联立SBFEM与PSO-LSSVM的混凝土重力坝综合弹性模量快速反演方法

Fast Inversion Method of Composite Elastic Modulus Concrete Gravity Dam Based on SBFEM and PSO-LSSVM

针对混凝土坝综合弹性模量常规反演法效率低及其有限元正分析受限于网格划分等问题,提出一种联立比例边界有限元法(SBFEM)和粒子群算法优化最小二乘支持向量机(PSO-LSSVM)的重力坝综合弹模快速反演方法.通过分析混凝土重力坝坝体综合弹模与水平位移的映射关系,在构建重力坝综合弹模反演方程基础上,建立基于MALTAB平台的重力坝结构比例边界有限元模型,并利用PSO-LSSVM算法对大坝结构正分析结果学习训练获取其反演参数.经实例考证表明,该方法无论其数值结果精度还是计算效率皆有所提升,同时克服了大坝结构常规反分析受制有限元奇异单元等先天缺陷影响,实现重力坝结构性能等效参数快速识别,为混凝土坝变形性能监测提供新的思路.

In view of the low efficiency of the conventional inversion method for the comprehensive elastic modulus of concrete dams and the limitation of the finite element forward analysis to the grid division,a finite element fast inversion method combined the scaled boundary finite element method(SBFEM)and optimization of least squares support vector machine by particle swarm optimization(PSO-LSSVM)are proposed.Analyzing the mapping relationship between the comprehensive elastic modulus of concrete gravity dam and the horizontal displacement,and on the basis of constructing the inverse equation of the comprehensive elastic modulus of the gravity dam,the scaled boundary finite element model of the gravity dam structure based on the MATLAB is established,and the PSO-LSSVM algorithm is used to learn and train the positive analysis results of the dam structure to obtain its inverse parameters.The case study shows that the method has improved both the accuracy of numerical results and the efficiency of calculation.At the same time,it overcomes the inherent defects of conventional back analysis of dam structure,such as the influence of singular element of finite element,and realizes the rapid identification of equivalent parameters of gravity dam structure performance.It provides a new idea for monitoring the deformation performance of concrete dam.