Adaptive Super-Twisting Sliding Mode Control of Active Power Filter Using Interval Type-2-Fuzzy Neural Networks

Aiming at the unknown uncertainty of an active power filter system in practical operation, combining advantages self-feedback structure, interval type-2 fuzzy neural network, and super-twisting sliding mode, adaptive mode control method network with recursive structure (IT2FNN-SFR STSMC) is proposed this paper. IT2FNN has uncertain membership function, which can enhance nonlinear ability robustness network. The historical information will be stored utilized by (SFR) runtime. Therefore, novel IT2FNN-SFR designed to improve dynamic approximation effect reduce dependence controller on actual mathematical model. rate each weight Lyapunov gradient descent (GD) algorithm ensure convergence stability system. Super-twisting (STSMC) strong robustness, effectively chattering, accuracy performance. gain integral term STSMC set as a constant, other changed adaptively whose deduced through proof greatly reduces difficulty parameter adjustment. harmonic suppression strategy verified simulation experiments.