Research on intelligent design of coal mine roadway support scheme
-
摘要: 目前煤矿巷道支护方案设计仍以人工设计、工程类比、FLAC模型模拟为主，存在主观性强、普适性低、未充分利用煤矿支护大数据等问题，而基于专家系统的设计方法规则设定程序繁琐，工程量大，智能化程度较低。将案例推理（CBR）和深度学习技术引入巷道支护方案设计领域，基于煤矿支护规程、支护规范及煤矿巷道地质报告等文本大数据，提出了一种煤矿巷道支护方案智能设计方法。获取346份不同煤矿的巷道支护资料，抽取结构化数据并划分为输入、输出参数，通过常属性变量滤波和高相关性滤波方法对输入、输出参数进行优化。建立CBR模型，并将抽取的结构化数据导入CBR模型，形成支护方案比选案例库，计算新的巷道支护方案与历史方案的相似度，输出相似度最高的3条历史方案进行对比，实现相似案例比选。分别采用BP神经网络和基于长短期记忆（LSTM）网络建立煤矿巷道支护方案自动生成模型，通过对比预测指标，确定采用基于LSTM模型与CBR模型结合，建立煤矿巷道支护方案智能设计系统。将该系统用于不连沟煤矿掘进F6226工作面辅运巷支护方案设计，通过试验验证了系统生成方案下巷道两帮变形量和顶板最大位移均小于人工设计方案，巷道顶板及两帮完整性较好，围岩承载能力增强，支护效果明显。Abstract: Currently, the design of coal mine roadway support schemes is still mainly based on manual design, engineering analogy, and FLAC model simulation, which has problems such as strong subjectivity, low universality, and insufficient utilization of coal mine support big data. The design method based on expert systems has cumbersome rule setting procedures, large engineering quantities, and low intelligence. Case based reasoning (CBR) and deep learning techniques are introduced into the field of roadway support scheme design. Based on text big data such as coal mine support regulations, support standards, and coal mine roadway geological reports, an intelligent design method for coal mine roadway support scheme is proposed. The method obtains 346 sets of roadway support data from different coal mines, extracts structured data and divides it into input and output parameters, and optimizes the input and output parameters through constant attribute variable filtering and high correlation filtering methods. The method establishes a CBR model and imports the extracted structured data into the CBR model to form a case library of support scheme comparison and selection. The method calculates the similarity between the new roadway support scheme and the historical scheme, and outputs the three historical schemes with the highest similarity for comparison, achieving similar case comparison. BP neural network and long short term memory (LSTM) network are respectively used to establish automatic generation models for coal mine roadway support schemes. By comparing the prediction indicators, it is determined to use the combination of LSTM model and CBR model to establish an intelligent design system for coal mine roadway support scheme. The system is used for the design of auxiliary transportation roadway support scheme in the F6226 working face of Buliangou Coal Mine excavation. Through experiments, it is verified that the deformation of the two sides of the roadway and the maximum displacement of the roof under the system generated scheme are smaller than those under the manual design scheme. The integrity of the roadway roof and two sides is good, the bearing capacity of the surrounding rock is enhanced, and the support effect is significant.
-
图 1 煤矿巷道支护方案智能设计研究框架
Figure 1. Research framework for intelligent design of coal mine roadway support scheme
图 3 煤矿巷道支护方案自动生成模型预测结果
Figure 3. Prediction results of automatic generation model of coal mine roadway support scheme
图 4 煤矿巷道支护方案智能设计系统运行流程
Figure 4. Operation process of intelligent design system of coal mine roadway support scheme
图 5 煤矿巷道支护方案智能设计系统界面
Figure 5. Interface of intelligent design system of coal mine roadway support scheme
表 1 输入和输出参数优化结果
Table 1. Optimization results of input and output parameters
模型端口 参数类型 参数名称 输入端 开采 埋藏深度，开采方法，煤柱宽度，服务年限，层间距，围岩强度 顶板 直接顶厚度，基本顶厚度，抗压强度，泊松比，内摩擦角，直接顶初次垮落步距，直接顶厚度与采高比值 煤层 煤层厚度，煤层倾角，抗压强度，泊松比，内摩擦角 底板 直接底厚度，基本底厚度，抗压强度，泊松比，内摩擦角 巷道 断面形状，断面宽度，断面高度 地下水 正常涌水量 地应力 水平应力，垂直应力 输出端 支护方式 锚杆，锚索，网片，钢带，喷浆，钢棚 锚杆 锚杆类型，锚杆直径，锚杆长度，锚杆间距，锚杆排距，药卷类型，药卷数量，药卷直径，锚杆设计锚固力，锚杆预紧力，锚杆托盘类型，托盘规格 锚索 锚索类型，锚索直径，锚索长度，锚索间距，锚索排距，药卷类型，药卷数量，药卷直径，锚索设计锚固力，锚索预紧力，锚索托盘类型，托盘规格 网片 网片类型，铁丝直径，网孔大小，网片大小 钢带 钢带类型，钢带长度，钢带宽度，钢带厚度 喷浆 喷浆材料，喷浆厚度，喷浆浆体强度 钢棚 钢棚型号，钢棚间距 
下载: 导出CSV
表 2 输入参数权重赋值结果
Table 2. Weight of input parameters
输入参数 权重/% 输入参数 权重/% 埋藏深度 6.832 煤层抗压强度 4.899 开采方法 4.399 煤层泊松比 1.865 煤柱宽度 5.039 煤层内摩擦角 4.516 服务年限 3.502 直接底厚度 1.563 层间距 6.016 基本底厚度 1.397 围岩强度 3.724 底板抗压强度 2.070 直接顶厚度 4.269 底板泊松比 1.217 基本顶厚度 3.698 底板内摩擦角 2.289 顶板抗压强度 4.832 断面形状 3.310 顶板泊松比 2.267 断面宽度 3.942 顶板内摩擦角 4.309 断面高度 1.768 直接顶初次垮落步距 4.090 地下水情况 1.732 直接顶厚度与采高比值 4.965 水平应力 2.668 煤层厚度 4.082 垂直应力 2.312 煤层倾角 2.428
下载: 导出CSV
表 3 LSTM模型结构
Table 3. LSTM model structure
层名称 输出大小 层类型 Input （30，1，1） 序列输入 Lstm_1 （200，1，1） LSTM dropout_1 （200，1，1） Dropout Lstm_2 （200，1，1） LSTM dropout_2 （200，1，1） Dropout fc_1 （50，1，1） 全连接 fc_2 （10，1，1） 全连接 Regression output （10，1，1） 回归输出
下载: 导出CSV
表 4 2种模型评价指标对比
Table 4. Evaluation indexes of the two models
模型 R2 MAE/% RMSE/% 基于BP神经网络 0.359 6 26.065 3 5.761 2 基于LSTM 0.869 4 1.565 4 2.638 9
下载: 导出CSV
表 5 F6226工作面辅运巷支护方案对比
Table 5. Comparison of support scheme for auxiliary transportation roadway in F6226 working face
支护体 参数名称 参数值 人工设计方案 相似案例1 相似案例2 相似案例3 系统生成方案 锚杆 锚杆类型 左旋无纵筋螺纹
钢锚杆1左旋无纵筋螺纹
钢锚杆1左旋无纵筋螺纹
钢锚杆1左旋无纵筋螺纹
钢锚杆1左旋无纵筋螺纹
钢锚杆1锚杆直径/mm 18 18 18 18 18 锚杆长度/mm 2 400 2 400 2 400 2 400 2 400 锚杆间距/mm 1 000 1 000 1 000 850 1 000 锚杆排距/mm 1 000 1 100 1 100 900 1 100 药卷类型 CK2350，K2350 CK2350，K2350 CK2350，K2350 CK2350，K2350 CK2350，K2350 药卷数量 2 2 2 2 2 药卷直径/mm 23 23 23 23 23 锚杆设计锚固力/kN 110 128 128 110 128 锚杆预紧力/（N·m） 200 250 200 200 200 锚杆托盘类型 蝶形 蝶形 蝶形 蝶形 蝶形 锚杆托盘规格/
（mm×mm×mm）150×150×10 150×150×10 150×150×10 150×150×10 150×150×10 锚索 锚索类型 钢绞线锚索 钢绞线锚索 钢绞线锚索 钢绞线锚索 钢绞线锚索 锚索直径/mm 17.8 17.8 17.8 21.8 17.8 锚索长度/mm 8 000 6 300 6 300 8 000 6 300 锚索间距/mm 1 000 2 000 1 800 1 700 1 800 锚索排距/mm 2 000 2 200 3 300 1 800 1 800 药杆类型 CK2350，K2350 CK2350，K2350 CK2350，K2350 CK2350，K2350 CK2350，K2350 药卷数量 3 3 3 3 3 药卷直径/mm 23 23 23 23 23 锚索设计锚固力/kN 582 355 355 582 355 锚索预紧力/（N·m） 200 200 200 200 200 锚索托盘类型 蝶形 蝶形 蝶形 蝶形 蝶形 锚索托盘规格/
（mm×mm×mm）300×300×16 300×300×14 300×300×14 300×300×16 300×300×14 网片 网片类型 钢筋网 钢筋网 钢筋网 钢筋网 钢筋网 铁丝直径/mm 6.5 6.5 6.5 6.5 6.5 网孔大小/（mm×mm） 100×100 100×100 100×100 100×100 100×100 网片大小/（mm×mm） 5 500×1 200 5 500×1 200 5 500×1 200 5 500×1 200 5 500×1 200
下载: 导出CSV
-
[1] 查文华,樊昊,刘新权,等. 新型拉力分散型锚杆支护参数优选数值模拟研究[J]. 煤矿安全,2023,54(9):105-111.ZHA Wenhua,FAN Hao,LIU Xinquan,et al. Numerical simulation study on optimization of supporting parameters of a new type of tension dispersed bolt[J]. Safety in Coal Mines,2023,54(9):105-111. [2] 张夫净,王宏伟,王浩然,等. 煤矿巷道支护钢带锚孔智能识别与定位[J]. 工矿自动化,2022,48(10):76-81.ZHANG Fujing,WANG Hongwei,WANG Haoran,et al. Intelligent identification and positioning of steel belt anchor hole in coal mine roadway support[J]. Journal of Mine Automation,2022,48(10):76-81. [3] 赵晓明. 基于5G网络的庞庞塔煤矿智能矿山建设[J]. 江西煤炭科技,2022(1):201-203. doi: 10.3969/j.issn.1006-2572.2022.01.068ZHAO Xiaoming. Intelligent mine construction of Pangpangta Coal Mine based on 5G network[J]. Jiangxi Coal Science & Technology,2022(1):201-203. doi: 10.3969/j.issn.1006-2572.2022.01.068 [4] 史光亮,王瑞君,孔祥宇. 多网融合下的煤矿应急广播通信系统设计与应用[J]. 煤炭技术,2023,42(11):245-248.SHI Guangliang,WANG Ruijun,KONG Xiangyu. Design and application of coal mine emergency broadcast communication system under multi-network integration[J]. Coal Technology,2023,42(11):245-248. [5] 赵振宇,张开加,董宇. 鑫岩煤矿井下煤矸分选与充填开采一体化系统设计[J]. 煤炭工程,2022,54(1):11-17.ZHAO Zhenyu,ZHANG Kaijia,DONG Yu. Integrated system design of coal and gangue separation and backfill mining in Xinyan Coal Mine[J]. Coal Engineering,2022,54(1):11-17. [6] 程德强,寇旗旗,江鹤,等. 全矿井智能视频分析关键技术综述[J]. 工矿自动化,2023,49(11):1-21.CHENG Deqiang,KOU Qiqi,JIANG He,et al. Overview of key technologies for mine-wide intelligent video analysis[J]. Journal of Mine Automation,2023,49(11):1-21. [7] XIA Tongqiang,LI Diao,LI Xiaolin,et al. A novel in-depth intelligent evaluation approach for the gas drainage effect from point monitoring to surface to volume[J]. Applied Energy,2024,353. DOI: 10.1016/J.APENERGY.2023.122147. [8] 张力文,胡海峰. 基于Arduino的新型智能矿用搜救机器人设计[J]. 仪表技术,2022(3):19-22.ZHANG Liwen,HU Haifeng. A new intelligent mining search and rescue robot based on Arduino[J]. Instrumentation Technology,2022(3):19-22. [9] WANG Yan,HU Hejuan,SUN Xiaoyan,et al. Unified operation optimization model of integrated coal mine energy systems and its solutions based on autonomous intelligence[J]. Applied Energy,2022,328. DOI: 10.1016/J.APENERGY.2022.120106. [10] 张大明,孙贵洋,李刚. 双重采动影响下复采煤层巷道稳定性分析与维护方案设计[J]. 工程地质学报,2021,29(4):1028-1036.ZHANG Daming,SUN Guiyang,LI Gang. Support design of the stoping roadway in the re-mined coal seam under influence of dual mining[J]. Journal of Engineering Geology,2021,29(4):1028-1036. [11] WANG Yajun,XU Tao,CHENG Tong. Deformation analysis of deep coal mining roadway and optimization design of bolt support scheme[J]. Fresenius Environmental Bulletin,2024,30(11):11894-11901. [12] 吕彪,赵象卓,张铁松,等. 大变形巷道锚固系统让压装置设计与支护方案优化[J]. 采矿与岩层控制工程学报,2023,5(4):25-34.LYU Biao,ZHAO Xiangzhuo,ZHANG Tiesong,et al. Design of yielding device and optimization of support scheme of anchoring system in large deformation roadway[J]. Journal of Mining and Strata Control Engineering,2023,5(4):25-34. [13] 杨仁树,马鑫民,李清,等. 煤矿巷道支护方案专家系统及应用研究[J]. 采矿与安全工程学报,2013,30(5):648-652.YANG Renshu,MA Xinmin,LI Qing,et al. Research on expert system of roadway supporting schemes for coal mine and its application[J]. Journal of Mining & Safety Engineering,2013,30(5):648-652. [14] 赵军,高树国,何瑞东,等. 变压器油中乙炔门控循环单元网络多步预测超参数优化方法[J]. 高压电器,2024,60(7):163-172,190.ZHAO Jun,GAO Shuguo,HE Ruidong,et al. Hyper-parameters optimization method for multi-step prediction of acetylene in power transformer oil by gated cyclic unit network[J]. High Voltage Apparatus,2024,60(7):163-172,190. [15] 王佳明. 煤矿巷道支护方案自动生成及智能比选研究[D]. 徐州:中国矿业大学,2023.WANG Jiaming. Research on automatic generation and intelligent comparison of coal mine roadway support scheme[D]. Xuzhou:China University of Mining and Technology,2023. [16] 杜伟健,陈云霁,支天,等. QingLong:一种基于常变量异步拷贝的神经网络编程模型[J]. 计算机学报,2020,43(4):587-599. doi: 10.11897/SP.J.1016.2020.00587DU Weijian,CHEN Yunji,ZHI Tian,et al. QingLong:a neural network programming model based on asynchronous copy of constant and variable[J]. Chinese Journal of Computers,2020,43(4):587-599. doi: 10.11897/SP.J.1016.2020.00587 [17] 郭亮,郭子雪,贾洪涛,等. 基于皮尔逊相关系数与SVM的居民窃电识别[J]. 河北大学学报(自然科学版),2023,43(4):357-363. doi: 10.3969/j.issn.1000-1565.2023.04.003GUO Liang,GUO Zixue,JIA Hongtao,et al. Residents electric larceny detection based on Pearson correlation coefficient and SVM[J]. Journal of Hebei University(Natural Science Edition),2023,43(4):357-363. doi: 10.3969/j.issn.1000-1565.2023.04.003 [18] 丁国辉,刘宇琪,王言开,等. 基于翻转网络的低相关性序列数据预测研究[J]. 计算机工程,2024,50(2):78-90.DING Guohui,LIU Yuqi,WANG Yankai,et al. Research on low-correlation sequence data prediction based on flip network[J]. Computer Engineering,2024,50(2):78-90. [19] 李全贵,李建波,胡千庭,等. 基于案例推理的煤与瓦斯突出预警模型研究[J]. 矿业安全与环保,2023,50(5):24-29,36.LI Quangui,LI Jianbo,HU Qianting,et al. Research on early warning model of coal and gas outburst based on case-based reasoning[J]. Mining Safety & Environmental Protection,2023,50(5):24-29,36. [20] 杨艺,赵惊涛,付国强. 基于PSO−LSTM模型的地热储层温度预测研究[J]. 矿业科学学报,2024,9(4):538-548.YANG Yi,ZHAO Jingtao,FU Guoqiang. Predicting geothermal reservoir temperature based on the PSO-LSTM model[J]. Journal of Mining Science and Technology,2024,9(4):538-548. [21] 周江平,周媛媛,周学军,等. 基于BP神经网络的测量设备无关协议参数预测[J]. 电子科技大学学报,2024,53(4):611-616.ZHOU Jiangping,ZHOU Yuanyuan,ZHOU Xuejun,et al. Measurement device independent protocol parameter prediction based on BP neural network[J]. Journal of University of Electronic Science and Technology of China,2024,53(4):611-616. [22] 田辽西,覃华清. 基于多变量LSTM神经网络的地下水位预测方法研究[J]. 干旱区资源与环境,2024,38(9):138-146.TIAN Liaoxi,QIN Huaqing. Multivariable LSTM model-based groundwater level prediction[J]. Journal of Arid Land Resources and Environment,2024,38(9):138-146. -
点击查看大图
图(5) / 表(5)
计量
- 文章访问数: 91
- HTML全文浏览量: 28
- PDF下载量: 6
- 被引次数: 0
