Simulation Analysis of Dynamic Characteristics of AC Motor Based on BP Neural Network Algorithm

The difficulty of traditional AC speed regulation has been hindering the development of AC motors, and vector control technology can make AC motors obtain the control characteristics of DC motors. Based on this, this paper establishes the voltage output characteristic model of AC motor dynamic system using BP neural network optimized by genetic algorithm, and trains some measured data as training samples of BP neural network optimized by genetic algorithm. The research shows that the neural network algorithm is used to estimate the rotational speed, and a high-speed and high-precision control system without speed sensor based on vector control is realized. The maximum synchronization error of the AC motor at start-up is reduced by 78.77%, and the maximum synchronization error is reduced by 20.88% in the case of sudden change in speed. The results show that compared with the traditional controller, the neural network controller has better adaptability and robustness to the model and environment, and effectively improves the control result of the system and achieves the expected purpose.