1.College of Energy and Mining Engineering, Xi'an University of Science and Technology, Xi'an 710054, China
2.Key Laboratory of Western Mine Exploitation and Hazard Prevention, Ministry of Education, Xi'an University of Science and Technology, Xi'an 710054, China
3.School of Mine Safety, North China Institute of Science and Technology, Langfang 065201, China
To address the problem of roadway instability caused by deformation of sectional coal pillars beneath remnant pillars during close-distance coal seam mining, a distributed optical fiber sensing method was employed by embedding fibers inside the coal pillars. Strain data from five monitoring boreholes were systematically processed and normalized. A training dataset was constructed using a sliding-window approach, and hyperparameters were optimized via grid search to develop an integrated mine pressure prediction model combining XGBoost (Extreme Gradient Boosting) and LSTM (Long Short-Term Memory) algorithms. The results show that the proposed model achieves a coefficient of determination (R²) of 0.922, with the root mean square error (RMSE) reduced to 4.215 and the mean absolute error (MAE) lowered to 2.135, demonstrating superior prediction accuracy, robustness, and generalization compared with single models such as XGBoost, LSTM, and random forest (RF). The research conclusion reveals the horizontal strain distribution law of coal pillar under the condition of secondary mining, and provides reference for the deformation prediction of section coal pillar.
采用两层Stacking框架,整体计算流程如下:①基学习器训练(Level-0层)使用原始数据分别训练XGBoost和LSTM模型,在验证集上输出各基学习器的预测结果;②构造二级特征,将一级模型的预测结果拼接成新的特征向量 Z;③元学习器训练(Level-1层)以 Z 作为输入特征,使用元学习器进行训练,得到最终集成预测模型;④测试与预测,在测试集上,先用基学习器生成预测结果,再输入元学习器,输出最终预测值。
WANGBeifang, JIANGJiaqi, ZHANGXuepeng, et al. Study on strong mining pressure manifestation cause and support load of shallow-buried working face under goaf[J]. Journal of Mining & Safety Engineering, 2025, 42(5): 1064-1075.
ZHANGHongwei, ZHAOXiangzhuo, HANJun, et al. Strata behavior characteristics of extra contiguous seams with repeated mining[J]. Journal of Liaoning Technical University (Natural Science), 2018, 37(2): 225-231.
DINGZiwei, LIShuai, ZHANGJie, et al. Asymmetric failure mechanism and control of entries in short-distance coal seam[J]. Journal of Mining & Safety Engineering, 2024, 41(2): 242-254.
XUMengtang, XUYoulin, JINZhiyuan. Research on support resistance of contiguous coal seam mining under room-and-pillar gob[J]. Coal Science and Technology, 2020, 48(8): 63-69.
LILiang, HEFulian, XUXuhui, et al. Study on the evolution of stress arch shape and abutment pressure distribution in close distance coal seams[J]. Journal of Mining & Safety Engineering, 2023, 40(2): 295-303.
ZHANGXuping, ZHANGYixin, WANGLiang, et al. Current status and future of research and applications for distributed fiber optic sensing technology[J]. Acta Optica Sinica, 2024, 44(1): 0106001.
CHENGGang, WANGZhenxue, SHIBin, et al. Research progress of DFOS in safety mining monitoring of mines[J]. Journal of China Coal Society, 2022, 47(8): 2923-2949.
[15]
TANGB, CHENGH. Application of distributed optical fiber sensing technology in surrounding rock deformation control of TBM-excavated coal mine roadway[J]. Journal of Sensors, 2018, 2018(1): 8010746.
[16]
CHAIJ, DUW G, YUANQ, et al. Analysis of test method for physical model test of mining based on optical fiber sensing technology detection[J]. Optical Fiber Technology, 2019, 48: 84-94.
[17]
XUS A, ZHANGP S, ZHANGD, et al. Simulation study of fiber optic monitoring technology of surrounding rock deformation under deep mining conditions[J]. Journal of Civil Structural Health Monitoring, 2015, 5(5): 563-571.
YANGJianfeng, LIUZeyu, CHAIJing, et al. Applied research on fiber optic monitoring of internal deformation of coal columns in sections[J]. Journal of Mining and Strata Control Engineering, 2025, 7(2): 224-237.
DUWengang, CHAIJing, ZHANGDingding, et al. Optical fiber sensing and characterization of water flowing fracture development in mining overburden[J]. Journal of China Coal Society, 2021, 46(5): 1565-1575.
ZHANGChensi, WANGMaoning, ZHONGYuzhong, et al. Weak speech signal detection in high interference environment based on distributed acoustic sensing[J]. Advanced Engineering Sciences, 2025(2): 29-39.
CHAIJing, WANGRunpei, DUWengang, et al. Study on time series prediction of rock pressure by XGBoost in optical fiber monitoring[J]. Journal of Mining and Strata Control Engineering, 2020, 2(4): 60-67.
ZHAOYixin, YANGZhiliang, MABinjie, et al. Deep learning prediction and model generalization of ground pressure for deep longwall face with large mining height[J]. Journal of China Coal Society, 2020, 45(1): 54-65.