基于灰色时滞OBGM-BP神经网络模型的滑坡变形预测  

Prediction of Landslide Deformation Based on Grey Time-delay OBGM-BP Neural Network Model

作　　者：曾欣 刘军[1,2] 柳福祥[1,2] 刘红美[1,2] ZENG Xin;LIU Jun;LIU Fu-xiang;LIU Hong-mei(School of Science,China Three Gorges University,Yichang 443002,China;Three Gorges Mathematical Research Center,China Three Gorges University,Yichang 443002,China)

机构地区：[1]三峡大学理学院,湖北宜昌443002 [2]三峡大学三峡数学研究中心,湖北宜昌443002

出　　处：《数学的实践与认识》2022年第5期112-122,共11页Mathematics in Practice and Theory

基　　金：国家自然科学基金(11771172);三峡大学高层次人才科研启动基金(8000303)。

摘　　要：旨在研究大气降雨因素影响下的滑坡变形预测.文章首先使用时滞灰关联分析提取滑坡位移相对降雨量的滞后期特征;然后将该时滞因子引入多变量OBGM(1,N)模型,构建带时滞因子的一种新OBGM模型,以模拟滑坡位移序列趋势特征;以BP神经网络模型拟合具有较强随机性的滑坡位移偏离量;最终建立带时滞因子的灰色OBGM-BP神经网络组合模型来预测滑坡位移.应用模型对长江三峡库区新铺滑坡作实际模拟和预测,结果显示本文模型具有较强的趋势跟踪性能和有效性,对制定滑坡灾害防治策略和措施具有一定实际参考意义和辅助决策作用.This paper aims to study the prediction of landslide deformation under the influence of atmospheric rainfall.Firstly,the lag characteristics of landslide displacement relative to rainfall are extracted by time-delay grey correlation model.Then,the time-delay factor is introduced into the multivariable OBGM(1,N) model,and a new OBGM model with time-delay factor is constructed to simulate the trend characteristics of landslide displacement sequence.The landslide displacement deviation with strong randomness is fitted by BP neural network model.Finally,the grey OBGM-BP neural network combined model with time-delay factor is established to predict landslide displacement.The model in this paper is applied to simulate and predict the Xinpu landslide in the Three Gorges Reservoir area of the Yangtze River.The results show that the model in this paper has strong trend tracking performance and effectiveness.It has certain practical reference significance and auxiliary decision-making effect for the formulation of landslide disaster prevention strategies and measures.

关 键 词：时滞灰关联分析 多变量时滞OBGM(1 N)模型 BP神经网络 滑坡预测 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] P642.22[自动化与计算机技术—控制科学与工程]