论文部分内容阅读
以预测煤矿开采而引起的地表高程的损失为目的,通过灰色系统理论的建模、关联度分析和残差辨识,建立基于贫信息的传统GM(1,1)模型、GM(1,1)残差模型、时序残差GM(1,1)模型,又建立基于原始数据具有绝对误差的灰色CompertzⅠ和灰色LogisticⅠ模型与具有相对误差的灰色CompertzⅡ和灰色LogisticⅡ模型,并将其应用到金竹山矿业公司土珠煤矿的地表沉降量的实际预测分析中,对该矿2007年度1—10月的地表高程损失量进行灰色生成后,建立了7种灰色预测模型。根据其预测值的精度检验结果对比分析表明,所建立的7种模型均为一级(好)模型,且灰色CompertzIⅡ和灰色LogisticIⅡ模型远优于传统GM(1,1)模型,预测精度高,可靠性强,对煤矿开采的复垦规划有重要指导作用。
With the purpose of forecasting the loss of surface elevation caused by coal mining, the traditional GM (1,1) model, GM (1,1) model based on poor information is established through the modeling of gray system theory, correlation analysis and residual identification. Residual model and time series residual GM (1, 1) model, a gray CompertzⅠand gray LogisticⅠ model with relative error and a Gray CompertzⅡand Gray LogisticⅡ model with relative error were established and applied to Jinzhushan Mining In the actual prediction and analysis of the surface subsidence of Tuzhuang Mine Company, seven kinds of gray forecasting models were established after gray generation of surface elevation loss from January to October in 2007. According to the comparison of the accuracy test results of the predicted values, it is found that the seven models are all first-order (good) models, and the gray CompertzIⅡ and gray LogisticIⅡ models are far superior to the traditional GM (1,1) models with high prediction accuracy, High reliability, reclamation plan for coal mining has an important guiding role.