基于神经网络的盾构液压推进系统的参数辨识（英文）

Parameter identification of shield hydraulic propulsion system based on neural network

为了提高盾构液压推进系统速度控制的精度,减小建立数学模型与实际系统之间的偏差,提出基于时延神经网络和系统参数上下界值的动态系统参数辨识方法。在建立盾构液压推进系统速度控制模型的基础上,利用神经网络在待辨识参数的范围内对系统的不定参数进行辨识,搜索出更逼近实际盾构推进系统的一组参数,满足对系统输入实际信号时能够准确地得到实际系统的输出。利用盾构模拟实验台的另一组采样数据对系统辨识结果进行验证,结果表明:该辨识方法得到的模型能够逼近真实的物理系统。

In order to improve the accuracy of the speed control of the shield hydraulic propulsion system and re-duce the deviation between the mathematical model and the actual system,a dynamic system parameter identifica-tion method based on the time delay neural network and the upper and lower bounds of the system parameters is proposed.On the basis of establishing the speed control model of shield hydraulic propulsion system,the neural network is used to identify the indefinite parameters of the system within the range of parameters to be identified,and search for a set of parameters closer to the actual shield propulsion system to meet the system input.The actu-al system output can be accurately obtained for the actual signal.Finally,another set of sampled data of the shield simulation test bench is used to verify the system identification results.The results show that the model obtained by the identification method can approximate the real physical system.