IoT-enabled sensor devices and machine learning methods have played an essential role in monitoring and forecasting mine hazards. In this paper, a prediction model has been proposed for improving the safety and productivity of underground coal mines using a hybrid CNN-LSTM model and IoT-enabled sensors. The hybrid CNN-LSTM model can extract spatial and temporal features from mine data and efficiently predict different mine hazards. The proposed model also improves the flexibility, scalability, and coverage area of a mine monitoring system to an underground mine's remote locations to minimize the loss of miners' lives. The proposed model efficiently predicts miner's health quality index (MHQI) for working faces and gases in goaf areas of mines. The experimental results demonstrated that the predicted mean square error of the proposed model is less than 0.0009 and 0.0025 for MHQI; 0.0011 and 0.0033 for CH₄ in comparison with CNN and LSTM models, respectively. The less means square error indicates the better prediction accuracy of the trained. Similarly, the correlation coefficient (R²) value of the proposed model is found greater than 0.005 and 0.001 for MHQI; 0.007 and 0.001 for CH₄ compared to CNN and LSTM models, respectively. Thus, the proposed CNN-LSTM model performed better than the two existing models.

支持物联网的传感器设备和机器学习方法在监测和预测矿山危险方面发挥了重要作用。在本文中，使用混合 CNN-LSTM 模型和支持物联网的传感器提出了一种预测模型，用于提高地下煤矿的安全性和生产率。混合 CNN-LSTM 模型可以从矿山数据中提取空间和时间特征，并有效地预测不同的矿山危害。所提出的模型还提高了矿山监测系统对地下矿山偏远地区的灵活性、可扩展性和覆盖范围，以最大限度地减少矿工的生命损失。所提出的模型有效地预测了矿山采空区工作面和瓦斯的矿工健康质量指数（MHQI）。实验结果表明，所提模型的预测均方误差分别小于0.0009和MHQI的0.0025；CH 为 0.0011 和 0.0033₄分别与 CNN 和 LSTM 模型进行比较。均方误差越小表明训练的预测精度越好。类似地，对于MHQI，发现所提出模型的相关系数（R ²）值大于0.005和0.001；与 CNN 和 LSTM 模型相比，CH ₄分别为 0.007 和 0.001 。因此，所提出的 CNN-LSTM 模型比现有的两个模型表现更好。