Abstract
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.