摘要
针对多变量非线性系统 ,提出了一种基于 Tchebycheff正交神经网络的多步预测控制方案 ,采用 Tchebycheff正交神经网络离线建立预测模型 ,并以偏差补偿和模型修正相结合的方式对预测模型进行误差补偿 ,经在线校正用于预测控制。同时对性能指标中的偏差项和控制项加权 ,进一步改善预测控制性能。
A predictive control strategy based on a Tchebycheff orthogonal neural network is proposed for a nonlinear multivariable system. This paper uses a Tchebycheff orthogonal neural network to build a predictive model off line and adopts error compensation and model correction to correct the predictive model online. In addition, it gives the weighting factors of error and control efforts in the cost function to improve the performance of the control. The results of the simulation show the effectiveness of the control algorithm.
出处
《青岛科技大学学报（自然科学版）》
CAS
2003年第1期70-72,共3页
Journal of Qingdao University of Science and Technology:Natural Science Edition
