Accurate identification and prediction of abnormal strata pressure in intelligent longwall mining faces are essential for ensuring mine safety and production efficiency. Although machine learning has been increasingly applied to hydraulic support resistance prediction, challenges remain in capturing the strong temporal dependency and periodic pressure characteristics associated with strata behavior. In this study, a novel abnormal strata pressure identification and prediction framework based on the Gated Recurrent Unit (GRU) integrated with an attention mechanism (AM) is proposed for fully mechanized coal mining faces. The model is designed to capture both short-term fluctuations and long-term cyclic characteristics of support resistance, thereby enhancing its sensitivity to dynamic loading conditions and precursory abnormal pressure signals. Results indicate that the proposed GRU-AM model achieves high prediction accuracy for both single-support and multi-support scenarios, with the predicted resistance closely matching the measured values. Compared with conventional LSTM and CNN models, GRU-AM demonstrates consistently improved performance across multiple evaluation metrics, including RMSE, MAE, MAPE, and Pearson correlation coefficient (R), in both short-step and long-step prediction tasks. At a 1 min step length, the model achieves an overall Accuracy of 0.9741 for abnormal pressure identification, and maintains a high Accuracy of 0.9195 at a 10 min step length. Field application across different mining conditions further confirms the robustness, computational efficiency, and practical reliability of the proposed method. These results demonstrate that the GRU-AM framework provides an effective and scalable solution for real-time abnormal strata pressure recognition and early warning in intelligent coal mining environments.

Coal-mine-gas-monitoring data exhibits missing phenomena due to the harsh underground operating environment. Accurate imputation of missing values in gas-monitoring sequences serves as a key data foundation for guaranteeing the continuity of gas data, enhancing the reliability of disaster early warning, and improving the accuracy of mine safety situation analysis and judgment. Aiming at the prevalent random and segmented missing issues in coal-mine-gas-monitoring time-series data, and the limitation that existing imputation methods struggle to accurately capture the nonlinear spatiotemporal correlations and long-range temporal dependencies of such data, this study proposes a missing data imputation method for coal mine gas time-series data based on the Spatio-Temporal Graph Attention Network—Echo State Network (ST-GAT-ESN). Firstly, this method extracts temporal features of the gas concentration sequence using a Gated Recurrent Unit (GRU). Subsequently, it models multiple monitoring points as graph nodes through a Graph Attention Network (GAT), constructs an adjacency matrix based on airflow propagation relationships, and adaptively learns the spatial dependency weights between monitoring points to realize the deep fusion of spatiotemporal features. Finally, it designs a dual-channel Echo State Network (ESN), synchronously inputs the spatiotemporal fusion features of the missing regions before and after, efficiently fits the nonlinear evolutionary trend of the data by virtue of the echo state property of the reservoir, and solves the output layer weights through ridge regression to achieve accurate imputation of missing values. Experimental results demonstrate that, compared with the single-ST-GAT-ESN, ESN, and ARIMA models, the proposed method achieves the optimal imputation performance in both random and segmented missing scenarios within the missing rate range of 5–50%. The three evaluation metrics—Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE)—are reduced by 30–80% compared with the benchmark models. Moreover, the imputation curve achieves the best fitting performance with the ground-truth curve at a 50% segmented missing rate. This study confirms that the ST-GAT-ESN model effectively enhances the adaptability and robustness to complex missing patterns via spatiotemporal collaborative modeling and a dual-channel fusion mechanism, providing a high-precision and highly stable technical solution for ensuring the integrity of coal-mine-gas-monitoring data, and also provides theoretical references and engineering insights for the missing-value processing of industrial time-series monitoring data.