结合改进Weibull时间函数的开采沉陷动态预测模型  

Dynamic prediction model of mining subsidence combined with improved Weibull time function

作　　者：张琰君 阎跃观[1] 龙思放 朱元昊 戴华阳[1] 孔嘉嫄 ZHANG Yan-jun;YAN Yue-guan;LONG Si-fang;ZHU Yuan-hao;DAI Hua-yang;KONG Jia-yuan(College of Geoscience and Surveying Engineering,China University of Mining and Technology-Beijing,Beijing 100083,China;College of Biosystems Engineering and Food Science,Zhejiang University,Hangzhou,Zhejiang 310058,China)

机构地区：[1]中国矿业大学(北京)地球科学与测绘工程学院,北京100083 [2]浙江大学生物系统工程与食品科学学院,浙江杭州310058

出　　处：《岩土力学》2024年第6期1824-1834,共11页Rock and Soil Mechanics

基　　金：国家自然科学基金重大项目(52394191);中国矿业大学(北京)博士研究生拔尖创新人才培育基金(No.BBJ2023018,No.BBJ2023023)。

摘　　要：煤炭开采引起的地表沉陷是一个多维动态变化过程,动态预测可以获取采空区上方任意位置、时刻的形变大小,对保护地面基础设施和人民生命安全具有重要意义。为实现地表沉陷的动态预测,针对Weibull时间函数模型结构复杂、参数较多等不足,基于开采沉陷相关理论,建立了仅含一个模型参数,且可以准确描述地表点下沉量、下沉速度、下沉加速度的改进Weibull时间函数模型。在此基础上,结合已有的地表沉陷盆地模型,建立了一种新的开采沉陷动态预测模型,详细阐述了模型参数的确定方法及其对沉陷盆地形态的影响,并结合某矿313工作面和3214工作面实测数据验证了模型的预测精度和适用性。结果表明:改进的Weibull时间函数模型最大均方根误差为52 mm,最大相对误差为2.1%,较改进前分别提高了60.3%和64.4%;开采沉陷动态预测模型预测的下沉曲线形态和实测下沉曲线形态一致,最大均方根误差为17 mm,最大相对误差为1.76%,表明该模型可以预测地表沉陷过程,具有较好的适用性和可靠性。该研究结果可为矿区地表沉陷动态预测提供参考。Coal mining-induced surface subsidence is a complex,multi-dimensional dynamic process.Dynamic prediction plays a crucial role in determining the magnitude of deformation at any location and time above the goaf,thereby safeguarding ground infrastructure and human life.To achieve dynamic prediction of surface subsidence,an improved Weibull time function model with a single model parameter was developed to address the limitations of the complex structure of the existing model,based on mining subsidence theory.This enhanced model accurately describes surface point subsidence,subsidence velocity,and subsidence acceleration.Additionally,a new dynamic prediction model for mining subsidence was established by integrating the improved Weibull time function model with the existing surface subsidence basin model.The method for determining model parameters and their impact on the shape of the subsidence basin was elaborated in detail.The model’s prediction accuracy and applicability were validated using measured data from working faces 313 and 3214 in a mine.The results indicate that the maximum root mean square error of the improved Weibull time function model is 52 mm,with a maximum relative error of 2.1%,representing a 60.3%and 64.4%improvement,respectively,over the previous version.The predicted subsidence curve shape of the mining subsidence dynamic prediction model aligns with the measured subsidence curve shape,with a maximum root mean square error of 17 mm and a maximum relative error of 1.76%,demonstrating the model’s ability to predict surface subsidence processes with high applicability and reliability.These research findings offer valuable insights for the dynamic prediction of surface subsidence in mining areas.

关 键 词：Weibull时间函数 开采沉陷 沉陷盆地 动态预测 

分 类 号：TD325[矿业工程—矿井建设]