论文部分内容阅读
提出了利用人工神经元网络预测岩石工程数值分析中所需的岩体力学参数的方法,其优点是神经元网络可以把岩体较多的非定量的地质描述,经过换算后作为初始参数参与运算.通过对岩体抗压强度和弹性模量的预测验证表明,预测结果与实测结果吻合较一致.
The method of using artificial neural network to predict the mechanical parameters of rock mass required for numerical analysis of rock engineering is proposed. The advantage of this method is that the neural network can take more non-quantitative geological description of the rock mass and convert it into an initial parameter . The prediction of compressive strength and elastic modulus of rock mass shows that the predicted results are in good agreement with the measured ones.