利用BP人工神经网络反算沥青路面基层弹性模量研究

基于层状弹性体系理论,利用BP人工神经网络预测沥青路面基层弹性模量。通过构建路表弯沉盆与沥青路面基层参数之间的数据库,建立了BP人工神经网络反算基层弹性模量预测模型。由理论弯沉盆作为已知输入参数进行反算时,基层弹性模量的反算值与理论值相对误差在8%左右;由实测弯沉盆作为已知输入参数进行反算时,计算弯沉盆与标准化实测弯沉盆的拟合均方差RMSE为4.49%。检验结果表明:基于层状弹性体系理论,建立的BP人工神经网络反算沥青路面基层弹性模量模型,可满足实践工程要求。

基于不同基层弹性模量的沥青路面加铺厚度设计案例分析

中国以沥青路面结构为主导的公路路网已基本建成并开始进入全面养护维修阶段。文中针对现阶段常使用的加铺设计方法,通过案例探讨如何确定半刚性基层沥青路面结构层的有效模量,进而确定沥青路面加铺层设计厚度。结果表明采用现行规范方法进行加铺层设计存在一定局限性,按3层沥青面层的旧路基层在最有利和最不利状态下的弹性模量计算出的适宜加铺厚度相差约3cm,基层弹性模量的变化对加铺厚度的影响不大。

Resilient Modulus of Hydraulically Bound Road Base Materials with High Volume Waste Dust

The paper presents laboratory test results on hydraulically bound road base materials containing high volume of steel slag and blast furnace slag waste dusts compared with control mixtures. These mixtures contain higher levels of （4mm-0.0 mm） dust, than would be the case in standard un bound road base mixtures. The combined influence of the steel slag and granulated blast furnace slag wastes content is to enhance the stiffness of the road base materials and save materials and cost during road construction. Triaxial repeated load tests were performed on the unbound and lightly bound materials to measure their resilient modulus. The test results show important improvements in the bond strength between the contents of road base materials. This offers the prospect of using these materials in road base materials to reduce the use of primary aggregates and thus minimize the cost of roads and highways construction.