补偿模糊神经网络在砂土液化势评价中的应用

Application of Compensative Fuzzy Neural Network in Assessment of Sand Liquefaction Potential

在分析砂土液化影响因素的基础上,选取震级、地面加速度最大值、标准贯入击数、比贯入阻力、相对密实度、平均粒径、地下水位等7个因素作为评价指标,建立了砂土液化势评价的补偿模糊神经网络模型。通过对网络的学习训练和仿真检验,表明补偿模糊神经网络是进行砂土液化势预测评价的有效手段。

This paper establishes the compensative fuzzy neural network model for assessing sand liquefaction potential with seven parameters including earthquake magnitude, peak ground surface acceleration, standard penetration value, specific penetration resistance, relative compaction, average particle diameter, and water table based on analyzing some influencing factors of sand liquefaction. The result indicates that compensative fuzzy neural network is a useful tool in the assessing and predicting liquefaction potential through training and simulating the network.