基于混沌神经网络的流域坝系稳定性分析  

Stability Analysis of Watershed Silt Dams Based on Chaos Optimization and Back-Propagation

作　　者：刘卉芳[1] 曹文洪[1] 王向东[1] 孙中峰[2] 

机构地区：[1]中国水利水电科学研究院,北京100048 [2]水利部水土保持植物开发管理中心,北京100038

出　　处：《水土保持通报》2011年第3期131-135,共5页Bulletin of Soil and Water Conservation

基　　金："973"国家重点基础研究发展计划"水土流失环境效应评价理论与指标体系"(2007CB407205);国家自然科学基金创新研究群体基金项目"流域水循环模拟与调控"(50721006);"十一五"国家科技支撑课题"沟壑整治工程优化配置与建造技术"(2006BAD09B02)

摘　　要：坝系相对稳定原理是淤地坝规划的理论基础。依据影响坝系稳定性的7个主要因素:坝控面积、坝数、总库容、可淤库容、坝前水深、防洪能力、淤地面积,以Matlab 7.0为平台,采用混沌神经网络(COBP)模型对马家沟流域13个坝系进行了稳定性分析。结果表明,13个坝系中有7个坝系处于不稳定状态,采用坝系稳定系数来校核COBP模型的计算结果,得出的结论一致,因此,可以判定采用神经网络方法得出的结果基本可信。此外,分析了7个坝系不稳定的原因,采用增加坝高和增加淤地坝数量的方法使7个不稳定坝系均达到稳定状态。通过对马家沟13个小流域淤地坝重新规划,形成的13个坝系全部处于稳定状态,可见COBP方法在确定流域坝系稳定方面具有实用的价值。The principle of relative stability of a dam system is the theoretical basis for planning silt-retention dams,therefore,it is of significance to study the relative stability of a dam system in planning silt-retention dams.This paper uses Matlab 7.0-based improved BP algorithm and chaos optimization and back-propagation（COBP） model to assess the stabilities of thirteen dams in Majiagou watershed according to seven major factors affecting the stability of a dam system,i.e.dam control area,dam number,total reservoir storage,silting-allowable volume,water depth,anti-flood capacity and silted area.Results show that seven dams out of the thirteen dams are unstable,which is confirmed by the stability coefficient analysis of each dam.The output of the COBP model is thus reliable.This paper further analyzes the reasons for the instabilities of seven dams and makes them stable by increasing dam height and number.All of the thirteen small-watershed dams in Majiagou watershed become stable after they are replanned.This demonstrates that the COBP method has practical values in assessing the stability of a dam system.

关 键 词：混沌神经网络 马家沟流域 坝系稳定性 

分 类 号：S157.31[农业科学—土壤学]