辨识与控制的联合设计算法仿真研究

Research on Combination Design Algorithm of Identification and Control

在自适应控制器设计中,控制器和辨识器一般是各自独立寻优的。在此,通过对进入辨识器的闭环数据进行预滤波,将辨识寻优指标和控制性能结合在一起,以改善控制器的动态特性。预滤波器的设计过程充分考虑了工程应用的可实现性。对滤波后的闭环数据利用开环转换思想,将闭环数据转换为两组开环数据,分别辨识出两个开环传函,再根据等价关系还原为要辨识的系统模型,从而抑制噪声对辨识的影响,得到更稳定可靠的模型。最后通过仿真研究验证了该算法的有效性。

System identification is of critical importance for implementing advanced control in the industries. As a result, the combination of identification and control, which views the identification problem in terms of its interaction with control system design, is a topic that possesses significant practical impact. In this paper, identification criteria are combined with control property via control-relevant pre-filtering. Its aim is to improve dynamic property of control system. And the pre-filter is easy to practice in the process industries. For overcoming the disturbance effect on the plant, coprime factor identification algorithm is used. It coverts the closed loop data to two open loops data by using open loop conversion idea. Then we can get two open loop transfer functions. At last we get system model on the grounds of equivalent relation to restrain the effect of disturbance. The simulation results show the availability of this algorithm.