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

Abstract

In safety-and precision-critical control for permanent magnet synchronous motors (PMSMs), the 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 learn the effect caused by disturbances. To this end, this paper proposes a novel approach based on the basic structure of a backpropagation neural network (BPNN) for adaptive real-time adjustment in motor control. Regarding the lack of explainability of BPNN, the electric motor physics is embedded into BPNN (BP-PHY) gradient update part to enlarge the range of stability. To overcome the shortage of a potential unstable output of neural network (NN), the learning parameter of NN is tailored based on stability theory and motor physics. Finally, the proposed methods are implemented into simulations and experiments. The recovery speed after disturbance increased to more than three times compared to the basic controller of PMSM, while the control stability of the NN is ensured.