论文部分内容阅读
提出一种基于虚拟目标值(virtual reference,VR)和支持向量机(support vector machine,SVM)的非线性控制器设计直接方法。该方法的优点在于,能够在对象未知的情况下,利用采集到的对象输入输出数据直接设计非线性反馈控制器。文中分析了虚拟目标值反馈调整(virtual reference feedback tuning,VRFT)理想控制器,给出了基于VR和SVM的非线性控制器的结构和设计步骤。仿真结果表明,该方法具有良好的处理非线性和噪声的能力,并且能消除稳态误差。与经典基于神经网络(neural networks,NN)的间接模型参考控制方法相比,计算量大大降低。
A direct method of nonlinear controller design based on virtual reference (VR) and support vector machine (SVM) is proposed. The advantage of this method is that the non-linear feedback controller can be directly designed by using the input and output data of the object without knowing the object. In this paper, an ideal controller of virtual reference feedback tuning (VRFT) is analyzed, and the structure and design steps of the nonlinear controller based on VR and SVM are given. The simulation results show that this method has a good ability to deal with nonlinear and noise, and can eliminate the steady-state error. Compared with the classical indirect model reference control method based on neural networks (NN), the computational cost is greatly reduced.