This study mainly focuses on the development of a second-order sliding mode-based meta-cognitive fuzzy neural network (MCFNN) control for power quality improvement, whereby an MCFNN is employed to learn modelling uncertainties. First, a second-order sliding mode control (SOSMC) is designed to track reference current for active power filter. Then, an MCFNN system with accurate approximation capability is further investigated to learn the unknown parts in SOSMC. Different from the existing predefined structure approaches, only necessary data can be extracted to adjust the structure and parameters of the networks in MCFNN. Subsequently, the Lyapunov stability analysis is presented to guarantee tracking performance and stability of the closed-loop system. Moreover, the excellent performance of the proposed MCFNN scheme is verified by simulation and experimental studies, and its remarkable characteristics are exhibited in comparison with other intelligent control schemes.