Development of an active power filter based on sliding mode control and RBF networks
Robotics and Mechatronics Engineering
In this article, an active power filter (APF) integrating sliding mode control and the radial basis function neural network (RBFNN) is proposed to track and suppress harmonic wave components generated by nonlinear loads in a power grid. The mathematical model of the APF is derived, and the sliding mode control strategy is presented. In addition, an RBFNN is proposed to approximate to the nonlinear characteristics of the plant so as to improve the controller's performance. The simulation and experimental results validate the effectiveness of the proposed approach.
Mechatronic Systems and Control
Digital Object Identifier (DOI)