基于在线支持向量机的非线性内模控制

Nonlinear internal model control based on online support vector machine

为了提高传统内模控制的鲁棒性和抗干扰能力,采用在线支持向量机回归(Online Support Vector Machine Regression,OSVMR)理论建立系统的正向模型和设计逆模控制器。首先简要介绍了OSVMR的原理和算法,然后将其应用于内模控制问题,并建立了OSVMR模型。其次,在控制过程可逆的条件下设计了OSVMR控制器,最后将该控制方法应用于可逆非线性系统和具未知干扰的温室环境控制问题,仿真结果表明该方法与RBF神经网络IMC相比,具有较简单的模型和较好的控制性能。

To improve the robustness and anti-interference of traditional inverse control,the system process is modeled and an inverse model controller using support vector machine regression（OSVMR） is designed.First,the OSVMR principle is briefly intro- duced.Second,the OSVMR is applied to the internal model control （IMC） problem,and the OSVMR internal model is developed. Third,an OSVMR controller for internal model control problem is proposed under the inverse condition of control process.Finally, the control algorithm is applied to the reversible nonlinear system and greenhouse environment with unknown disturbance,and compared with neural networks IMC using simulation,and the results show that the OSVMR IMC has a simplified model and good control performance.