计算机工程与应用 ›› 2011, Vol. 47 ›› Issue (29): 239-241.

• 工程与应用 • 上一篇    下一篇

盾构机密封舱压力控制模型参数辨识

李守巨1,陈禹臻2,王吉喆3,屈福政2   

  1. 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.大连理工大学 机械工程学院,辽宁 大连 116024
    3.大连医科大学 附属第二医院,辽宁 大连 116023
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2011-10-11 发布日期:2011-10-11

Model parameter estimation scheme in shield tunneling operation based on neural network

LI Souju1,CHEN Yuzhen2,WANG Jizhe3,QU Fuzheng2   

  1. 1.State Key Lab of Structural Analysis of Industrial Equipment,Dalian University of Technology,Dalian,Liaoning 116024,China
    2.School of Mechanical Engineering,Dalian University of Technology,Dalian,Liaoning 116024,China
    3.The Second Affiliated Hospital of Dalian Medical University,Dalian,Liaoning 116023,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-10-11 Published:2011-10-11

摘要: 为了解决盾构机密封舱压力控制模型参数辨识问题,提出了基于神经网络的盾构机密封舱压力控制模型参数辨识方法。根据系统输出(密封舱压力)与系统输入(螺旋输送机转速)之间的关系,建立了串并联神经网络辨识器。数值仿真结果表明,该辨识方法对于观测噪声具有良好的鲁棒性。实验台实验结果验证了所提出的模型参数辨识方法的有效性,模型预测的密封舱压力能够较精确拟合密封舱压力观测值。

关键词: 神经网络, 系统辨识, 盾构机掘进, 密封舱压力控制

Abstract: Model parameter estimation scheme is proposed to solve model parameter identification problem in shield tunneling operation.Neural network model is applied to system identification.Identifier of parallel-series neural network is developed based on the relationship between the system input(rotating speed of screw conveyor) and system output(earth pressure in chamber).Numerical simulation results show that the proposed procedure has high robustness to observation error.The effectiveness of identification approach is verified in laboratory test.The forecasted system outputs agree well with observed earth pressure in chamber.

Key words: neural network, system identification, shield tunneling operation, pressure control for pressurized chamber