During fully mechanized caving mining with large mining height, the significant enlargement of the extraction space hinders the effective filling of the fractured and caved overlying strata, resulting in frequent occurrences of strong ground pressure. To address this problem, a ground pressure prediction model for strong ground pressure zones was proposed based on hydraulic support load data, integrating a KNN-AWPSO(adaptive weighted particle swarm optimization)-GRU(gated recurrent unit) framework. In view of missing and abnormal hydraulic support load data, the KNN algorithm was employed for data correction, while the load distribution characteristics were analyzed. An AWPSO-GRU prediction model was constructed to predict and evaluate strong ground pressure zones. The results indicate that the KNN algorithm achieves satisfactory filling performance when the missing rate of data is within 5%. Furthermore, compared with PSO-GRU and GRU models, the proposed AWPSO-GRU model significantly improves prediction accuracy for strong ground pressure zones and achieves reliable regional load forecasting for fully mechanized caving mining faces. The model provides a basis for enhancing the adaptability of hydraulic supports in fully mechanized caving mining and for safety forecasting in strong ground pressure zones.
XieY S, ZhaoY S. Numerical simulation of the top coal caving process using the discrete element method[J]. International Journal of Rock Mechanics and Mining Sciences, 2009, 46(6): 983-991.
YanShao-hong, YinXi-wen, XuHong-jie, et al. Roof structure of short cantilever-articulated rock beam and calculation of support resistance in full-mechanized face with large mining height[J]. Journal of China Coal Society, 2011, 36(11): 1816-1820.
[4]
LiangM F, HuC J, YuR, et al. Optimization of the process parameters of fully mechanized top-coal caving in thick-seam coal using BP neural networks[J]. Sustainability, 2022, 14(3): 1340.
[5]
LeT D, BuiX N. Effect of key parameters on top coal first caving and roof first weighting in longwall top coal caving: a case study[J]. International Journal of Geomechanics, 2020, 20(5): 04020037.
[6]
LuY B, YanS H, ZhouK Y, et al. Structural quantification of multi-thick hard roof and strong ground pressure control in large mining height stope: a case study[J]. Geomechanics and Geophysics for Geo-Energy and Geo-Resources, 2025, 11: 56.
[7]
YangL, WangJ C, YangS L, et al. Improving the top coal recovery ratio in longwall top coal caving mining using drawing balance analysis[J]. International Journal of Mining, Reclamation and Environment, 2023, 37(5): 319-337.
[8]
SongY, FengY H, WangW D, et al. Data-driven prediction framework of surrounding rock pressure in a fully mechanized coal face with temporal-spatial correlation[J]. Scientific Reports, 2024, 14(1): 28476.
[9]
HuH D, LiY H, YaoQ L, et al. A prediction approach based on clustering reconstruction for abnormal mining pressure of longwall face under residual coal pillars[J]. Processes, 2024, 12(2): 283.
ZhaoYi-xin, YangZhi-liang, MaBin-jie, et al. Deep learning predietion and model generalization of ground pressure for deep longwall face with large mining height[J]. Journal of China Coal Sociey, 2020, 45(1): 54-65.
LiuQian-jin, XuGang, LuZhen-long, et al. Research and application of comprehensive evaluation and early warning model of hydraulicsupport working[J]. Coal Science and Technology, 2022, 50(10): 198-206.
YinXi-wen, XuGang, LiuQian-jin, et al. Method of double-cycle analysis and prediction for rock pressure based on the support load[J]. Journal of China Coal Society, 2021, 46(10): 3116-3126.
ChengJing-yi, WanZhi-jun, PengSyd S, et al. Technology of intelligent sensing of longwall shield supports status and roof strata based on massive shield pressure monitoring data[J]. Journal of China Coal Society, 2020, 45(6): 2090-2103.
[18]
ZhangQ L, YueJ C, LiuC, et al. Study of automated top-coal caving in extra-thick coal seams using the continuum-discontinuum element method[J]. International Journal of Rock Mechanics and Mining Sciences, 2019, 122: 104033.
[19]
DongJ J, XieZ Q, JiangH, et al. Multiple regression method for working face mining pressure prediction based on hydraulic support monitoring dataset[J]. Frontiers in Earth Science, 2023, 11: 1114033.
[20]
KimK G. Normalized class coherence change-based kNN for classification of imbalanced data[J]. Pattern Recognition, 2021, 120: 108126.
[21]
LiuJ B, ZhouJ, SunH F, et al. The inverse optimization of lithographic source and mask via GA-APSO hybrid algorithm[J]. Photonics, 2023, 10(6): 638.
[22]
LinS S, ShenS L, ZhouA. Real-time analysis and prediction of shield cutterhead torque using optimized gated recurrent unit neural network[J]. Journal of Rock Mechanics and Geotechnical Engineering, 2022, 14(4): 1232-1240.
[23]
ZhaoZ N, YunS N, JiaL Y, et al. Hybrid VMD-CNN-GRU-based model for short-term forecasting of wind power considering spatio-temporal features[J]. Engineering Applications of Artificial Intelligence, 2023, 121: 105982.