论文部分内容阅读
为了预测采矿过程中覆岩的移动,在正交实验设计优化组合的基础上,利用数值模拟软件FLAC3D对采宽、采厚、岩性及采深4个影响覆岩移动因素所构建的16种组合进行模拟。根据数值模拟结果,构建了基于BP神经网络预测方法,并借助BP神经网络对覆岩移动进行预测,并与数值模拟结果进行对比。研究结果表明,在正交实验设计的少量模拟结果的基础上,运用BP神经网络对覆岩移动的预测误差较小,具有较高的可信性。
In order to predict the movement of overlying strata during the mining process, based on the optimized combination of orthogonal experimental design, 16 numerical models of FLAC3D, including mining width, mining thickness, lithology and mining depth, Combination of simulation. Based on the numerical simulation results, a prediction method based on BP neural network is constructed, and BP neural network is used to predict the movement of overlying strata, and compared with the numerical simulation results. The results show that the prediction error of overlying strata movement using BP neural network is small and has high credibility based on the small number of simulation results of orthogonal experimental design.