论文部分内容阅读
针对矿区岩溶地表塌陷存在的非线性动力学特征,为更准确预测岩溶地质矿区地表塌陷区域分布,在分析研究某矿区岩溶地表塌陷机理及其影响因素基础上,确定矿区地表塌陷的影响因素,构建矿区岩溶地表塌陷BP神经网络非线性动力学预测模型。采集并分析某岩溶矿区大量岩溶地表塌陷历史数据,应用Matlab神经网络工具箱,采用构建的矿区岩溶地表塌陷BP神经网络预测模型,对上述矿区岩溶地表塌陷区域分布情况进行非线性预测。研究结果表明,采用训练的神经网络预测模型可以实现对矿区岩溶地表塌陷危险性的合理预测。
In order to more accurately predict the surface subsidence distribution in karst geology mining area, aiming at the nonlinear dynamic characteristics of the karst surface subsidence in the mining area, the paper analyzes the mechanism of karst surface subsidence in a mining area and its influencing factors and determines the influencing factors of surface subsidence in the mining area. Nonlinear Dynamic Prediction Model of BP Neural Network in Karst Ground Subsidence Area. The historical data of a large number of karst surface subsidence in a karst mining area were collected and analyzed. The prediction model of the karst subsidence area was established by using the Matlab neural network toolbox and the BP neural network prediction model of the karst surface subsidence. The results show that the trained neural network prediction model can reasonably predict the risk of karst collapse in the mining area.