In this paper, we present a method to analyze local and global stability in offset-free setpoint tracking using neural network controllers and we provide ellipsoidal inner approximations of the corresponding region of attraction. We consider a feedback interconnection of a linear plant in connection with a neural network controller and an integrator, which allows for offset-free tracking of a desired piecewise constant reference that enters the controller as an external input. Exploiting the fact that activation functions used in neural networks are slope-restricted, we derive linear matrix inequalities to verify stability using Lyapunov theory. After stating a global stability result, we present less conservative local stability conditions (i) for a given reference and (ii) for any reference from a certain set. The latter result even enables guaranteed tracking under setpoint changes using a reference governor which can lead to a significant increase of the region of attraction. Finally, we demonstrate the applicability of our analysis by verifying stability and offset-free tracking of a neural network controller that was trained to stabilize a linearized inverted pendulum.
翻译:在本文中,我们用神经网络控制器分析当地和全球在抵消性定点跟踪方面的稳定性的方法,我们提供了相应的吸引区域的垂直内部近似值。我们考虑了线性工厂与神经网络控制器和集成器的反馈连接,从而可以对进入控制器作为外部输入的可取的点常量参考进行无抵消性跟踪。我们利用神经网络使用的激活功能是斜坡限制的这一事实,我们得出线性矩阵不平等,用Lyapunov理论来核查稳定性。在指出全球稳定结果后,我们提出了较保守的地方稳定条件(一) 用于特定参考,(二) 用于某一集的任何参考。后一种结果甚至使定点变化得到保证,使用参照控制器可以导致吸引区域大幅增长。最后,我们通过核查稳定性和抵消性跟踪一个经训练可稳定倒置线形的神经网络控制器,来证明我们的分析是可行的。