盾构机土仓压力平衡系统智能建模及其实验  

Intelligent modeling pressure balance system in soil chamber in shield tunneling and its experimental investigation

作　　者：李守巨[1] 于贺[2] 曹丽娟[3] 

机构地区：[1]大连理工大学工业装备结构分析国家重点实验室,辽宁大连116024 [2]沈阳工业大学建筑工程学院,辽宁沈阳110023 [3]大连海洋大学机械工程学院,辽宁大连116023

出　　处：《煤炭学报》2012年第A02期325-329,共5页Journal of China Coal Society

基　　金：国家重点基础研究发展计划资助项目(2007CB714006);国家自然科学基金资助项目(51105048)

摘　　要：为解决盾构机土仓压力平衡系统时滞、非线性、时变和不确定特性建模问题,建立了基于神经网络和系统输入-输出观测数据的智能建模方法,解决了土仓压力平衡系统的解析数学建模所遇到的困难。计算结果表明,基于Gauss-Newton优化的神经网络训练方法,具有较快的收敛速度。盾构机实验台实验结果表明,与解析数学建模方法相比,所提出的新的智能建模方法拟合和预测精度提高了一个数量级,验证了智能建模方法的有效性和精确性。In order to deal with modeling problem of a pressure balance system with time-delay,nonlinear,time-varying and undetermining characteristics,an intelligent modeling procedure was proposed,which was based on neural network and input-output data during shield tunneling and can overcome the problems in analytically modeling approach.The computational results show that the training algorithm with Gauss-Newton optimization has fast convergent speed.The experimental investigation indicates that,comparing with analytically modeling approach,intelligent modeling procedure can obviously increase precision in pressure fitting and forecasting,and the effectiveness and accuracy of proposed intelligent modeling procedure were verified.

关 键 词：盾构机 土仓压力平衡 智能建模 神经网络 

分 类 号：U455.39[建筑科学—桥梁与隧道工程]