In coal mining operations, the stable operation of hydraulic supports is crucial for ensuring mine safety. However, the nonlinear, non-stationary characteristics and noise interference in hydraulic support pressure data pose significant challenges for anomaly detection and fault diagnosis. This study proposes an anomaly detection and failure identification method based on Gated Recurrent Unit Autoencoder (GRU-AE), aimed at achieving anomaly detection in hydraulic support pressure data and equipment failure early warning. Through in-depth analysis of data from two coal mines in China, we systematically evaluated the model’s key parameters. The study revealed that window size had a limited impact on model performance, with a window length of 144 demonstrating optimal comprehensive performance in both anomaly detection and failure mode identification. The study also investigated the effectiveness of teacher forcing techniques. Although this technique can accelerate model convergence, it may lead to training instability and reduced generalization capability, requiring careful consideration in practical applications. Our proposed Recurrent Reconstruction Network model demonstrated excellent performance in complex coal mine hydraulic support data, effectively identifying anomalous regions and potential equipment failure characteristics while revealing potential deviations between model predictions and actual data, demonstrating its superior learning capability for periodic data patterns and equipment failure characteristics. Experimental results validated the effectiveness of the GRU-AE model in hydraulic support pressure anomaly detection and equipment fault diagnosis, providing an innovative technical solution for coal mine safety monitoring.

The traditional anchoring method of bolts has insufficient control over the surrounding rock of the coal roadway. Based on this background, full-stress anchoring technology of bolts was proposed. Firstly, a mechanical relationship model of a bolt-drawing, anchoring interface was established to obtain the equations of the axial force and obtain shear stress distribution as well as the decreasing-load transfer law of the anchoring section of bolts. Through studying the prestress-loading experimental device of bolts, we found that increasing the initial preload could increase the axial force under the same conditions and the retarded anchoring section could control the axial-force loss of bolts in the middle of the anchoring section. Under the full-stress anchoring mode, the effect of applying a pre-tightening force was better than that of applying a pre-tightening force under traditional anchoring methods. Moreover, FLAC3D (Fast Lagrangian Analysis of Continua 3D; ITASCA (Ita sca International Inc), Minnesota, USA) numerical simulation calculation was performed. Under the full-stress anchoring mode of bolts, the increased anchoring length reduced the damage of the anchoring section, with a wider control range of the rock formation and higher strength of the compressive-stress anchoring zone. Based on the above research, four methods for applying the full-stress anchoring technology of bolts in engineering were proposed. The full-stress anchoring technology of bolts in the coal roadway has been applied in the support project of the return-air roadway at working face 3204 of the Taitou Coking Coal Mine of the Xiangning Coking Coal Group, Shanxi. The maximum moving distance of the roof and floor of the roadway was reduced from 200 to 42 mm, and the maximum moving distance on both coal sides was reduced from 330 to 86 mm. The full-stress anchoring technology of bolts was able to control the surrounding rock in the coal roadway.

The control of hard roof conditions in underground coal mining is critical for ensuring mining safety and efficiency. Hard roof control remains a critical challenge in underground mining, particularly affecting mining safety and efficiency. Traditional support theories often show limitations in addressing the complex interactions between bolt spacing patterns and geological variability. This study focuses on the No. 10904 working face of Jingu Mine, where three distinct roof types are present: Type I (thick limestone roof, TLR, ≥1.2 m), Type II (moderate limestone roof, MLR, 0.5–1.2 m), and Type III (composite mudstone–limestone roof, CLR). Through FLAC3D numerical simulation and field validation, the mechanisms of bolt support under hard roof conditions were systematically investigated, and the optimization of bolt support parameters, including spacing, length, and pre-tension force, was conducted. The results indicate that: (1) when the ratio between lateral and row spacing approaches unity, reducing lateral spacing while increasing row spacing enhances support effectiveness, achieving 2 mm less roof subsidence with the 1.0 m × 1.5 m configuration compared to the 1.4 m × 0.8 m arrangement, despite a 21% reduction in bolt density; (2) an optimal rib bolt length of 1.8 m was determined, with support effectiveness diminishing beyond 2.0 m, and 1.5 m-long bolts reducing rib convergence by 15% compared to unsupported conditions; and (3) when the anchoring length exceeds 60% of the total bolt length, further increases in bolt length have minimal impact on deformation control under TLR, MLR, and CLR conditions. Field implementation of the optimized support scheme confirmed its effectiveness, with borehole television inspection showing no separation or fracturing within the monitored depth of 4 m in the roof strata. These findings provide practical guidelines for support design in similar geological settings, particularly for shallow-buried roadways with hard roof conditions.

Microseismic data are widely employed for assessing rockburst risks; however, significant disparities exist in the monitoring capabilities of seismic networks across different mines, and none can capture a complete dataset of microseismic events. Such differences introduce unfairness when applying the same methodologies to evaluate rockburst risks in various mines. This paper proposes a method for assessing the monitoring capability of seismic networks applicable to heterogeneous media in mines. It achieves this by integrating three gradient boosting algorithms: Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and Categorical Boosting (CatBoost). Initially, the isolation forest algorithm is utilized for preliminary data cleansing, and feature engineering is constructed based on the relative locations of event occurrences to monitoring stations and the working face. Subsequently, the optimal hyperparameters for three models are searched for using 8508 microseismic events from the a Coal Mine in eastern China as samples, and 18 sub-models are trained. Model weights are then determined based on the performance metrics of different algorithms, and an ensemble model is created to predict the monitoring capability of the network. The model demonstrated excellent performance on the training and test sets, achieving log loss, accuracy, and recall scores of 7.13, 0.81, and 0.76 and 6.99, 0.80, and 0.77, respectively. Finally, the method proposed in this study was compared with traditional approaches. The results indicated that, under the same conditions, the proposed method calculated the monitoring capability of the key areas to be 11% lower than that of the traditional methods. The reasons for the differences between these methods were identified and partially explained.

Hydraulic supports in coal mining faces require continuous pressure monitoring to detect anomalies indicative of roof instability or equipment failure. Existing reconstruction-based methods rely on standard convolutional or recurrent encoders whose limited receptive fields or coarse temporal representations restrict detection accuracy; static per-window thresholding further discards temporal continuity during online deployment. This study proposes a temporal convolutional network autoencoder (TCN-AE) coupled with a Cumulative Sum (CUSUM) control chart for online anomaly detection in hydraulic support pressure data. The TCN encoder uses dilated convolutions with symmetric padding and residual connections, producing an exponentially expanding receptive field that captures temporal patterns at multiple scales. The CUSUM chart accumulates sustained positive deviations in the reconstruction error sequence, improving detection sensitivity while suppressing isolated false alarms. Component analysis experiments on synthetic anomalies show TCN-AE achieves an AUC of 0.811, outperforming CNN, LSTM, GRU, and fully connected autoencoder variants, along with Isolation Forest and One-Class SVM. On a manually curated real fault test set, where per-window reconstruction scores carry negligible discriminative information (AUC = 0.586, near chance), the CUSUM strategy exploits temporal continuity to improve F1 from 0.213 to 0.905 for TCN-AE. This +0.692 gain is driven entirely by temporal accumulation rather than model discriminability, demonstrating that the CUSUM framework is most valuable precisely when per-window signals are weakest.