基于神经网络的滑坡预测及其控制研究

说明：  本文针对滑坡预测预报这一复杂性问题提出一种基于前向反馈传播（BP）神经网络的预测模型，描述了滑坡系统输入输出之间的非线性关系。为克服 BP 网络后期收敛速度慢、易陷入局部极小点等缺点，以遗传算法（GA）和模拟退火算法（SA）相结合的方式即遗传-模拟退火（GSA）算法对网络权值进行优化。用该方法预测滑坡位移获得了较好的效果(In this paper, a prediction model based on forward feedback propagation (BP) neural network is proposed for the complex problem of landslide prediction. The nonlinear relationship between input and output of landslide system is described. In order to overcome the shortcomings of BP network, such as slow convergence speed and easy to fall into local minima, genetic algorithm (GA) and simulated annealing algorithm (SA) are combined to optimize the network weight. The method can be used to predict the displacement of landslides)

基于神经网络的滑坡预测及其控制研究_陈煌琼.caj, 2549811 , 2020-02-01