岩体力学参数反演的模拟退火支持向量机方法

Simulated Annealing and Support Vector Machine Method to Back Analyzing Mechanical Parameters of Rock and Soil

针对支持向量机在参数(包括核函数及其参数)确定方面的问题,利用其在处理小样本、高维数、非线性等问题的优良特性,及模拟退火算法的全局优化能力,提出了基于模拟退火算法的支持向量机方法,将该方法引入到岩土工程问题中,形成岩土体参数识别的模拟退火支持向量机方法,并通过算例说明了该方法的可靠性.

A new support vector machine method based on simulated annealing algorithms, which combines the global optimization characteristic of simulated annealing algorithms and the nonlinear mapping characteristic of support vector machine, is proposed in this paper. The method is used to recognize the mechanical parameters of rock and soil. A numerical example shows the reliability of this method.