Stability Study of Electronic Capacitor-Less Drive System for Permanent Magnet Synchronous Motor Based on BP Neural Network

In this paper, the control of stabilizing bus voltage and increasing system reliability of electrolytic capacitor-less variable frequency speed control system is investigated. The problems of power coupling and low reliability of electroless capacitor inverter drive under conventional double closed-loop vector control are discussed. By analyzing the DC bus voltage stability, the use of BP neural network PI control in the speed loop is proposed in order to improve the reliability of the motor under speed variation. The proposed method reduces the sensitivity to speed changes by changing the controller parameters according to the speed given and the feedback value, thus preventing the bus voltage overshoot. A simulation model and an experimental platform are built to verify the feasibility of the control strategy of the electrolytic capacitor-less variable frequency speed control system, and it is proved that the proposed control strategy can effectively improve the reliability of the system.