基于R/S分析方法的渐进式滑坡位移预测研究  

A study of displacement prediction of progressive landslide based on the R/S analysis method

作　　者：汤罗圣[1] 殷坤龙[1] 

机构地区：[1]中国地质大学(武汉)工程学院,湖北武汉430074

出　　处：《水文地质工程地质》2013年第3期93-97,共5页Hydrogeology & Engineering Geology

基　　金：国家自然科学基金项目(41002103;41101515);中央高校基本科研业务费专项资金优秀青年教师基金(CUGL100213);教育部长江三峡库区地质灾害研究中心开放基金(TGRC2010121)

摘　　要：渐进式滑坡由于其位移-时间曲线不规则而无法准确判断其趋势位移和随机位处变形阶段,导致很难预测其失稳破坏的时间。为此,提出了RS分析方法,将滑坡总位移分解为趋势位移和随机位移两部分,然后分别采用神经网络模型和多项式拟合对两种位移进行预测,最后将两部分预测位移加起来预测其总位移。以典型渐进式滑坡———八字门滑坡为例,对前述模型进行验证,并将其预测结果与GM(1,1)模型预测结果进行对比。研究结果表明本模型预测的结果误差小于2%,而GM(1,1)模型预测结果误差接近40%,说明该模型更适合预测渐进式滑坡的位移。It is difficult to predict the time of instability and failure for the progressive landslide whose displacement-time curve is irregular.Therefore,it is difficult to accurately judge its located deformation stage.For this reason,this paper divides the landslide total displacement into the trend displacement and random displacement based on the R/S analysis method,and apply the neural network model and a polynomial fitting to forecast trend displacement and random displacement respectively.The total prediction displacement is obtained by adding the two parts prediction displacement.Taking the typical gradual landslide-Bazimen landslide as an example,this paper validates the above prediction model and compare the results with those of GM(1,1) model.The results show that the prediction error of the above prediction model is less than 2%,while that of the GM(1,1) model is close to 40%.The model is more suitable for predicting the displacement of a gradual landslide.

关 键 词：R/S分析方法 渐进式滑坡 神经网络模型 多项式拟合 位移预测 八字门滑坡 

分 类 号：P642.22[天文地球—工程地质学]