基于灰色预测和在线切换算法的研究,提出一种自适应灰色预测控制方法,该方法根据控制系统不同周期的输出误差值,自适应调整灰色预测控制器的预测步长,提高系统输出非平稳时间序列的光滑度,减少其随机性,以改进系统的暂态和稳态性能。并基于线性时不变对象,推导了该类自适应预测控制系统数学模型,给出其收敛的充分条件。最后,通过实例仿真分析证实了本方法控制精度高,鲁棒性强,具有良好的应用价值。 Based on the research of gray prediction and online switching algorithms, an adaptive gray prediction control method is proposed. The method adjusts the gray prediction controller’s prediction step adaptively according to the output error of different periods of the control system, and improves the system output non-stationary time The smoothness of the sequence reduces its randomness to improve the transient and steady state performance of the system. Based on the invariable linear objects, the mathematic model of adaptive predictive control system is deduced, and the sufficient condition for its convergence is given. Finally, the simulation results show that the method has high control accuracy and robustness, and has good application value.