Neural-Network-Based Robust Adaptive Synchronization and Tracking Control for Multimotor Driving Servo Systems

This article proposes a novel neural-network-based robust adaptive synchronization and tracking control strategy for multimotor driving servo systems. By designing a hyperbolic tangent function to adjust the synchronization control input, an adaptive adjacent cross-coupling synchronization structure is proposed to reduce the coupling effect between synchronization and tracking. Then, a nonsingular finite-time tracking controller is constructed to guarantee the finite-time stability of the tracking error, and the unknown nonsmooth nonlinearity is approximated by neural networks with discontinuous activation functions, which can reduce the computational complexity using fewer neural nodes. Simulation and experimental results verify the effectiveness of the proposed control method.