To address the difficulty in parameter tuning of the adaptive law in the model reference adaptive system (MRAS) for parameter identification of permanent magnet synchronous motors
a stepwise parameter identification strategy for MRAS based on a hybrid back propagation neural network and particle swarm optimization is proposed. This strategy adopts an “offline training- online identification”approach
improving the adaptive law of the conventional MRAS using a back propagation neural network and particle swarm optimization algorithm
thereby avoiding the complex parameter tuning process. On the MATLAB/Simulink simulation platform
the proposed strategy is compared and analyzed with existing stepwise MRAS identification strategies. Simulation results show that under complex operating conditions
the proposed strategy achieves higher identification accuracy
LIU Z,FENG G,HAN Y. Extended-kalman-filter-based magnet flux linkage and inductance estimation for PMSM considering magnetic saturation [C ] .2021 36th Youth Academic Annual Conference of Chinese Association of Automation (YAC).Nanchang,China:IEEE,2021:430-435.
AN X,LIU G,CHEN Q,et al. Adjustable model predictive control for IPMSM drives based on online stator inductance identification [J ] .IEEE Transactions on Industrial Electronics,2022,69(4):3368-3381.
RAFAQ M S,MOHAMMED S A Q,JUNG J W. Online multiparameter estimation for robust adaptive decoupling PI controllers of an IPMSM drive:variable regularized APAs [J ] .IEEE/ASME Transactions on Mechatronics,2019,24(3):1386-1395.
EL MERRASSI W,ABOUNADA A,RAMZI M. Performance analysis of novel robust ANN-MRAS observer applied to induction motor drive [J ] .International Journal of System Assurance Engineering and Management,2022,13(4):2011-2028.
LIU Z H,NIE J,WEI H L,et al. Switched PI control based MRAS for sensorless control of PMSM drives using fuzzy-logic-controller [J ] .IEEE Open Journal of Power Electronics,2022,3:368-381.
WANG L,ZHANG S,ZHANG C,et al. An improved deadbeat predictive current control based on parameter identification for PMSM [J ] .IEEE Transactions on Transportation Electrification,2024,10(2):2740-2753.
KAKODIA S K,DYANMINA G. Implementation of FPGA-based neural network controller for reducing speed ripple for a PMSM-driven EV using MRAS speed estimator [J ] .IEEE Transactions on Artificial Intelligence,2025:1-12.
HUANG S,ZHANG Y,SHI L,et al. An improved MRAS-based multi-parameter identification method for permanent magnet synchronous motor drives [C ] .2024 6th International Conference on Electrical Engineering and Control Technologies (CEECT).Shenzhen,China:IEEE,2024:39-43.