Abstract: The suurrounding rock deformation of highway tunnel is an important index to assess its stability and economy of support structule in NATM．It is a data column which is related with measurement time sequence,so we can set up some effective models and methods to pledicate the surrounding rock deformation．According to the surrounding rock deformation characteristic of Yangzong highway tunnel，this paper sdopts the nerve network technology to predict the subsidenee displacements．The research results show this prediction method is simple and effective．

Key words: Yangzong highway tunnel, nerve network, surrounding rock defommfion, prediction

摘要： 隧道新奥法施工中，常以围岩变形量作为评判围岩稳定性和支护结构合理性的重要指标，公路隧道围岩变形 量是随时间而变化的数据序列，因而可以建立一些实时跟踪预测模型和方法．本文根据阳宗隧道围岩拱顶下沉位 移变形的特性，采用神经网络技术来预测其变形量，结果表明该方法简易、有效．

关键词: 阳宗隧道, 神经网络, 围岩变形, 预测