基于自组织神经网络的砂土液化评价

Evaluation of Sand Liquefaction Based on SOFM Neural Network

在分析自组织特征映射(SOFM)神经网络基本学习算法的基础上,从提高算法收敛速度和性能出发,提出了一种改进算法:根据实际应用并结合专家经验确定初始连接权值;采用高斯函数作为拓扑邻域函数;将算法分为粗调整和细调整两个阶段,分别采用不同的学习率和邻域函数,然后采用改进后的SOFM算法对砂土液化进行评价。实例研究表明,应用SOFM神经网络评价砂土液化高效可行,为砂土液化评价提供了新方法。

An improved algorithm for self-organizing feature map neural network is presented. In this algorithm,the expert experience and actual state are considered using training weight vectors, the Gauss weight neighborhood function is used to replace the square or circular function, and different descending functions of learning rate and neighborhood width are used in two learning periods. The improved algrithm is used to evaluate the sand liquefaction. The testing results of practical examples show that the method based on SOFM neural network is feasible and effective, and it provides a new approach to research sand liquefaction potential.