液压弯辊系统的自适应模糊神经网络控制

Application of AFNNC to Bending Rolls Control

液压弯辊系统具有时变、非线性、外界干扰严重等特点,难以建立精确的用于控制的数学模型。针对该问题,在预先设计了一个PID控制器的基础上,用模糊神经网络设计了一种具有自适应能力的控制器。仿真实验表明,同常规PID控制器相比,该控制器可以克服弯辊系统的参数改变对控制性能的影响,极大地提高了系统的抗干扰能力,降低了控制系统性能对弯辊系统解析模型精度的依赖程度。结果证明该控制方法对于弯辊系统的控制是有效的。

In view of the time variability and the non linear character in rolling mills, for example UC rolling mill, a AFNNC with self-adapting ability is developed after a PID controller have been finished. Compared with PID controller, the simulation shows that AFNNC has more desirable performance in self-adapting ability and robustness. This control method is very useful for improving the quality of shape control.