detection accuracy, a high probability of missed detections, and inadequate real-time performance. These issues stem from the complexities associated with diverse industrial environments and mining conditions, such as the mixing of coal gangue and insufficient illumination within coal mines. A detection model, referred to as EBD-YOLO, is proposed based on YOLOv11n. First, the C3k2-EMA module is integrated with the EMA attention mechanism within the C3k2 module of the backbone network, thereby enhancing the model’s feature extraction capabilities. Second, the introduction of the BiFPN module reduces computational complexity while enriching both semantic information and detail within the model. Finally, the incorporation of the DyHead detector head further enhances the model’s ability to express features in complex environments. The experimental results indicate that the precision (P) and recall (R) of the EBD-YOLO model are 88.7% and 83.9%, respectively, while the mean average precision (mAP@0.5) is 91.7%. These metrics represent increases of 3.4%, 3.7%, and 3.9% compared to those of the original model, respectively. Additionally, the frames per second (FPS) improved by 10.01%. Compared to the mainstream YOLO target detection algorithms, the EBD-YOLO detection model achieves the highest mAP@0.5 while maintaining superior detection speed. It exhibits a slight increase in computational load, despite an almost unchanged number of parameters, and demonstrates the best overall detection performance. The EBD-YOLO detection model effectively addresses the challenges of missed detections, false detections, and real-time detection in the complex environment of coal mines.

The mine air door is the primary facility for regulating airflow and controlling the passage of personnel and vehicles. Intelligent monitoring of personnel and vehicles within the mine air door system is a crucial measure to ensure the safety of mine operations. To address the issues of slow speed and low efficiency associated with traditional detection methods in mine air door scenarios, this study proposes a CGSW-YOLO man-vehicle monitoring model based on YOLOv8n. Firstly, the Faster Block module, which incorporates partial convolution (PConv), is integrated with the C2f module of the backbone network. This combination aims to minimize redundant calculations during the convolution process and expedite the model’s aggregation of multi-scale information. Secondly, standard convolution is replaced with GhostConv in the backbone network to further reduce the number of model parameters. Additionally, the Slim-neck module is integrated into the neck feature fusion network to enhance the information fusion capability of various feature maps while maintaining detection accuracy. Finally, WIoUv3 is utilized as the loss function, and a dynamic non-monotonic focusing mechanism is implemented to adjust the quality of the anchor frame dynamically. The experimental results indicate that the CGSW-YOLO model exhibits strong performance in monitoring man-vehicle interactions in mine air door scenarios. The Precision (P), Recall (R), and the map@0.5 are recorded at 88.2%, 93.9%, and 98.0%, respectively, representing improvements of 0.2%, 1.5%, and 1.7% over the original model. The Frames Per Second (FPS) has increased to 135.14 f·s⁻¹, reflecting a rise of 35.14%. Additionally, the parameters, the floating point operations per second (FLOPS), and model size are 2.36 M, 6.2 G, and 5.0 MB, respectively. These values indicate reductions of 21.6%, 23.5%, and 20.6% compared to the original model. Through the verification of on-site surveillance video, the CGSW-YOLO model demonstrates its effectiveness in monitoring both individuals and vehicles in scenarios involving mine air doors.

In the study of the movement law of the overlying rock containing intercalated gangue and coal, Digital Image Correlation (DIC) was employed to document the changes in the strain field of the upper rock layer of the coal seam during the experiment. Prior to the formation of fractures, a stress concentration area consistently exists. The emergence of this stress concentration area provides predictive insights into the development of fractures. Monitoring the progression of fractures offers a reflection of the temporal changes occurring in the overlying rock layer of the coal seam. Currently, the selection of full-process monitoring data for the DIC strain field is often conducted through manual identification, a method that is highly subjective. Consequently, in conjunction with the DIC stress analysis cloud map, the fracture development process is categorized into three distinct stages: fracture generation (FG), fracture development (FD), and fracture completion (FC). Leveraging the YOLOv8 model, we propose a novel algorithm tailored for dynamic fractures, termed GFB-YOLO, to effectively identify the fracture development process. Firstly, the GSConv is introduced into the backbone network to replace the standard convolution, aiming to enhance the model’s accuracy in fracture extraction. Secondly, the Faster block is incorporated into C2f to improve the model’s real-time performance for fracture identification, while simultaneously significantly reducing model complexity. Lastly, the Bi-FPN mechanism is integrated into the neck network to enhance the fusion efficiency of fractures across different scales within the model. The research revealed that the average detection accuracy, real-time detection performance, and model complexity of GFB-YOLO for identifying the fracture development process in the experiment were 91.3%, 93 f·s ⁻¹ , and 6.1G, respectively. Notably, the real-time detection performance improved by 12.0%, effectively addressing the issue of missed detections. It provides a new technical means for DIC strain field fracture development observation scene.