煤矿罐笼是矿工进出矿井的主要运输工具,承担着从地面到地下数百米深的运载任务。由于罐笼在运行过程中存在速度快、空间有限等特点,矿工在罐笼内站立不稳、意外摔倒等行为可能导致严重的安全事故。提出了一种基于人员行为检测的罐笼辅助系统,以提升煤矿作业的安全性,特别是保障煤矿工人在井下和运输过程中的安全。系统利用IP摄像头实时监控罐笼内部,通过边缘计算设备实现目标检测和行为识别算法,及时发现和处理矿工的异常行为。采用轻量级的MobileNetv2和改进的TSM模型,并增加多尺度区域特征融合模块(MRFA),以提升行为识别的精确性和鲁棒性。试验结果表明,改进后的TSM模型在准确率、参数量和推理速度方面均优于传统行为识别算法,特别是在计算资源有限的边缘设备上表现出更高的效率和可靠性。改进的TSM模型在矿工行为数据集上的准确率达99.30%,显著高于其他主流行为识别算法,具有较高的实用价值和广泛的应用前景。

 The coal mine cage is the main transportation tool for miners to enter and exit the mine, undertakingthe task of transporting from the ground to hundreds of meters deep underground. Due to the fast speed and limitedspace of the cage during operation, miners may experience serious safety accidents such as unstable standing andaccidental falls inside the cage. A cage assistance system based on personnel behavior detection was proposed toenhance the safety of coal mining operations, especially to ensure the safety of coal miners underground and duringtransportation. The system uses IP cameras to monitor the inside of the cage in real time, and realizes targetdetection and behavior recognition algorithms through edge computing equipment, so as to detect and deal withabnormal behaviors of miners in a timely manner. Adopting lightweight MobileNetv2 and improved TSM model, andadding multi-scale region feature fusion module ( MRFA) to improve the accuracy and robustness of behaviorrecognition. The experimental results showed that the improved TSM model outperformed traditional behaviorrecognition algorithms in terms of accuracy, parameter count, and inference speed, especially exhibiting higherefficiency and reliability on edge devices with limited computing resources. The improved TSM model achieves an     accuracy of 99. 30% on the miner behavior dataset, significantly higher than other mainstream behavior recognitionalgorithms, and has high practical value and broad application prospects.