一种跟踪问题中的次优非线性预测控制算法  

Suboptimal model predictive control for nonlinear system on tracking problem

作　　者：王亚锋[1,2] 孙富春[2] 张友安[1] 刘华平[2] 

机构地区：[1]海军航空工程学院自动控制系,山东烟台264001 [2]清华大学计算机科学与技术系,北京100084

出　　处：《控制与决策》2009年第11期1682-1687,共6页Control and Decision

基　　金：国家自然科学杰出青年基金项目(60625304);国家自然科学基金项目(90716021;60621062);国家重点基础研究发展计划项目(2007cb311003;2009cb724002)

摘　　要：针对跟踪问题中无状态和输入约束的非线性预测控制最优解的求取问题,引入参考输入轨迹的概念,利用Stirling插值公式,将非线性系统模型沿参考输入输出轨迹展开,取其一阶近似,处理成参数已知的线性模型.在此基础上,利用线性系统预测控制理论求解得到原系统的次优控制律.该方法不要求系统模型连续可导,且无需对线性化后的模型参数进行在线辨识,计算量小,易于实现.For the computation of optimal solution in model predictive control with no constraint on state and input for nonlinear system on tracking problem, the concept of reference input trajectory is introduced and the nonlinear system model is expanded by using Stirling＇s interpolation formula along the reference input and output trajectory. Then, the system model is approximated with a linear model with known value parameters by reserving the first order of the expanded series. Based on this Linear model, the suboptimal control can be computed by using the linear model predictive control theory. This method does not demand the system model to be continuous and differentiable, and needs no on-line identification of the parameters for the linear model. Its actualization is very easy and the computation burden is low.

关 键 词：模型预测控制 线性化 次优控制 跟踪问题 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]