液压支架时空区域支护质量动态评价

贾思锋; 付翔; 王然风; 王宏伟; 王朋飞

doi:10.13272/j.issn.1671-251x.17992

液压支架时空区域支护质量动态评价

doi: 10.13272/j.issn.1671-251x.17992

贾思锋^{1, 2,},
付翔^{1, 2, 3},
王然风^{1, 2},
王宏伟^{2, 3, 4},
王朋飞¹

1.
太原理工大学矿业工程学院, 山西太原　030024
2.
太原理工大学山西省煤矿智能装备工程研究中心, 山西太原　030024
3.
山西焦煤集团有限责任公司博士后工作站, 山西太原　030024
4.
太原理工大学机械与运载工程学院, 山西太原　030024

基金项目: 国家自然科学基金项目(52274157，52274092)；国家重点研发计划项目(2020YFB1314004)；内蒙古自治区重点专项项目(2022EEDSKJXM010)；山西省揭榜招标项目(20201101005)。

详细信息

作者简介:
贾思锋( 1998—) ，男，山西朔州人，硕士研究生，研究方向为煤矿自动化与控制工程，E-mail:786938065@qq.com

中图分类号: TD355
计量
- 文章访问数: 191
- HTML全文浏览量: 56
- PDF下载量: 29
- 被引次数: 0
出版历程
- 收稿日期: 2022-08-02
- 修回日期: 2022-09-30
- 网络出版日期: 2022-10-25

Dynamic evaluation of support quality of hydraulic support in space-time region

JIA Sifeng^{1, 2
,},
FU Xiang^{1, 2, 3},
WANG Ranfeng^{1, 2},
WANG Hongwei^{2, 3, 4},
WANG Pengfei¹

1.
College of Mining Engineering, Taiyuan University of Technology, Taiyuan 030024, China
2.
Center of Shanxi Engineering Research for Coal Mine Intelligent Equipment, Taiyuan University of Technology, Taiyuan 030024, China
3.
Postdoctoral Workstation, Shanxi Coking Coal Group Co., Ltd., Taiyuan 030024, China
4.
College of Mechanical and Vehicle Engineering, Taiyuan University of Technology, Taiyuan 030024, China

摘要

摘要: 液压支架支护过程是一个时间、空间上的动态变化过程，目前液压支架支护质量评价大多关注支架静态特征，对支架立柱压力动态变化研究较少。针对上述问题，采用深度学习方法构建了一种基于改进型LeNet−5网络的液压支架时空区域支护质量动态评价模型。首先，将工作面液压支架立柱压力数据进行预处理（缺失值填充、异常值处理、筛选、排序等），得到较为完整的液压支架压力数据。其次，将预处理后的液压支架立柱压力数据按照时间和空间排列，并提取反映智采工作面液压支架支护情况的初撑力、循环末阻力、时间加权阻力、阻力空间分布情况等重要特征量，将压力时间序列和空间序列组合为时间−空间二维总时空压力矩阵。再次，根据工作面支护要求，将时空区域支护质量划分为支护质量初步恶化、支护质量持续恶化、支护质量深度恶化、支护质量保持一般、支护质量初步优化、支护质量持续优化、支护质量保持良好7类，在总时空压力矩阵上使用滑动窗口按照一定间隔截取给定大小的子矩阵，将子矩阵与7类时空区域支护质量一一对应，形成样本和标签。最后，将样本和标签输入改进型LeNet−5网络进行训练，构建液压支架时空区域支护质量评价模型，实时评价该区域支架支护情况。实验结果表明：基于改进型LeNet−5网络的液压支架时空区域支护质量评价模型可用于工作面区域内支护质量动态效果辨识，为现场操作人员有针对性地调整液压支架支护状态提供依据，分类准确率为85.25%，比基于LeNet−5网络的模型提高了12%。同时，改进型LeNet−5网络在训练过程中能较快地收敛到最优解，加快了网络训练速度，验证了改进型LeNet−5网络用于智采工作面液压支架时空区域支护质量评价的优势。
- 智采工作面 /
- 液压支架 /
- 立柱压力 /
- 支护质量评价 /
- 时空区域 /
- 深度学习 /
- 卷积神经网络
Abstract: The support process of hydraulic support is a dynamic change process in time and space regions. At present, the evaluation of support quality of hydraulic support mostly focuses on the static characteristics of support. There is little research on the dynamic change of support column pressure. In order to solve the above problems, a dynamic evaluation model of support quality of hydraulic support in the space-time region based on improved LeNet-5 network is established by using the deep learning method. Firstly, the column pressure data of hydraulic support in working face is preprocessed (missing value filling, abnormal value processing, screening, sorting, etc.) to obtain more complete pressure data hydraulic support. Secondly, the preprocessed column pressure data of the hydraulic support is arranged according to time and space. The important characteristics are extracted such as initial setting force, circulating end-resistance, time-weighted resistance, and spatial distribution condition of resistance, which reflect the support condition of the hydraulic support in intelligent mining working face. The pressure time-sequence and the pressure space-sequence are combined into the total space-time pressure matrix in 2D space-time region. Thirdly, according to the support requirements of the working face, the support quality of the space-time region into seven types, namely, support quality preliminary deterioration, support quality continuous deterioration, support quality deep deterioration, support quality general maintenance, support quality preliminary optimization, support quality continuous optimization and support quality good maintenance. On the total space-time pressure matrix, the sliding window is used to intercept the sub-matrix with the given size at a certain interval. The sub-matrix is one-to-one corresponding to the seven support quality types in space-time regions to form samples and labels. Finally, the samples and the labels are input into the improved LeNet-5 network for training. The dynamic evaluation model of support quality of hydraulic support in space-time region is constructed, which evalues the support condition of hydraulic support in the region in real-time. The experimental results show that the model based on improved LeNet-5 network can be used to identify the dynamic effect of support quality in the working face, and provide the basis for the field operators to adjust the support state of the hydraulic support pertinently. The classification accuracy is 85.25%, which is 12% higher than that of the model based on LeNet-5 network. At the same time, the improved LeNet-5 network can converge to the optimal solution quickly in the training process, which accelerates the training speed of the network. The result verifies the advantages of the improved LeNet-5 network in evaluation of the support quality of hydraulic support in space-time region of intelligent working face.
- intelligent working face /
- hydraulic support /
- column pressure /
- support quality evaluation /
- space-time region /
- deep learning /
- convolutional neural network

HTML全文

图 1 60号支架时间维度压力曲线

Figure 1. Curve of time dimension pressure of No.60 support

下载: 全尺寸图片幻灯片

图 2 单架支架工作循环压力曲线

Figure 2. Pressure curve in single support working cycle

下载: 全尺寸图片幻灯片

图 3 工作面整体支撑力分布

Figure 3. Overall support force distribution of working face

下载: 全尺寸图片幻灯片

图 4 智采工作面液压支架整体支护压力时空热力图

Figure 4. Space-time thermal diagram of overall support pressure of hydraulic support in intelligent working face

下载: 全尺寸图片幻灯片

图 5 液压支架时空区域支护质量动态评价建模流程

Figure 5. Dynamic evaluation modeling process of support quality of hydraulic support in space-time region

下载: 全尺寸图片幻灯片

图 6 LeNet−5网络结构

Figure 6. LeNet-5 network structure

下载: 全尺寸图片幻灯片

图 7 样本集中各支护效果类别样本个数

Figure 7. Sample number of support effect categories in the sample set

下载: 全尺寸图片幻灯片

图 8 改进型LeNet−5网络结构

Figure 8. Improved LeNet-5 network structure

下载: 全尺寸图片幻灯片

图 9 LeNet−5网络训练效果

Figure 9. LeNet-5 network training effect

下载: 全尺寸图片幻灯片

图 10 改进型LeNet−5网络训练效果

Figure 10. Improved LeNet-5 network training effect

下载: 全尺寸图片幻灯片

参考文献(19)

[1]	王国法,庞义辉,任怀伟. 煤矿智能化开采模式与技术路径[J]. 采矿与岩层控制工程学报,2020,2(1):5-19. WANG Guofa,PANG Yihui,REN Huaiwei. Intelligent coal mining pattern and technological path[J]. Journal of Mining and Strata Control Engineering,2020,2(1):5-19.
[2]	张良,李首滨,黄曾华,等. 煤矿综采工作面无人化开采的内涵与实现[J]. 煤炭科学技术,2014,42(9):26-29,51. ZHANG Liang,LI Shoubin,HUANG Zenghua,et al. Definition and realization of unmanned mining in fully-mechanized coal mining face[J]. Coal Science and Technology,2014,42(9):26-29,51.
[3]	葛世荣. 智能化采煤装备的关键技术[J]. 煤炭科学技术,2014,42(9):7-11. doi: 10.13199/j.cnki.cst.2014.09.002 GE Shirong. Key technology of intelligent coal mining equipment[J]. Coal Science and Technology,2014,42(9):7-11. doi: 10.13199/j.cnki.cst.2014.09.002
[4]	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.
[5]	谢生荣,潘浩,陈冬冬,等. 多煤层开采层间等效基本顶结构及其活动规律[J]. 中国矿业大学学报,2017,46(6):1218-1225. doi: 10.13247/j.cnki.jcumt.000748 XIE Shengrong,PAN Hao,CHEN Dongdong,et al. The structure and activity laws of interlayer equivalent basic roof in multi-seam mining[J]. Journal of China University of Mining & Technology,2017,46(6):1218-1225. doi: 10.13247/j.cnki.jcumt.000748
[6]	郝海金,吴健,张勇,等. 大采高开采上位岩层平衡结构及其对采场矿压显现的影响[J]. 煤炭学报,2004,29(2):137-141. doi: 10.3321/j.issn:0253-9993.2004.02.003 HAO Haijin,WU Jian,ZHANG Yong,et al. The balance structure of main roof and its action to immediate roof in large cutting height workface[J]. Journal of China Coal Society,2004,29(2):137-141. doi: 10.3321/j.issn:0253-9993.2004.02.003
[7]	王国法. 综采自动化智能化无人化成套技术与装备发展方向[J]. 煤炭科学技术,2014,42(9):30-34,39. WANG Guofa. Development orientation of complete fully-mechanized automation,intelligent and unmanned mining technology and equipment[J]. Coal Science and Technology,2014,42(9):30-34,39.
[8]	QIAO Hongbing, XU Hailong, PANG Aoshuang, et al. A research on mine pressure monitoring data analysis and forecast expert system of fully mechanized coal face[C]. Proceedings of IEEE 19th International Conference on Industrial Engineering and Engineering Management, Changsha, 2012: 1452-1455.
[9]	侯刚. 矿用液压支架支护质量综合监测保障系统设计与实现[J]. 煤矿开采,2016,21(5):24-28. HOU Gang. Integrated monitoring safeguard system design and implementation of mine hydraulic support supporting quality[J]. Coal Mining Technology,2016,21(5):24-28.
[10]	赵吉玉. 基于支架工作阻力的工作面矿压显现规律自动分析技术研究[D]. 青岛: 山东科技大学, 2017. ZHAO Jiyu. Research on automatic analysis technology of strata pressure behavior based on working resistance of supports[D]. Qingdao: Shandong University of Science and Technology, 2017.
[11]	PENG S S,CHENG Jingyi,DU Feng,et al. Underground ground control monitoring and interpretation,and numerical modeling,and shield capacity design[J]. International Journal of Mining Science and Technology,2019,29(1):79-85. doi: 10.1016/j.ijmst.2018.11.026
[12]	LIU Chuang,LI Huamin,JIANG Dongjie. Numerical simulation study on the relationship between mining heights and shield resistance in longwall panel[J]. International Journal of Mining Science and Technology,2017,27(2):293-297. doi: 10.1016/j.ijmst.2017.01.017
[13]	庞义辉. 液压支架支护状态感知与数据处理技术[J]. 工矿自动化,2021,47(11):66-73. doi: 10.13272/j.issn.1671-251x.2021040061 PANG Yihui. Support state perception and data processing technology of hydraulic support[J]. Industry and Mine Automation,2021,47(11):66-73. doi: 10.13272/j.issn.1671-251x.2021040061
[14]	王国法,庞义辉. 液压支架与围岩耦合关系及应用[J]. 煤炭学报,2015,40(1):30-34. WANG Guofa,PANG Yihui. Relationship between hydraulic support and surrounding rock coupling and its application[J]. Journal of China Coal Society,2015,40(1):30-34.
[15]	王国法. 工作面支护与液压支架技术理论体系[J]. 煤炭学报,2014,39(8):1593-1601. WANG Guofa. Theory system of working face support system and hydraulic roof support technology[J]. Journal of China Coal Society,2014,39(8):1593-1601.
[16]	程敬义,万志军,PENG S S,等. 基于海量矿压监测数据的采场支架与顶板状态智能感知技术[J]. 煤炭学报,2020,45(6):2090-2103. CHENG Jingyi,WAN Zhijun,PENG S 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.
[17]	CHENG Jingyi,WAN Zhijun,PENG S S. et al. What can the changes in shield resistance tell us during the period of shearer's cutting and neighboring shields' advance?[J]. International Journal of Mining Science and Technology,2015,25(3):361-367. doi: 10.1016/j.ijmst.2015.03.006
[18]	张帆,栾佳星,崔东林,等. 基于SSD−LeNet的矿井移动目标检测与识别方法[J]. 矿业科学学报,2021,6(1):100-108. doi: 10.19606/j.cnki.jmst.2021.01.011 ZHANG Fan,LUAN Jiaxing,CUI Donglin,et al. SSD-LeNet based method of mine moving target detection and recognition[J]. Journal of Mining Science and Technology,2021,6(1):100-108. doi: 10.19606/j.cnki.jmst.2021.01.011
[19]	陈建平,王春雷,王雪冬. 基于CNN神经网络的煤层底板突水预测[J]. 中国地质灾害与防治学报,2021,32(1):50-57. doi: 10.16031/j.cnki.issn.1003-8035.2021.01.07 CHEN Jianping,WANG Chunlei,WANG Xuedong. Coal mine floor water inrush prediction based on CNN neural network[J]. The Chinese Journal of Geological Hazard and Control,2021,32(1):50-57. doi: 10.16031/j.cnki.issn.1003-8035.2021.01.07