摆式客车倾摆控制系统神经网络预测控制  

Neural Network Predictive Control of Tilting Control System in Tilting Passenger Car

作　　者：张济民[1] 张继彤[1] 任利慧[1] 

机构地区：[1]同济大学铁道与城市轨道交通研究院,上海200331

出　　处：《同济大学学报（自然科学版）》2006年第7期947-952,共6页Journal of Tongji University:Natural Science

摘　　要：考虑伺服电机及机械系统的非线性对车体倾摆的影响,并包括伺服电机的饱和非线性特性的影响在内,采用神经网络方法对非线性特性的动态系统的输入输出关系进行辨识研究,建立摆式客车伺服系统神经网络非线性模型;提出在摆式客车中运用神经网络预测控制结合鲁棒控制的复合控制系统,解决这类非线性系统的控制问题,即应用神经网络进行辨识及预测控制.研究表明,从理论及工程应用角度看神经网络预测控制都是切实可行的,为在摆式客车倾摆控制系统中应用神经网络预测方法提供了一个新的方向.In this paper, study is focused on the effect of nonlinear servo electromotor and mechanic system on tilting of passenger cars. The dynamic nonlinear system is identified in neural network and the neural network model is constructed. The neural network predictive control and the robust control are combined to solve the control problem of nonlinear system. The identification and control law is studied on the basis of the neural network. The predictive control of tilting passenger car is also discussed. Study results show that the neural network predictive control method is both theoretically and practically feasible. A new direction is pointed out to set up the neural network predictive way of the tilting system in tilting passenger car.

关 键 词：摆式客车 神经网络 预测控制 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] U271[自动化与计算机技术—控制科学与工程]