【摘要】 由于三容水箱是一个具有多变量、非线性和耦合特征的系统,难以建立精确的数学模型。为此,提出了基于RBF-ARX模型的预测控制策略。RBF-ARX模型是神经网络RBF(Radial Basis Function)和线性自回归ARX(Auto-Regres-sive e Xogenous)模型兼容组合的模型,适用于非线性系统的建模。预测控制算法基于此模型预测对象输出变化,并通过闭环控制,使误差最小。该设计首先构建三容水箱系统的RBF-ARX模型,并辨识、优化模型参数。基于此模型设计了系统预测控制器,最后通过实时控制证实了该方法的可行性和有效性。更多还原

【Abstract】 The three-tank water system which is multivariable,nonlinear and coupled with each other makes it difficult to establish accurate mathematical model,for the problem,the design of predictive control algorithm based on RBF-ARX model are discussed.This modeling method is a combination model based on the theory of neural network RBF(Radial Basis Function)and linear autoregressive ARX(Auto-Regressive e Xogenous)model,it is used to construct the model of nonlinear system.Predictive control algorithm predicts system ’s output,and makes the error minimum through closed-loop control.The structure of the three-tank water system ’s RBF-ARX model is built firstly,then the model’s parameters are identified and optimized.Predictive control algorithm is taken to control the three-tank water system based on this model,the real-time control verify the feasibility and validity of the method.更多还原