【摘要】 针对倒立摆系统的高阶次、非线性和强耦合特性,导致难以建立准确的数学模型,针对这个难题,提出了基于RBF-ARX模型的预测控制算法。该建模方法结合了线性自回归模型和高斯径向基函数的理论,通常用于构建非线性系统的模型。预测控制算法采取RBF-ARX模型多步向前预测输出,并反馈到输入端,根据参考轨迹进行校正,使误差最小。该法首先构建倒立摆系统的RBF-ARX模型结构,然后辨识并优化模型参数。基于此模型采取预测控制算法控制倒立摆系统,最后通过仿真控制效果验证了该方法的可行性和有效性。更多还原

【Abstract】 The Inverted Pendulum System which is high order,nonlinear and coupled with each other makes it difficult to es-tablish accurate mathematical model,for the problem,the design of predictive control algorithm based on RBF-ARX model werediscussed. This modeling method is a combination model based on the theory of linear autoregressive(Auto-Regressive e Xogenous,ARX)model and Gauss radial basis function(Radial Basis Function)neural network(RBF),it is used to construct the model ofnonlinear system usually. Predictive control algorithm uses RBF-ARX model to predict multi-steps output forward,and feedbackto the input in order to minimize the error according to the reference trajectory correction. The structure of the Inverted PendulumSystem s RBF-ARX model is built firstly,then the models parameters are identified and optimized. Take predictive control algo-rithm to control the inverted pendulum system based on this model,the simulation results verify the feasibility and validity of themethod.更多还原