基于模糊情感神经网络的有源电力滤波器全局积分终端滑模控制

To address harmonic pollution caused by nonlinear loads, this article proposes a global integration terminal sliding mode controller (GITSMC) based on fuzzy affective neural network (FANN) for active power filters (APFs). First, FANN is constructed by integrating fuzzy logic with affective computation, in which Hermite orthogonal polynomials and fuzzy activation functions are introduced to significantly enhance nonlinear approximation ability. Then, the baseline GITSMC with composite performance function is designed and approximated using FANN. Furthermore, the stability of the closed-loop system is rigorously proved via Lyapunov theory. Finally, multiscenario simulations and hardware experiments are carried out. The results show that the proposed method significantly reduces the total harmonic distortion (THD) under steady-state conditions and maintains superior dynamic performance under load fluctuations.