混凝土坝风险失效概率的SAGA-LSSVM分析方法  

SAGA-LSSVM Analysis Method for Risk Failure Probability of Concrete Dam

作　　者：姜彦作 苗君 董庆煊 陈仁宏 王翔 JIANG Yanzuo;MIAO Jun;DONG Qingxuan;CHEN Renhong;WANG Xiang(Power China Guiyang Engineering Corporation Limited,Guiyang 550081,China;Huaneng Lancang River Hydropower Inc,Kunming 650214,China)

机构地区：[1]中国电建集团贵阳勘测设计研究院有限公司,贵州省贵阳市550081 [2]华能澜沧江上游水电有限公司,云南省昆明市650214

出　　处：《水电与抽水蓄能》2023年第3期33-39,共7页Hydropower and Pumped Storage

基　　金：贵州省水利厅科技专题经费项目资助(KT201902)。

摘　　要：针对混凝土坝服役风险失效概率的分析方法,首先研究了自我调节遗传算法(Self-Adaptive Genetic Algorithm,简称SAGA)和支持向量机(Support Vector Machine,简称SVM)的建立原理,然后分析了混凝土坝风险失效概率最小二乘支持向量机(Least Squares Support Vector Machine,简称LSSVM)的构建方法,最后将结构计算和数值分析相结合,以有限元计算结果作为样本,利用自我调节遗传算法对最小二乘支持向量机的参数进行优化,将自我调节遗传算法与最小二乘支持向量机技术有机融合,从而建立混凝土坝风险失效概率的自我调节遗传优化最小二乘支持向量机分析方法。实例分析表明该方法能够高效准确地确定混凝土坝的风险失效概率,是有效可行的。该方法是混凝土坝风险失效概率计算的新方法,具有一定的工程实用价值。Aiming at the analysis method of risk failure probability of concrete dam,firstly,the establishment principle of selfregulating genetic algorithm(SAGA)and Support Vector Machine(SVM)is studied.construction method of least squares support vector machine(Least Squares Support Vector Machine,LSSVM)for the risk failure probability of concrete dam is analyzed,Finally combining structure calculation and numerical analysis,the calculation result of finite element as samples,The self-regulated genetic algorithm is used to optimize the parameters of the least squares support vector machine,and the self-regulated genetic algorithm is organically integrated with the least squares support vector machine technology,so as to establish the self-regulated genetic optimization least squares support vector machine analysis method for the risk failure probability of concrete dam.The example analysis shows that this method can determine the risk failure probability of concrete dam efficiently and accurately,and is effective and feasible.This method is a new method to calculate the risk failure probability of concrete dam and has certain practical value in engineering.

关 键 词：混凝土坝 风险失效概率 自我调节遗传算法 最小二乘支持向量机 

分 类 号：TV641.43[水利工程—水利水电工程]