The frequency of roof-caving accidents ranks first among all coal mine accidents. However, the scattered knowledge system in this field and the lack of standardization exacerbate the difficulty of analyzing roof fall accidents. This study proposes an ontology-based semantic modeling method for roof fall accidents to share and reuse roof fall knowledge for intelligent decision-making. The crucial concepts of roof fall accidents and the correlations between concepts are summarized by analyzing the roof fall knowledge, providing a standard framework to represent the prior knowledge in this field. Besides, the ontology modeling tool Protégé is used to construct the ontology. As for ontology-based deep information mining and semantic reasoning, semantic rules based on expert experience and data fusion technology are proposed to evaluate mines’ potential risks comprehensively. In addition, the roof-falling rules are formalized based on the Jena syntax to make the ontology uniformly expressed in the computer. The Jena reasoning engine is utilized to mine potential tacit knowledge and preventive measures or solutions. The proposed method is demonstrated using roof fall cases, which confirms its validity and practicability. Results indicate that this method can realize the storage, management, and sharing of roof fall accident knowledge. Furthermore, it can provide accurate and comprehensive experience knowledge for the roof fall knowledge requester.

Video AI recognition is crucial for coal mine safety, but complex environments often yield low-quality images, hindering intelligent monitoring. Existing enhancement methods typically focus on image quality alone, lacking adaptability to specific tasks. Therefore, we propose Mine-DCE-YDT: a task-aware low-light image enhancement model that jointly optimizes enhancement with downstream object detection, ensuring enhanced images are both visually clearer and more conducive to accurate detection. Firstly, an improved Zero-DCE algorithm (Mine-DCE) is presented by introducing a Brightness-aware Mask Coordinate Attention (BMCA) module to improve illumination balance in the Value channel of the HSV image and a Multi-scale Detail Enhancement (MDE) module to reinforce textures and suppress noise. Then, Mine-DCE is co-modeled with YOLOv11n by training end-to-end via a joint loss fusing detection and enhancement quality losses to form Mine-DCE-YDT, which can enhance specific details containing image detection targets. Experimental results show that compared with Zero-DCE, Mine-DCE-YDT achieves reductions of 9.5% in NIQE and 35.5% in BRISQUE on the custom-constructed MineDataset and exhibits great enhancement performance on the public dataset LOL-V1. For the miner detection task in MineDataset, the integration of Mine-DCE-YDT with YOLOv11n achieves increases of 2.8% and 8.3% in mAP@0.5 and mAP@0.5:0.95, demonstrating its effectiveness in enhancing task-critical image features.

Vibration deformation of a reflector antenna under a moving load will reduce pointing performance. Current vibration suppression technology for reflector antennas, such as the application of mesh reflector antennas, the construction of large radomes, the use of antennas with high stiffness, and the improvement of the shaft servo systems, can reduce the impact of vibrations. However, the disadvantages of high-frequency transmission, high cost, increased weight, and servo bandwidth limitations, are unavoidable. A cable actuation system is proposed as a method for reducing the vibration of reflector antennas while having little influence on the original structure. In this method, the acceleration of the reflector is measured, and an unbiased minimum variance estimator of the system state is introduced to observe the vibration state of the reflector. Then using the LQR approach, drivers on the slide rail pull the cables to suppress the vibration of the reflector. Moreover, the position of the drivers on the slide rail can be adjusted depending on the moving load condition. Finally, the experimental results show that the vibration time of the reflector without control was approximately 7 s, while the vibration time of the reflector with control was reduced to approximately 1 s when the pendulum fell from the same height to excite the reflector.

Landslides induced by slope deformation in open-pit coal mines pose significant risks to personnel safety and production continuity. Intelligent slope recognition is a prerequisite for early deformation warning, yet no publicly available segmentation dataset specifically targeting open-pit mine slopes currently exists, hindering progress in vision-based monitoring. To address this gap, we present OPMS-Seg, a benchmark dataset for semantic segmentation of open-pit mine slopes. The dataset contains 2814 UAV-captured RGB images and 15,334 polygon instances, covering four geometric slope types (Backlight, Stepped, Rubble, and Bottom types). Annotation files are provided in COCO (JSON), YOLO (TXT), and binary mask (PNG) formats to support diverse segmentation models. All annotations were validated by mining engineering experts. The dataset supports two segmentation tasks: (1) binary segmentation (slope vs. background) and (2) four-class fine-grained segmentation (distinguishing the four slope geometry types). In this paper, we present baseline results for the binary segmentation task, while the four-class task is provided as a benchmark for future research. We evaluated four classic models—U-Net, DeepLabV3+, YOLOv5-Seg, and YOLOv11-Seg—on OPMS-Seg, achieving strong performance and confirming annotation accuracy and scene representativeness. This open-access dataset is intended to accelerate intelligent monitoring, algorithm benchmarking, and low-altitude remote sensing tasks in open-pit environments.