论文部分内容阅读
基于三层BP神经网络和层状弹性理论,由路表变形反算土基回弹模量。利用层状弹性计算程序构建了土基回弹模量与路表弯沉数据库,并输入BP神经网络进行训练,建立了基于BP神经网络的土基回弹模量反算模型。理论和实测路表弯沉反算结果表明,该方法具有良好的识别能力和泛化能力,是一种实用而有效的方法,为进一步快速、有效地评定土基的承载能力提供了依据。
Based on the three - layer BP neural network and layered elastic theory, the elastic modulus of soil foundation is inverse calculated from the deformation of road surface. The layered elastic modulus calculation program is used to build the database of the rebound modulus and the deflection of the road surface, and then input to the BP neural network for training. The back-calculation modulus of the rebound modulus of the foundation is established based on the BP neural network. The theoretical and experimental results show that the method has good recognition ability and generalization ability. It is a practical and effective method to provide a basis for further rapid and effective assessment of the bearing capacity of the soil foundation.