Prediction of mine strata behaviors law and main control factors in the fully mechanized caving face of Hujiahe Coal Mine
-
摘要: 现有工作面矿压显现规律预测方法中，基于数值模拟与统计回归的方法无法实现对工作面矿压显现规律的实时精准预测，深度学习方法存在超参数较多且难以设置、模型训练速度慢等问题。针对上述问题，以胡家河煤矿402102回采工作面采动过程中监测到的煤体内部应力变化时序数据为基础，将基于粒子群优化的门控循环单元（PSO−GRU）应用到回采工作面矿压显现规律预测中。采用PSO算法对GRU进行优化，构建PSO−GRU模型，实现对超参数的自动寻优，从而提高GRU的训练速度和预测精度。以预测结果为依据，采用层次分析法建立402102回采工作面矿压主控因素评价指标体系，将顶板条件、回采工艺、煤层赋存、地质构造确定为影响工作面矿压的一级指标，进一步细分出具有代表性的14个二级指标。测试结果表明：① 与未经优化的GRU模型相比，PSO−GRU模型的均方误差（MSE）降低了83.9%，均方根误差（RMSE）降低了59.8%，平均绝对误差（MAE）降低了59.0%，决定系数R2提升了28.9%。② PSO−GRU模型对矿压数据预测的拟合度达0.980以上，具有良好的非线性拟合能力和泛化能力。③ 地质条件中的煤层赋存因素对回采工作面矿压的影响最大，权重为0.47；可人为干预的影响因素中工作面推进速度对矿压的影响最大，权重为0.13。Abstract: Among the existing prediction methods for strata behaviors law in working faces, the methods based on numerical simulation and statistical regression cannot achieve real-time and precise prediction of strata behaviors law in working faces. Deep learning methods have problems such as a large number of hyperparameters that are difficult to set and slow model training speed. In order to solve the above problems, based on the time-series data of internal stress changes in the coal body monitored during the mining process of the 402102 working face in Hujiahe Coal Mine, the particle swarm optimization based gate recurrent unit (PSO-GRU) is applied to predict the strata behaviors law in the working face. The PSO algorithm is used to optimize GRU. The PSO-GRU model is constructed to achieve automatic optimization of hyperparameters, thereby improving the training speed and prediction precision of GRU. Based on the prediction results, the analytic hierarchy process (AHP) is used to establish the evaluation index system of the main control factors of the strata behaviors of the 402102 mining face. The roof conditions, mining technology, coal seam occurrence, and geological structure are identified as the first level indicators affecting the strata behaviors of the working face. The 14 representative second level indicators are further subdivided. The test results show the following points. ① Compared with the unoptimized GRU model, the mean square error (MSE) of the PSO-GRU model is reduced by 83.9%, the root mean square error (RMSE) is reduced by 59.8%, the mean absolute error (MAE) is reduced by 59.0%, and the coefficient of determination R2 is increased by 28.9%. ② The PSO-GRU model has a fitting degree of over 0.980 for predicting strata behaviors data, demonstrating good nonlinear fitting and generalization capabilities. ③ The occurrence factors of coal seams in geological conditions have the greatest impact on the strata behaviors of the mining face, with a weight of 0.47. Among the factors that can be intervened by humans, the impact of advancing speed on the strata behaviors of the working face is the greatest, with a weight of 0.13.
-
表 1 PSO−GRU模型训练结果
Table 1. PSO-GRU model training results
训练集占比/% MSE RMSE MAE 75 43.57 6.61 4.69 80 8.08 2.84 1.89 85 3.56 1.89 1.34 
下载: 导出CSV
表 2 各模型误差对比
Table 2. Error comparison of each model
模型 MSE RMSE MAE R2 LSTM 9.83 3.14 2.33 0.57 GRU 3.56 1.89 1.34 0.76 PSO−GRU 0.57 0.76 0.55 0.98
下载: 导出CSV
表 3 各测站预测误差
Table 3. Prediction error of each measuring station
测站 MSE RMSE MAE R2 1号测站 0.22 0.34 0.39 0.980 2号测站 0.15 0.21 0.12 0.985 3号测站 0.13 0.14 0.12 0.996
下载: 导出CSV
表 4 不同指标数量对应 的RI值
Table 4. RI values corresponding to different numbers of indicators
指标数量 3 4 5 RI 0.58 0.90 1.12
下载: 导出CSV
表 5 各因素权重计算结果和排序
Table 5. Calculation and ranking of weights for each factor
一级指标 二级指标 总权重 总排序 指标 权重 排序 指标 权重 B1 0.0953 4 C1 0.54 0.05 7 C2 0.30 0.03 10 C3 0.16 0.02 12 B2 0.2776 2 C4 0.29 0.08 5 C5 0.47 0.13 2 C6 0.17 0.05 8 C7 0.07 0.02 14 B3 0.4669 1 C8 0.56 0.26 1 C9 0.26 0.12 3 C10 0.12 0.06 6 C11 0.06 0.03 11 B4 0.1603 3 C12 0.26 0.04 9 C13 0.64 0.10 4 C14 0.10 0.02 13
下载: 导出CSV
-
[1] 谢和平. 深部岩体力学与开采理论研究进展[J]. 煤炭学报,2019,44(5):1283-1305.XIE Heping. Research review of the state key research development program of China:deep rock mechanics and mining theory[J]. Journal of China Coal Society,2019,44(5):1283-1305. [2] 丁自伟,李小菲,张杰,等. 掘进巷道空顶板壳理论分析与超越函数的数值解算及其验证[J]. 采矿与安全工程学报,2021,38(3):507-517.DING Ziwei,LI Xiaofei,ZHANG Jie,et al. A theoretical analysis of unsupported roof plate and shell in excavation roadway and numerical calculation and verification of transcendental function[J]. Journal of Mining & Safety Engineering,2021,38(3):507-517. [3] 黄庆享. 浅埋煤层的矿压特征与浅埋煤层定义[J]. 岩石力学与工程学报,2002,21(8):1174-1177. doi: 10.3321/j.issn:1000-6915.2002.08.014HUANG Qingxiang. Ground pressure behavior and definition of shallow seams[J]. Chinese Journal of Rock Mechanics and Engineering,2002,21(8):1174-1177. doi: 10.3321/j.issn:1000-6915.2002.08.014 [4] 何满潮,马新根,王炯,等. 中厚煤层复合顶板切顶卸压自动成巷工作面矿压显现特征分析[J]. 岩石力学与工程学报,2018,37(11):2425-2434.HE Manchao,MA Xingen,WANG Jiong,et al. Feature analysis of working face strata pressure with roof cutting pressure releasing in medium-thick seam and compound roof condition[J]. Chinese Journal of Rock Mechanics and Engineering,2018,37(11):2425-2434. [5] 许家林,鞠金峰. 特大采高综采面关键层结构形态及其对矿压显现的影响[J]. 岩石力学与工程学报,2011,30(8):1547-1556.XU Jialin,JU Jinfeng. Structural morphology of key stratum and its influence on strata behaviors in fully-mechanized face with super-large mining height[J]. Chinese Journal of Rock Mechanics and Engineering,2011,30(8):1547-1556. [6] 宋振骐,蒋金泉. 煤矿岩层控制的研究重点与方向[J]. 岩石力学与工程学报,1996,15(2):33-39.SONG Zhenqi,JIANG Jinquan. The current research situation and developing orientation of strata control in coal mine[J]. Chinese Journal of Rock Mechanics and Engineering,1996,15(2):33-39. [7] 钱鸣高,石平五,许家林. 矿山压力与岩层控制[M]. 徐州:中国矿业大学出版社,2010.QIAN Minggao,SHI Pingwu,XU Jialin. Mining pressure and strata control[M]. Xuzhou:China University of Mining and Technology Press,2010. [8] 闫少宏,尹希文,许红杰,等. 大采高综采顶板短悬臂梁−铰接岩梁结构与支架工作阻力的确定[J]. 煤炭学报,2011,36(11):1816-1820.YAN Shaohong,YIN Xiwen,XU Hongjie,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. [9] 宋振骐. 实用矿山压力控制[M]. 徐州:中国矿业大学出版社,1988.SONG Zhenqi. Practical mine pressure control[M]. Xuzhou:China University of Mining and Technology Press,1988. [10] 钱鸣高,许家林. 煤炭开采与岩层运动[J]. 煤炭学报,2019,44(4):973-984.QIAN Minggao,XU Jialin. Behaviors of strata movement in coal mining[J]. Journal of China Coal Society,2019,44(4):973-984. [11] JU Jinfeng,XU Jialin. Structural characteristics of key strata and strata behavior of a fully mechanized longwall face with 7.0 m height chocks[J]. International Journal of Rock Mechanics & Mining Sciences,2013,58:46-54. [12] 钱鸣高,缪协兴,许家林. 岩层控制中的关键层理论研究[J]. 煤炭学报,1996,21(3):2-7.QIAN Minggao,MIAO Xiexing,XU Jialin. Theoretical study of key stratum in ground control[J]. Journal of China Coal Society,1996,21(3):2-7. [13] 黄庆享,周金龙. 浅埋煤层大采高工作面矿压规律及顶板结构研究[J]. 煤炭学报,2016,41(增刊2):279-286.HUANG Qingxiang,ZHOU Jinlong. Roof weighting behavior and roof structure of large mining height longwall face in shallow coal seam[J]. Journal of China Coal Society,2016,41(S2):279-286. [14] 王金安,尚新春,刘红,等. 采空区坚硬顶板破断机理与灾变塌陷研究[J]. 煤炭学报,2008,33(8):850-855. doi: 10.3321/j.issn:0253-9993.2008.08.003WANG Jin'an,SHANG Xinchun,LIU Hong,et al. Study on fracture mechanism and catastrophic collapse of strong roof strata above the mined area[J]. Journal of China Coal Society,2008,33(8):850-855. doi: 10.3321/j.issn:0253-9993.2008.08.003 [15] 冯龙飞,窦林名,王晓东,等. 回采速度对坚硬顶板运动释放能量的影响机制[J]. 煤炭学报,2019,44(11):3329-3339.FENG Longfei,DOU Linming,WANG Xiaodong,et al. Mechanism of mining advance speed on energy release from hard roof movement[J]. Journal of China Coal Society,2019,44(11):3329-3339. [16] 王继林,袁永,屠世浩,等. 大采高综采采场顶板结构特征与支架合理承载[J]. 采矿与安全工程学报,2014,31(4):512-518.WANG Jilin,YUAN Yong,TU Shihao,et al. Roof structure characteristics in fully mechanized coalface with large mining height and reasonable loading of support[J]. Journal of Mining & Safety Engineering,2014,31(4):512-518. [17] 宋振骐,郝建,石永奎,等. “实用矿山压力控制理论”的内涵及发展综述[J]. 山东科技大学学报(自然科学版),2019,38(1):1-15.SONG Zhenqi,HAO Jian,SHI Yongkui,et al. An overview of connotation and development of practical ground pressure contorl theory[J]. Journal of Shandong University of Science and Technology(Natural Science),2019,38(1):1-15. [18] 赵元放,张向阳,涂敏. 大倾角煤层开采顶板垮落特征及矿压显现规律[J]. 采矿与安全工程学报,2007,24(2):231-234. doi: 10.3969/j.issn.1673-3363.2007.02.024ZHAO Yuanfang,ZHANG Xiangyang,TU Min. Roof caving characteristic and strata behavior in exploiting steep coal seams[J]. Journal of Mining & Safety Engineering,2007,24(2):231-234. doi: 10.3969/j.issn.1673-3363.2007.02.024 [19] 张志强,许家林,刘洪林,等. 沟深对浅埋煤层工作面矿压的影响规律研究[J]. 采矿与安全工程学报,2013,30(4):501-505,511.ZHANG Zhiqiang,XU Jialin,LIU Honglin,et al. Influencing laws study of depth of gully on dynamic strata pressure of working face in shallow coal seams[J]. Journal of Mining & Safety Engineering,2013,30(4):501-505,511. [20] 庞军林. 基于统计分析法的工作面来压预测研究[J]. 煤矿开采,2012,17(4):93-95. doi: 10.3969/j.issn.1006-6225.2012.04.029PANG Junlin. Research on prediction of working face pressure based on statistical analysis method[J]. Coal Mining Technology,2012,17(4):93-95. doi: 10.3969/j.issn.1006-6225.2012.04.029 [21] 张通,赵毅鑫,朱广沛,等. 神东浅埋工作面矿压显现规律的多因素耦合分析[J]. 煤炭学报,2016,41(增刊2):287-296.ZHANG Tong,ZHAO Yixin,ZHU Guangpei,et al. A multi-coupling analysis of mining-induced pressure characteristics of shallow-depth coal face in Shendong mining area[J]. Journal of China Coal Society,2016,41(S2):287-296. [22] 常峰. 基于GA−BP神经网络的工作面顶板矿压预测模型应用研究[D]. 徐州:中国矿业大学,2019.CHANG Feng. Application research of the prediction model for the coal working face roof pressure based on GA-BP neural networks[D]. Xuzhou:China University of Mining and Technology,2019. [23] 赵毅鑫,杨志良,马斌杰,等. 基于深度学习的大采高工作面矿压预测分析及模型泛化[J]. 煤炭学报,2020,45(1):54-65.ZHAO Yixin,YANG Zhiliang,MA Binjie,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. [24] 曾庆田,吕珍珍,石永奎,等. 基于Prophet+LSTM模型的煤矿井下工作面矿压预测研究[J]. 煤炭科学技术,2021,49(7):16-23.ZENG Qingtian,LYU Zhenzhen,SHI Yongkui,et al. Research on prediction of underground coal mining face pressure based on Prophet+LSTM model[J]. Coal Science and Technology,2021,49(7):16-23. [25] LI Jale,ZHANG Zhishuai,WANG Xuefei,et al. Intelligent decision-making model in preventive maintenance of asphalt pavement based on PSO-GRU neural network[J]. Advanced Engineering Informatics,2022,51. DOI: 10.1016/j.aei.2022.101525. [26] 连晓晗,马永强,刘真,等. 基于PSO−GRU神经网络的青椒生长期需水预测[J]. 水利信息化,2023(1):33-39.LIAN Xiaohan,MA Yongqiang,LIU Zhen,et al. Prediction of water demand in green pepper growth period based on PSO-GRU neural network[J]. Water Resources Informatization,2023(1):33-39. [27] KARTHIK C R,RAGHUNANDAN,ASHWATH R B,et al. Forecasting variance of NiftyIT index with RNN and DNN[J]. Journal of Physics:Conference Series,2022,2161(1). DOI: 10.1088/1742-6596/2161/1/012005. [28] 敖永才,师奕兵,张伟,等. 自适应惯性权重的改进粒子群算法[J]. 电子科技大学学报,2014,43(6):874-880. doi: 10.3969/j.issn.1001-0548.2014.06.014AO Yongcai,SHI Yibing,ZHANG Wei,et al. Improved particle swarm optimization with adaptive inertia weight[J]. Journal of University of Electronic Science and Technology of China,2014,43(6):874-880. doi: 10.3969/j.issn.1001-0548.2014.06.014 [29] 刘洋. 基于GRU神经网络的时间序列预测研究[D]. 成都:成都理工大学,2017.LIU Yang. The research of time series prediction based on GRU neural network[D]. Chengdu:Chengdu University of Technology,2017. [30] 龚田李慧. 基于MDS和PSO−GRU神经网络的短期负荷预测研究[D]. 武汉:湖北工业大学,2021.GONG Tianlihui. Research on short-term load forecasting based on MDS and PSO-GRU neural network[D]. Wuhan:Hubei University of Technology,2021. -
点击查看大图
图(6) / 表(5)
计量
- 文章访问数: 103
- HTML全文浏览量: 60
- PDF下载量: 10
- 被引次数: 0
