一种基于DDPG算法的永磁同步电机速度环控制方法
By using an intelligent control method based on the DDPG algorithm, the speed error and other states are directly mapped to the quadrature axis reference current, which solves the response and accuracy problems of traditional methods under complex working conditions and realizes fast response and high robustness control of permanent magnet synchronous motor.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- XIAMEN UNIV
- Filing Date
- 2026-05-11
- Publication Date
- 2026-07-17
AI Technical Summary
Traditional control methods for permanent magnet synchronous motors struggle to achieve high dynamic response and steady-state accuracy under complex nonlinear and highly time-varying conditions. Furthermore, indirect control methods based on deep reinforcement learning lack end-to-end global optimization capabilities, resulting in limited control performance.
An intelligent control method based on the DDPG algorithm is adopted, which constructs an Actor network and a Critic network. The speed error, error integral, and error differential are used as state inputs to directly map the quadrature-axis reference current. Combined with an empirical replay pool and a soft update mechanism, end-to-end control strategy optimization is achieved.
It achieves rapid response and robust control of permanent magnet synchronous motors under sudden load changes, avoiding response delay and accuracy loss caused by multi-level controllers, and improving control accuracy and robustness.
Smart Images
Figure CN122178793B_ABST