Ship PMSM Nonlinear ADRC Parameter Self-tuning Based on Neural Network

To address the problem that the magnetic synchronous motor for ships based on traditional PI controller is susceptible to interference and variable marine environment, resulting in unstable control system and insufficient adaptability, a nonlinear self-turbulence controller is used to replace the traditional PI controller, which can effectively improve the tracking accuracy and anti-turbulence capability of the system. However, since the traditional nonlinear self-turbulent control system requires more parameters to be adjusted and the adjustment process is more complicated, a parameter self-tuning method based on radial basis function neural network is proposed to realize the online self-tuning of parameters of the active disturbance rejection control system, and the simulation model was established and analyzed by Simulink. The results of simulation show that the active disturbance rejection controller based on radial basis function neural network has faster dynamic response speed, stronger anti-interference and compensation ability.