RESUMEN
The blockage and the deformation and failure of the ore pass walls constitute two major problems in applying the ore passes in mines. These problems, which affect the normal operation of mine production, have attracted widespread attention worldwide. The labeled-particle layers method based on numerical simulation was used to investigate the flow characteristics of the ore-rock bulk in the ore pass under different eccentric distances of the ore-drawing port center and ore pass centerline. Moreover, the overpressure coefficient and overpressure number are used to evaluate the degree of damage to the ore-pass wall. The results show that: (1) During the ore drawing process under different eccentricities, the flow patterns of the topmost labeled-particle layers in the ore pass are always in a "-" shaped distribution, and the other layers in the ore pass gradually transition from a "-" shape to a "U" shaped distribution, and then gradually to a "V" shape closer to the drawing funnel; (2) in the range of the ore-drawing funnel, the flow pattern of the ore-rock bulk gradually changes from an upright "V" shape to an italic "V" shape with increasing eccentricity and tip slants to the drawing port, and is less affected in the shaft; and (3) the dynamic lateral pressure caused by the ore-rock flow mainly acts on the lower part of the storage section. When the eccentricity is 0.5 m, the maximum overpressure coefficient and overpressure times are the smallest, leading to the lowest damage degree of the ore pass wall.
RESUMEN
The unsafe action of miners is one of the main causes of mine accidents. Research on underground miner unsafe action recognition based on computer vision enables relatively accurate real-time recognition of unsafe action among underground miners. A dataset called unsafe actions of underground miners (UAUM) was constructed and included ten categories of such actions. Underground images were enhanced using spatial- and frequency-domain enhancement algorithms. A combination of the YOLOX object detection algorithm and the Lite-HRNet human key-point detection algorithm was utilized to obtain skeleton modal data. The CBAM-PoseC3D model, a skeleton modal action-recognition model incorporating the CBAM attention module, was proposed and combined with the RGB modal feature-extraction model CBAM-SlowOnly. Ultimately, this formed the Convolutional Block Attention Module-Multimodal Feature-Fusion Action Recognition (CBAM-MFFAR) model for recognizing unsafe actions of underground miners. The improved CBAM-MFFAR model achieved a recognition accuracy of 95.8% on the NTU60 RGB+D public dataset under the X-Sub benchmark. Compared to the CBAM-PoseC3D, PoseC3D, 2S-AGCN, and ST-GCN models, the recognition accuracy was improved by 2%, 2.7%, 7.3%, and 14.3%, respectively. On the UAUM dataset, the CBAM-MFFAR model achieved a recognition accuracy of 94.6%, with improvements of 2.6%, 4%, 12%, and 17.3% compared to the CBAM-PoseC3D, PoseC3D, 2S-AGCN, and ST-GCN models, respectively. In field validation at mining sites, the CBAM-MFFAR model accurately recognized similar and multiple unsafe actions among underground miners.