基于粒子群优化的在线支持向量回归预测控制方法  

Online Support Vector Regression Predictive Control Algorithm Based on Particle Swarm Optimization

作　　者：陈进东 潘丰 

机构地区：[1]江南大学轻工过程先进控制教育部重点实验室,江苏无锡214122

出　　处：《信息与控制》2013年第6期723-728,734,共7页Information and Control

基　　金：国家自然科学基金资助项目(61273131);江苏省高校优势学科建设工程资助项目

摘　　要：针对非线性系统模型预测控制中,预测模型容易失配和目标函数难以求解的问题,提出了一种基于粒子群优化算法的非线性系统在线支持向量回归模型预测控制方法.该方法利用在线支持向量回归建立被控对象的非线性预测模型,并通过在线学习实现模型的在线自校正;同时采用粒子群优化算法求解目标函数,完成滚动优化.对非线性系统的仿真结果表明,该方法是有效的且具有良好的自适应性.For the problems of model mismatch and difficulty in solving objective function in the predictive control of the nonlinear system model, an online support vector regression predictive control algorithm based on particle swarm optimiza- tion （PSO） is proposed. An nonlinear predictive model for the object is built based on the online support vector regression, and the object is identified and the identified model also can be self-adjusted through online learning. Meanwhile, the ob- jective function is solved by PSO, the rolling optimization is realized. The nonlinear system simulation results show the effectiveness and adaptability of the presented algorithm.

关 键 词：非线性模型预测控制 在线支持向量机 粒子群优化(PSO) 滚动优化 

分 类 号：TP13[自动化与计算机技术—控制理论与控制工程]