概率神经网络在隧道变形位移预测中的应用  

Application of probabilistic neural network in the tunnel deformation displacement forecast

作　　者：刘宇[1] 卢宇[2] 张玉欣[3] 

机构地区：[1]吉林铁道职业技术学院铁道工程系,吉林吉林132001 [2]吉林省机电研究设计院 [3]北华大学

出　　处：《冶金自动化》2012年第4期20-22,共3页Metallurgical Industry Automation

摘　　要：将概率神经网络(PNN)引入到隧道变形位移预测中,建立了非线性智能预测模型,并采用递推预报误差(RPE)算法对PNN进行训练。以铜黄高速大田连拱隧道施工实地监测数据为样本对网络进行训练与预测分析,仿真结果表明本方法训练速度快且预测值与实测值吻合度较高。Probabilistic neural network is introduced into the tunnel deformation displacement forecast in this paper. Nonlinear intelligent forecast model is established and recursive prediction error （RPE） algorithm has been adopted to train the PNN network. Actual data of Datian double-arch tunnel in Tonghuang high-way are used as sample to train PNN and predict tunnel deformation displacement. The simulation results show that this method has a fast training speed and a high goodness of fit be- tween forecasted and observed values.

关 键 词：概率神经网络 递推预报误差算法 非线性系统 隧道变形位移 智能预测模型 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] U456.3[自动化与计算机技术—控制科学与工程]