论文部分内容阅读
滑坡变形预测对于指导灾害的预防工作、保护人民的生命和财产安全具有重大实用价值。从系统论观点出发,结合岩土体流变理论和时序分析原理,在深入研究影响滑坡变形的主控环境变量基础上,将位移时序分解为趋势项和偏离项。采用灰色系统模型提取位移时序趋势项,结合遗传算法和人工神经网络建立起进化神经网络模型,逼近主控环境变量与位移偏离项之间的非线性关系。根据蠕变阶段和变形对环境变量响应情况,实时调整模型,建立起滑坡变形预测的动态灰色-进化神经网络(GM-ENN)模型。将此预测思路和方法应用于三峡库区某滑坡变形预测研究中,证实了模型的有效性和实用性,显示了动态预测的重要性。
Prediction of landslide deformation has great practical value in guiding disaster prevention and protecting people’s life and property safety. Based on the rheological theory of rock and soil and the principle of time series analysis, based on the systematic theory, the displacement sequence is decomposed into the trend item and the deviation item based on the further study of the main environmental variables that affect the landslide deformation. The gray system model is used to extract the trend of displacement sequence, and the genetic algorithm and artificial neural network are used to establish the evolutionary neural network model to approximate the nonlinear relationship between the main control environment variables and displacement deviations. According to the response of creep stage and deformation to environment variables, the model is adjusted in real time and a dynamic gray-evolutionary neural network (GM-ENN) model of landslide deformation prediction is established. Applying this prediction method and method to the landslide deformation prediction in the Three Gorges Reservoir Area, the validity and practicability of the model are verified, and the importance of dynamic prediction is demonstrated.