岩层移动角选取的神经网络方法研究

岩层移动角是进行各类保护煤柱设计时的关键性参数 ,涉及地表建 (构 )筑物的安全。在综合分析影响岩层移动角因素的基础上 ,采用人工神经网络方法建立岩层移动角选取的模型。该模型采用改进的BP算法 ,运用我国典型的地表移动观测站资料作为学习训练样本和测试样本 ,对模型的计算结果与实测值进行了对比分析。分析结果表明 :用人工神经网络方法求算岩层移动角考虑的因素更为全面 ,结果更接近于实际。笔者为岩层移动角的理论计算探索出了一种新的方法。

Study on Artificial Neural Network Method for Calculation of Displacement Angle of Strata

The displacement angles of strata are the key parameters of designing protective coal pillars. It can probably affect the safety of surface structures. On the basis of analyzing the main geologic and mining factors, the model for calculating the displacement angles of strata is established by applying the theory of artificial neural network (ANN). A large amount of data from observation stations was used as learning and training samples to train and test the artificial neural network model. The results of the ANN model and the observed values are compared and analyzed showing it is more precise by ANN technology.