摘要
针对一类参数大范围变化的不确定系统,提出一种基于分类转换策略的神经滑模控制方法.按小偏差原理对系统模型进行划分,利用结合主成分分析的最小二乘支持向量机进行分类训练,并分别设计基于径向基函数神经网络在线调整切换项增益的滑模控制器,在线时利用分类器按系统数据自动选择相应的控制器.同时,引入结合混沌机制的量子粒子群算法,并将其用于控制器近似最佳切换函数的构造.仿真结果表明,系统具有良好的跟踪性能和较强的鲁棒性,有效地降低了抖振.
A classifying and switching strategy based on least square support vector maehine（LS_SVM） for the control of uncertain system with the parameters varying in a wide range is proposed. The original system model is divided into several models with small range of uncertainty. These models are classified by LS_SVM combined with principal component analysis（PCA） offline. For each model, the sliding-mode controller（SMC） with its gain tuned by radial basis function neural network（RBFNN） is designed and applied. In online situation, the designed SMC is selected automatically by LSSVM based on system data. The quantum-behaved particle swarm optimization（QPSO） with chaos strategy is designed and applied to adjusting the parameters, so as to construct an optimized switching function. Finally, the system scheme is designed by the proposed strategy. Simulation results show the high tracking performance and strong robustness of the new strategy, as well as the effectively reduced chattering problem.
出处
《控制与决策》
EI
CSCD
北大核心
2009年第10期1559-1564,共6页
Control and Decision
基金
国家863计划项目(2006AA04Z402)
关键词
不确定系统
最小二乘支持向量机
量子离子群算法
滑模控制
神经网络
Uncertain system
Least square support vector machine
Quantum-behaved particle swarm optimization
Sliding mode control
Neural network
