基于总体最小二乘法改进GM(1,1)模型的矿区沉降预测

Mining Subsidence Prediction Based on Improved GM(1,1)Model by Total Least Squares Method

【目的】针对煤矿区地表沉降受各种因素影响难以精确预测的问题,本研究提出采用总体最小二乘法(TLS)融入GM(1,1)模型进行试验研究。【方法】基于某矿区2011—2017年的沉降监测数据,分别采用基于总体最小二乘法(TLS)与最小二乘法(LS)的GM(1,1)模型进行预测试验。【结果】试验结果表明,基于GM(1,1)预测模型,采用TLS方法对2018年矿区沉降预测的精度较LS方法提高了0.49 mm;对2019年矿区沉降预测的精度较LS方法提高了0.55 mm。【结论】本研究验证了采用TLS方法的GM(1,1)模型相较于LS方法的GM(1,1)模型在矿区地面沉降预测中具有更高的精度和更好的效果。

[Purposes]This study proposes the use of Total Least Squares(TLS)in combination with the GM(1,1)model to conduct experimental research on the difficult-to-predict surface subsidence in coal mining areas affected by various factors.[Methods]Specifically,this study is based on the subsidence monitoring data from a certain mining area between 2011 and 2017.The GM(1,1)model is used in con⁃junction with both the Total Least Squares(TLS)and the Ordinary Least Squares(LS)methods for predic⁃tive experiments.[Findings]The experimental results indicate that,based on the GM(1,1)prediction model,the use of the TLS method improves the accuracy of subsidence monitoring predictions in the min⁃ing area by 0.49 mm for the year 2018 and by 0.55 mm for the year 2019 compared to the LS method.[Conclusions]Therefore,this study confirms that the GM(1,1)model using the TLS method provides higher accuracy and better performance in predicting ground subsidence in mining areas compared to the GM(1,1)model using the LS method.