Long-term deformation prediction of Tianhuangpin “3.29” landslide based on neural network with annealing simulation method

摘要

Landslide has already become one of the most dangerous geo-hazards in China,there are alot of economy loss and personnel casualty. Recently,the safety research on stability analysis or predict to thehazard taken place for landslides is more and more important. But,it is difficult to predict when the sliding willhappen accurately since the factors affected on landslide are complex. Thus,in these years,monitor scheme isadopted for many landslides,how to use the monitoring data to predict the landslide will occur is an importantproblem in geological field. In this paper,based on adopting neural network with simulated annealing method,the model of landslide deformation prediction in long-term was set up,which using simulated annealing methodto overcome the disadvantage of BP neural network,furthermore,by using dynamic forecasting technique toreduce the influence of the prophase displacement,it can get better forecast precision. Finally,the Tianhuangpin“3.29 landslide” deformation in long-term was predicted by using the model discussed in this paper,the resultis coincident to the real condition of the slope.