Nonlinearity Estimation and Compensation for Accurate PMSM Modeling and Voltage Prediction

For permanent magnet synchronous machine (PMSM), the machine model is critical to predict the operating states for motor control, which, however, can be greatly affected by system nonlinearities. Hence, this paper investigates accurate machine modeling for control and parameter estimation. In the proposed approach, the PMSM model with saturated inductances is used as the base model, and this paper investigates modeling and compensation of the offsets to the base model due to system nonlinearities such as saturation and core loss effects for accurate machine modeling and voltage prediction. Specifically, the offsets to the base model are modeled using nonlinear functions with variable coefficients to compensate saturation and core loss effect, which can achieve better accuracy without changing the model structure. A differential estimation model is derived to estimate the model coefficients from a small amount of measurements with simplified procedure. Moreover, the model offset calculation is both computation and memory efficient with simplified implementation. The contribution is to improve the machine model accuracy and achieve precise voltage prediction for practical applications. Experiments, comparisons and the application to temperature estimation are conducted on a test interior PMSM to validate the proposed approach.