基于ANN模型的非线性自校正预测控制器

ARTIFICIAL NEURAL NETWORKS BASED NONLINEAR SELF TUNING PREDICTIVE CONTROLLER

采用局部建模和线性化方法，提出了一种基于人工神经网络（ＡｒｔｉｆｉｃｉａｌＮｅｕｒａｌＮｅｔ－ｗｏｒｋ——ＡＮＮ）模型的非线性自校正预测控制算法．仿真实例表明，所提控制策略可有效地控制某些未知多变量非线性动态系统．

Using neural networks as nonlinear predictors, this paper proposes a self tuning predictive controller for multivariables nonlinear systems. The main idea of the presented control strategy is to use the linearization technique in feedforward neural net identifier models. Simulation examples including a time varying plant and a nonlinear plant are shown to demonstrate the effectiveness of the control algorithm.