论文部分内容阅读
由于板带轧制的环境十分复杂,如温度的变化是无法避免的干扰,以及HC轧机液压弯辊系统的非线性和不确定性,使得按传统理论建立的模型和控制方法都难以达到理想的效果.针对这一问题,提出了一种基于径向基函数(RBF)神经网络的模型预测控制方案应用于带材控制中,以提高带材的成材率,充分发挥液压弯辊力对板形的调整作用,改善轧机系统的动态特性.仿真结果表明了该控制系统的性能良好,有较强的抗干扰能力和较好的鲁棒性和快速性.
Due to the complex environment of strip rolling, such as the change of temperature is unavoidable interference and the nonlinearity and uncertainty of hydraulic rolling system of HC mill, it is difficult to achieve the ideal model and control method based on traditional theory Effect.Aiming at this problem, a model predictive control scheme based on Radial Basis Function (RBF) neural network is proposed in the strip control to improve the yield of the strip and give full play to the effect of hydraulic bending force on the plate shape The simulation results show that the control system has good performance, strong anti-interference ability and good robustness and rapidity.