[1]殷裁云,顾雷雨,韩健,等.基于三角网模型与云GIS技术的煤层单元体塌陷精确识别*[J].中国安全生产科学技术,2025,21(8):95-102.[doi:10.11731/j.issn.1673-193x.2025.08.012]
YIN Caiyun,GU Leiyu,HAN Jian,et al.Precise identification of coal seam unit collapse based on TIN model and cloud GIS technology[J].Journal of Safety Science and Technology,2025,21(8):95-102.[doi:10.11731/j.issn.1673-193x.2025.08.012]
点击复制
基于三角网模型与云GIS技术的煤层单元体塌陷精确识别*
YIN Caiyun,GU Leiyu,HAN Jian,et al.Precise identification of coal seam unit collapse based on TIN model and cloud GIS technology[J].Journal of Safety Science and Technology,2025,21(8):95-102.[doi:10.11731/j.issn.1673-193x.2025.08.012]
《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]
- 卷:
- 21
- 期数:
- 2025年8期
- 页码:
- 95-102
- 栏目:
- 职业安全卫生管理与技术
- 出版日期:
- 2025-08-30
文章信息/Info
- Title:
- Precise identification of coal seam unit collapse based on TIN model and cloud GIS technology
- 文章编号:
- 1673-193X(2025)-08-0095-08
- Keywords:
- cloud GIS technology; triangulated irregular network model; coal seam unit; collapse identification; backpropagation neural network
- 分类号:
- X936
- 文献标志码:
- A
- 摘要:
- 为解决煤层单元体塌陷过程中因非线性动力系统特性导致的识别精度低的问题，提出基于三角网模型与云GIS技术的煤层单元体塌陷精确识别方法。设计基于云GIS技术的煤层单元体塌陷识别监测平台，便于管理监测数据并展示识别结果；利用Delaunay三角剖分方法结合地质信息和空间数据，构建煤层单元体三角网模型，捕捉三角网模型中煤层单元体的变化特征数据；选定三角网模型中的关键特征数据，利用相空间重构技术捕捉煤层单元体塌陷区域的非线性等混沌特性，通过集成相空间重构-反向传播神经网络-自适应增强技术建立识别模型，对三角网模型中特征数据展开智能分析，实现煤层单元体塌陷的精确识别，并将其传输到云GIS平台以实现可视化展示。研究结果表明：所提方法在所有监测点均准确识别煤层单元体塌陷状态，Kappa系数普遍处于“很好”至“极好”区间，而SSA-LSTM预测模型多处误判，AHP-PF组合模型和深度学习模型也有误判且Kappa系数多落在“差”至“一般”范围，说明所提方法具有较高的建模精度和塌陷识别精度。研究结果可为煤层开采过程中单元体塌陷的精准监测与高效管理提供科学方法及技术参考，助力提升煤炭资源开采的安全性与稳定性。
- Abstract:
- In order to address the issue of low identification accuracy caused by nonlinear dynamic system characteristics during the collapse process of coal seam units,a precise identification method for coal seam unit collapse based on triangulated irregular network (TIN) model and cloud GIS technology was proposed.A monitoring platform for coal seam unit collapse identification is designed using cloud GIS technology to facilitate the management of monitoring data and visualization of identification results.By employing Delaunay triangulation combined with geological information and spatial data,a TIN model of coal seam units is constructed to capture characteristic change data.Key feature data from the TIN model are selected,and phase space reconstruction technology is utilized to extract nonlinear chaotic characteristics in collapse areas.An integrated model combining phase space reconstruction,backpropagation neural network,and adaptive boosting techniques is established to intelligently analyze feature data from the TIN model,achieving precise identification of coal seam unit collapse.This identification results is then transmitted to the cloud GIS platform for visualization.The results indicate that the proposed method accurately identifies collapse states of coal seam units across all monitoring points,with Kappa coefficient predominantly falling within the “very good” to “excellent” range.However,the SSA-LSTM prediction model exhibits multiple misjudgments,and both the AHP-PF hybrid model and deep learning model also exhibit misjudgments with Kappa coefficient largely distributed in the “poor” to “average” range.This conclusively indicates the superior modeling precision and collapse identification accuracy of the proposed approach.These findings provide scientific methodology and technical references for precise monitoring and efficient management of unit collapse during coal seam mining,thereby enhancing the safety and stability of coal resource mining.
参考文献/References:
［1］孙宇,刘盛,王诗俊,等.依据加权Delaunays三角网的林分空间结构分析与评价［J］.东北林业大学学报,2022,50(8):61-68.
SUN Yu,LIU Sheng,WANG Shijun,et al.Analysis and evaluation of forest spatial structure using weighted Delaunays triangle network ［J］.Journal of Northeast Forestry University,2022,50(8):61-68.
［2］成睿,李素敏,毛嘉骐,等.基于时序InSAR监测的VMD-SSA-LSTM矿区地表形变预测模型研究［J］.化工矿物与加工,2023,52(8):39-46.
CHENG Rui,LI Sumin,MAO Jiaqi,et al.Study on VMD-SSA-LSTM mine ground deformation prediction model based on InSAR monitoring ［J］.Industrial Minerals & Processing,2023,52(8):39-46.
［3］张静,崔健,马诗敏,等.基于层次分析法与频率比模型的采空塌陷危险性评价［J］.地质与勘探,2024,60(1):88-94.
ZHANG Jing,CUI Jian,MA Shimin,et al.Risk assessment of goaf collapse based on analytic hierarchy process and frequency ratio model ［J］.Geology and Exploration,2024,60(1):88-94.
［4］AN X,WU D,XIE X,et al.Slope collapse detection method based on deep learning technology［J］.CMES-Computer Modeling in Engineering & Sciences,2023,134(2):1091-1103.
［5］WU B,ZENG J,ZHU R,et al.A collapse risk assessment method for subway foundation pit based on cloud model and improved Dempster-Shafer evidence theory［J］.Scientific Reports,2024,14(1):2653.
［6］王章飞,方辉煌,桑树勋,等.两淮煤田低渗煤层孔隙结构三维可视化表征及其连通性［J］.科学技术与工程,2024,24(26):11195-11207.
WANG Zhangfei,FANG Huihuang,SANG Shuxun,et al.Three-dimensional visualization of pore structure of low permeability coal seam in lianghuai coal field and its connectivity［J］.Science Technology and Engineering,2024,24(26):11195-11207.
［7］黄湛煐,李郴娟.基于声发射主频分布的大理岩应力-应变全过程曲线特征研究［J］.公路,2023,68(2):284-287.
HUANG Zhanxi,LI Chenjuan.Research on the characteristics of the stress-strain curve of marble based on the frequency distribution of acoustic emission ［J］.Highway,2023,68(2):284-287.
［8］李泊立,王瑞丰,陈龙洋,等.冲击加载下材料应力应变曲线振荡现象的研究综述［J］.实验力学,2024,39(2):208-222.
LI Boli,WANG Ruifeng,CHEN Longyang,et al.A review on the oscillation phenomenon of stress strain curve of material under impact loading ［J］.Journal of Experimental Mechanics,2024,39(2):208-222.
［9］杨敬松,廖府,李智涛,等.一种基于Delaunay三角剖分的天然地震波初至实时拾取算法［J］.地球物理学进展,2024,39(5):1788-1799.
YANG Jingsong,LIAO Fu,LI Zhitao,et al.Real time picking algorithm for natural seismic wave first arrival based on Delaunay triangulation ［J］.Progress in Geophysics,2024,39(5):1788-1799.
［10］王经纬,宁建廷,许胜民,等.面向可变用户群体的可搜索属性基加密方案［J］.软件学报,2023,34(4):1907-1925.
WANG Jingwei,NING Jianting,XU Shengmin,et al.Searchable attribute-based encryption scheme for Dynamic user groups ［J］.Journal of Software,2023,34(4):1907-1925.
［11］宋建国,许永超.一种断层面约束下的Delaunay三角剖分与等值线生成算法［J］.中国石油大学学报(自然科学版),2023,47(6):35-42.
SONG Jianguo,XU Yongchao.An algorithm for Delaunay triangulation and contour generation under the constraints of fault surfaces ［J］.Journal of China University of Petroleum(Edition of Natural Science),2023,47(6):35-42.
［12］李建林,贺奇,王树威,等.相空间重构后矿井涌水量序列地质学含义及其应用研究［J］.河南理工大学学报(自然科学版),2024,43(5):43-52.
LI Jianlin,HE Qi,WANG Shuwei,et al.Study on the geological meaning and application of mine water inflow series after phase space reconstruction ［J］.Journal of Henan Polytechnic University（Natural Science）,2024,43(5):43-52.
［13］卞伟伟,邱旭阳,辛振芳,等.基于多特征的BP神经网络LSS目标识别方法［J］.计算机仿真,2021,38(4):338-342.
BIAN Weiwei,QIU Xuyang,XIN Zhenfang,et al.A BP neural network recognition method based on multi features for the LSS target ［J］.Computer Simulation,2021,38(4):338-342.
［14］陈发堂,王永航,张翰卿.多归一化因子的LDPC译码算法［J］.重庆邮电大学学报(自然科学版),2022,34(1):59-64.
CHEN Fatang,WANG Yonghang,ZHANG Hanqing.LDPC decoding algorithm with multiple normalization factors ［J］.Journal of Chongqing University of Posts and Telecommunications (Natural Science Edition),2022,34(1):59-64.
相似文献/References:
备注/Memo
- 备注/Memo:
-
收稿日期： 2025-03-25
* 基金项目： 国家重点研发计划项目(2023YFC3008900)；中国华能集团有限公司总部科技项目(HNKJ22-H44)
作者简介： 殷裁云，硕士，高级工程师，主要研究方向为矿山工程与灾害地质、透明智能地质保障系统等。
