基于DDPG-RP的功率硬件在环系统稳定性增强方法
By adopting a hierarchical collaborative control architecture based on DDPG-RP and a phase-compensated repetitive-voltage feedforward composite controller, the stability and accuracy issues of the PHIL simulation system were solved, achieving efficient dynamic response and stability verification under complex grid fault conditions, and improving the steady-state accuracy and fast dynamic response capability of the power hardware-in-the-loop system.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- TIANJIN UNIV
- Filing Date
- 2026-04-30
- Publication Date
- 2026-07-17
AI Technical Summary
Traditional PHIL simulation systems suffer from stability issues. Delays and bandwidth limitations caused by interface devices lead to system oscillations, impedance mismatch between the digital side and the device under test causes power fluctuations, and nonlinear loads and harmonic interference affect simulation accuracy. Existing control methods are also unable to cope with complex operating conditions.
A hierarchical collaborative control architecture based on DDPG-RP is adopted, which combines a phase-compensated repetitive-voltage feedforward composite controller and a deep deterministic policy gradient algorithm to construct an intelligent controller. The controller is trained offline and deployed online through deep reinforcement learning to achieve dynamic response and stability verification to power grid faults.
It effectively solves the problem that traditional control systems cannot balance stability and performance under complex power grid fault conditions, improves the steady-state accuracy and fast dynamic response capability of power hardware-in-the-loop systems, significantly shortens transient recovery time, and improves system stability and response speed.
Smart Images
Figure CN122136980B_ABST