Evaluation of Sand Liquefaction Based on SOFM Neural Network

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.