Double-motor safety coordination control method under FDI network attack based on reinforcement learning

The invention discloses a reinforcement learning-based dual-motor safety coordination control method under FDI network attack. The method comprises the following steps of (1) establishing a dual-time scale mathematical model of a flexible connection dual permanent magnet synchronous motor system; (2) establishing an FDI network attack model of the dual-time scale mathematical model; (3) designing a safety coordination controller based on the LQR theory; (4) designing model-free reinforcement learning according to the FDI network attack model established in the step (2), and carrying out iterative solution on the safety coordination controller designed in the step (3); according to the method, the influence of FDI network attack on the system is avoided, the reinforcement learning algorithm is adopted without depending on model data, and the influence of motor parameter change on the system is avoided; the method is of great significance in improving the coordination control performance of the networked coordi