Permanent Magnet Synchronous Motor (PMSM) is widely used in the traction applications of electric vehicles. One of the ways to increase the output efficiency of the PMSM motor is to accurately estimate parameters. The effectiveness of the Long Short-Term Memory(LSTM) based permanent magnet temperature(PMT) estimation method has been verified through some experiment with a traction motor. In this paper, the temperature of the rotor, which affects the fluctuation temperature of the permanent magnet, is estimated by deep neural network model. The temperature of the permanent magnet is caused by losses, and copper loss, iron loss, and other control losses have an effect. However, it is complicated and inaccurate to express the effect of the loss as a formula, and it is difficult to solve the complex formula again when the motor and inverter are changed. Therefore, this paper estimates the rotor temperature based on data.
Motor Permanent Magnet Temperature estimation based on Neural Network
2023-11-28
1667024 byte
Conference paper
Electronic Resource
English
Neural network adaptive control algorithm for permanent magnet spherical motor
British Library Online Contents | 2014
|