基于双柔化系数在线调整的广义预测控制

在预测控制系统中，其控制品质与控制器的参数整定有很大的关系，特别是性能指标中的输出柔化系数及输入柔化系数。针对广义预测控制算法中控制参数整定困难这一缺点，利用BP神经网络，提出一种基于双柔化系数设计的广义预测控制算法，实现了广义预测控制中输入输出柔化系数的在线调整。仿真结果表明，该算法无论在跟踪性能、控制精度及鲁棒性上，均优于固定参数的广义预测控制算法，并对干扰有一定的抑制作用。

Generalized Predictive Control Based on the On-line Tuning of Double Softness Parameters

In predictive control systems,the control quality is strongly influenced by the parameters tuning of controllers,especially the output softness parameter and the input softness parameter in the performance index.In order to overcome the drawback of the generalized predictive control(GPC) in the parameters tuning,a new GPC based on the design of double softness parameters is presented by using BP neural networks,in which the on-line tuning of the input softness parameter and the output one is achieved.Simulation results show that the algorithm is superior to the GPC with invariable parameters in track capacity and control precision,and it also puts a check on the disturbance in some sense.