利用模糊神经网络进行砂土液化势评判

USING FUZZY NEURAL NETWORK TO EVALUATE SAND LIQUEFACTION POTENTIAL

利用模糊信息分析表达知识和人工神经网络在映射能力方面的优势 ,选取应力比、震级、地面运动最大加速度、标贯击数、地下水位作为评价参数指标 ,构造砂土液化势识别的模糊神经网络模型。验证和应用结果表明 ,模糊神经网络模型可提供更高的映射能力 。

From the data of many factors such as earthquake magnitude, stress ratio, SPT value, peak ground surface acceleration, and water table, a fuzzy neural network model was constructed and verified for classifying sand liquefaction potential in the paper. The result obtained is superior to those derived by conventional fuzzy clustering means. It indicates that this methodology is a potentially useful tool in objectively evaluating and predicting liquefaction potential of sand.