Optimal design of Takagi-Sugeno-Kang fuzzy neural network based on balancing composite motion optimization for chaotic synchronization with uncertainty and disturbance

In this paper, we propose an improved Takagi-Sugeno-Kang fuzzy neural network based on balancing composite motion optimization (BCMO-ITSKFNN) for a chaotic synchronization system. The investigation of chaotic synchronization systems is highly intriguing due to the intrinsic intricacy and enigmatic characteristics linked to chaotic systems. The BCMO-ITSKFNN controller is robust and suitable for modelling complex nonlinear systems, capturing intricate relationships between input and output variables, and being trained efficiently using data. The Lyapunov theory and balancing composite motion optimization techniques are used to optimize the parameters of BCMO-ITSKFNN. In comparison with previous methods, it is found that the proposed BCMO-ITSKFNN has the best learning ability and provides the best performance results. • The BCMO-ITSKFNN controller captures global and local characteristics and enhances system optimization by learning data. • The BCMO method simplifies optimization by allowing the best-ranked individual in their local space. • The BCMO-ITSKFNN controller is capable of handling both uncertainties and disturbances of 4D chaotic hyper-jerk systems.