基于BP网络的土基含水量反演
Back-calculating Methodology of Subgrade Moisture with BP Net
通过对土基含水量、土基弹性模量以及路面表面弯沉值之间关系的分析，发现其中存在一定的函数关系。但这种复杂的函数关系难以用显式表达，因此很难通过路表弯沉直接对土基含水量进行反演。鉴于BP神经网络强大的映射能力，建立了三层BP神经网络，并对土基含水量与路表弯沉及路面破损之间的关系进行了分析，结果表明利用神经网络完全可以建立路表弯沉、路标破损率和土基含水量之间的映射关系。实际的工程应用表明，该方法的精度也满足工程需要。
By analyzing the relationship of moisture and elasticity modulus of subgrade with the ratio of pavement distresses and deflection of pavement, it is sure that there must be some complex relationship that is hardly to express explicitly, saying nothing of back-calculation the moisture directly with the deflection and the ratio of pavement distresses. Considering the good innuendo ability of BP net, the paper forms a 3-layer ANN that can reflect the relationship between subgrade moisture and surface deflection and distress ratio of pavement properly.
陈团结、钱振东
工程基础科学水工材料水利工程基础科学
BP神经网络土基含水量反演路表弯沉综合破损率
BP NetMoisture of subgradeDeflection of pavementRatio of pavement distressescomplex relationship
陈团结,钱振东.基于BP网络的土基含水量反演[EB/OL].(2005-09-14)[2025-08-21].http://www.paper.edu.cn/releasepaper/content/200509-130.点此复制
评论