HUANG Wen-jen,HSU Chang-li.Displacement Predicted for the Backpropagation Neural Network Applying in Shonzongliao Landslide Area[J].Research of Soil and Water Conservation,2009,16(06):271-275.
应用倒传递类神经网络模拟预测山棕寮地滑地位移之研究
- Title:
- Displacement Predicted for the Backpropagation Neural Network Applying in Shonzongliao Landslide Area
- 关键词:
- 地滑; 倒传递类神经网络; Levenberg-Marquardt算法; 监测管理值
- Keywords:
- landslide; backpropagation neural network; Levenberg-Marquardt algorithm; monitoring management value
- 分类号:
- P642.22
- 摘要:
- 地滑为陡坡地最具破坏之灾害形态之一，藉由实施地滑地监测与评估，可以协助政府拟订适当的管理对策。研究以台东县池上乡山棕寮地滑地为例，利用倒传递类神经网络（BPNN）具有建构高复杂且非线性关系方式预测坡面位移变化。研究所发展之倒传递类神经网络分析系应用MATLAB 程序之Levenberg-Marquardt算法求解。网络输入系以直接关系位移之7个物理因子为变数，建构最佳之4层网络。根据监测资料共取12次台风暴雨事件，作为网络训练及模拟测试，并分别以6批次、8批次、10批次等3种情况网络训练对应模拟测试。研究结果显示所需监测台风暴雨事件至少8批次，即可达到13.1%预测位移误差。其误差精度可作为中危害度以上地滑地执行后续监测管理值与利用管理之参考。
- Abstract:
- Landslides has become one disaster type of the most serious destroy on the steep lands.The way to monitoring and assessment for landslide area can help government agencies to select suitable management and plan mitigation in unstable landslide areas. This research presents a case study of landslide monitoring and assessment at Shonzongliao Landslide area, Township, Taitung County, attempt to predict slope movements using backpropagation neural network (BPNN), as well as use powerful tools to model and investigate various complex and non-linear phenomena. The BPNN can performed calculation to use MATLAB program with the Levenberg-Marquardt algorithm. The data from the case study are used to train and test the developed model, to enable prediction of the magnitude ground movements with the seven input helpful of variables that have regard to direct physical significance. According to monitoring date picked 12 set event of typhoon or rainstorm. 3 situation of train versus simulation and test is introduced in the network architecture apart from 6, 8, 10 set-batch. The developed BPNN optimal model by 8 set-batch demonstrates that have good potential accurately for predicting error 13.1% to the slope movement. This promising result can offer the reference of building of monitoring and utilizing management value at the landslide areas.
参考文献/References:
[1] 林广荣.应用倒传递类神经网路模拟山棕寮地滑地滑移特性[D].台湾 屏东:屏东科技大学,2008:37-50.
[2] 罗华强.类神经网路－MATLAB的应用[M].台湾:高立图书有限公司.2005,5-1-108.MATLAB,Version 6.5.0,Math Works Inc.,Help Files;2002.
[3] Levenberg K A.Method for the solution of certain problem in least squares[J].Quart Appl. Math.,1994,2:166-168.
[4] Marquardt D.An algorithm for least-squares estimation of nonlinear parameters[J].SSAM J Appl Math ,1963,11:431-41.
[5] Ni S H,Lu P C,Juang C H.A fuzzy eural network approach to evaluation of slope failure potential[J].Journal of Microcomputers in Civil Engineering,1995,11:59-66.
[6] Juang C H,Chen C J.CPT-based liquefaction evaluation using Artificial Neural Networks[J].Journal of Computer-aided Civil and Infrastructure Engineering,1999,14:221-229.
[7] Juang C H,Chen C J,Tang W H,et al.CPTbased liquefaction analysis:Part I Deteminated. limit statefunction[J].Geotechnique,2000,50(5):583-592.
[8] Agrawal G,Frost J D,Chameau J L A.Data analysis and modeling using artificial neural network.XⅢ International Conference of Soil Mechanics and Foundation Engineering[M].New Delhi:Oxford and IBH Publishing,1994:1441-1444.
[9] Tsaparas I,Rahardjo H,Toll D G,et al.Control ling parameters for rainfall-induced landslides[J].Computers and Geotechnics,2002,29:1-27.
[10] Neaupane K M,Achet S H.Use back propagation neural network for landslide monitoring:a case study in the higher Himalaya[J].Journal of Engineering Geology,2004,74:213-216.
相似文献/References:
[1]许中立,李正义.边坡稳定逆算分析法之应用探讨[J].水土保持研究,1999,6(03):80.
Chung-LiHsu,Cheng-Yi Lee.The Application of Back Stability Analysis on Landslide Slope[J].Research of Soil and Water Conservation,1999,6(06):80.
[2]颜正平.天灾地变与防灾减灾——从台湾“9·21”大地震说起[J].水土保持研究,2001,8(01):2.
YAN Zhengping.Climatic Disasters and Earth Movements VS. Disaster Prevention and Minimization——Examining the Aftereffect of the “9.21” Quake in Taiwan[J].Research of Soil and Water Conservation,2001,8(06):2.
[3]徐弘明,许中立,戴欣怡.嘉义白杞村樟树坪地层滑动之探讨[J].水土保持研究,2009,16(06):259.
SHU Hung-ming,HSU Chang-li,DAI Shin-yi.Investigation of Changshuping Landslide on Paichi Village of Chiayi County[J].Research of Soil and Water Conservation,2009,16(06):259.
备注/Memo
收稿日期:2009-8-16;改回日期:。
基金项目:山棕寮观测1-4期
作者简介:黄文仁（1963- ），博士候选人，研究方向：崩塌地治理。E-mail：wjhaung@ms64.hinet.net
通讯作者:许中立（1963- ），副教授，研究方向：坡地工程技术。E-mail：clhsu@mail.npust.edu.tw