Online Parameter Identification for Surface-mounted Magnet Synchronous Motors based on Adaptive RBF Neural Network

This research suggests an adaptive RBF neural network (RBFNN) identification approach to increase the convergence speed and decrease the steady-state error of online parameter identification of the surface-mounted permanent magnet synchronous motor (SPMSM). The parameters to be determined are flux linkage, inductance, and stator resistance. To start, the voltage equation is changed to take inverter nonlinearity into account. The parameters are then represented as RBFNN, from which the adaptive rules are inferred. Finally, the outcomes of the experiments support the superiority of the suggested approach.