土压平衡盾构改性砂土离散元模型参数反演方法研究

Inversion on discrete element model parameters of conditioned soil of earth pressure balance shield machine

首次将遗传神经网络与三轴试验离散元数值模拟有机结合,用于改性砂土颗粒离散元接触模型参数反演.反演目标是使三轴试验离散元模拟曲线与真实实验曲线误差最小,采用的求解策略是基于遗传神经网络的参数识别.三轴试验的离散元数值模拟为网络提供训练样本,遗传算法映射网络输入与输出样本之间的复杂非线性关系,改性土三轴试验的真实测量曲线为参数反演提供依据.以反演结果为接触模型参数的三轴试验离散元模拟曲线与真实实验曲线相吻合,为改性土离散元接触模型参数的确定提供了有效和准确的方法,为进一步的盾构密封舱压力分析奠定了基础.

The inversion method combining the genetic neural network and the discrete element simulation of triaxial tests is firstly described for determining the contact model parameters of the conditioned soil.The purpose is to make the error of the simulation curves and the laboratory curves of the triaxial tests minimum.The approach to this solution is the parameters identification based on the genetic neural network.The network training sample is provided by the discrete element simulation and the complicated nonlinear relation between the input and the output samples is mapped by the genetic algorithm.The laboratory triaxial test curves are the basis for parameter identification. The simulation curves calculated with the inversed model parameters match the laboratory curves well,which illustrates that the presented inversion method of the discrete element parameters of the conditioned soil is feasible and correct.It provides the basis for the further pressure analysis of the closet of the shield machine.