Adaptive Terminal Sliding Mode Control of Single-Phase Active Power Filter Using Novel Recurrent Neural Network

In this article, a terminal sliding mode (TSM) strategy based on fuzzy double hidden layer recurrent neural network (FDHLRNN) is studied for a singe-phase active power filter (APF). Terminal sliding simulation solves the problem that the tracking error of traditional sliding mode cannot converge to zero in a finite time. The FDHLRNN is used to replace the equivalent of sliding mode control to reduce errors caused by unknown disturbances. Finally, the prototype experiments verify the reliability of the proposed control strategy.