Prediction of resilient modulus for subgrade soils based on ANN approach

Abstract

The resilient modulus (MR) of subgrade soils is usually used to characterize the stiffness of subgrade and is a crucial parameter in pavement design. In order to determine the resilient modulus of compacted subgrade soils quickly and accurately, an optimized artificial neural network (ANN) approach based on the multi-population genetic algorithm (MPGA) was proposed in this study. The MPGA overcomes the problems of the traditional ANN such as low efficiency, local optimum and over-fitting. The developed optimized ANN method consists of ten input variables, twenty-one hidden neurons, and one output variable. The physical properties (liquid limit, plastic limit, plasticity index, 0.075 mm passing percentage, maximum dry density, optimum moisture content), state variables (degree of compaction, moisture content) and stress variables (confining pressure, deviatoric stress) of subgrade soils were selected as input variables. The MR was directly used as the output variable. Then, adopting a large amount of experimental data from existing literature, the developed optimized ANN method was compared with the existing representative estimation methods. The results show that the developed optimized ANN method has the advantages of fast speed, strong generalization ability and good accuracy in MR estimation. 回弹模量作为路基结构的刚度指标, 是路面结构设计中的重要参数。为快速准确地获取路基土 回弹模量, 本文采用BP 神经网络对回弹模量进行直接预估, 以多种群遗传算法对BP 算法进行优化, 解决了传统BP 神经网络效率低、易陷于局部最优和过拟合等问题。建立了由10 个输入变量、21 个 隐含层和1 个输出变量组成的回弹模量预估方法。其中, 输入变量包括路基土的物性参数(液限、塑 限、塑性指数、细粒含量、最大干密度、最佳含水率)、状态变量(压实度、含水率)和应力变量(围压、 偏应力); 输出变量为回弹模量。结合已有文献中的大量试验数据, 将所建立的优化神经网络方法与现 有代表性的预估模型进行对比分析。研究结果表明, 相比于传统预估模型, 基于多种群遗传算法优化 的BP 神经网络预估方法在回弹模量预估中具有速度快、泛化能力强和预估精度高等优点。