Plant-Physics-Guided Neural Network Control for Permanent Magnet Synchronous Motors

In safety- and precision-critical control scenarios for permanent magnet synchronous motors (PMSMs), the external spontaneous disturbance causes unexpected speed drop. The disturbance occurs without routine, so it cannot be modeled specifically. The large speed drop and slow response speed cause a reduced life of the machines driven by PMSMs. Therefore, it is crucial to implement a method that can lead the controller to learn the effects caused by disturbances. To this end, this paper proposes a novel approach based on the basic structure of a backpropagation neural network (BP) for adaptive real-time adjustment in motor control. Regarding the lack of explainability of BP in existing methods, the electric motor physics is embedded into the BP (BP-PHY) gradient update part to enlarge the range of stability. To overcome the shortage of a potentially unstable output of neural network (NN), the learning parameter of NN is tailored based on the stability theory and motor physics. Finally, the proposed methods are implemented into simulations and experiments. The recovery time after disturbance decreases to 51.3% and the speed drop decreases to 50.3% compared to the basic controller of the PMSM, while the control stability of the NN is ensured.