Neural Network-based Robust Adaptive Synchronization and Tracking Control for Multi-Motor Driving Servo Systems

This paper proposes a novel neural network-based robust adaptive synchronization and tracking control strategy for multi-motor 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 non-singular finite-time tracking controller is constructed to guarantee the finite-time stability of the tracking error, and the unknown non-smooth nonlinearity is approximated by neural networks with discontinuous activation functions, which can reduce the computational complexity by using fewer neural nodes. Simulation and experimental results verify the effectiveness of the proposed control method.