开采沉陷反分析的神经网络方法研究

建立了沉陷反分析的神经网络模型，并用基于正交试验获得的训练样本对网 络进行学习，以此训练好的神经网络模型来描述岩体力学参数与开采沉陷之间的关系，利用反演结果，建立拉格朗日快速计算法(FLAC)模型，对地表沉陷进行预测，其预测结果是令人满意的。

Studies of an Artificial Neural Network Method for Inversing Mechanical Parameters of Rock Mass from Measured Mining-Induced Surface Subsidence

An ANN model for inversing mechamical parameters of rock mass from measured surface subsidence induced by underground mining has been established.The network was trained with input-output data pairs obtained from FLAC simulation based on the orthogonal tests.The trained network provided the relation between mechanical parameters of the rock mass and the surface subsidence induced by underground mining and was used to inverse the mechanical parameters of the rock mass.The inversion results were in turn used as input parameters of a FLAC model predicting the mining-induced surface subsidence.The prediction was in good agreement with the measured subsidence.