Open AccessAn Improved PMSM Drive Architecture Based on BFO and Neural Network
Author(s) -
Aymen Flah,
Lassâad Sbita
Publication year - 2013
Publication title -
international journal of advanced robotic systems
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.394
H-Index - 46
eISSN - 1729-8814
pISSN - 1729-8806
DOI - 10.5772/53011
Subject(s) - computer science , robustness (evolution) , control theory (sociology) , artificial neural network , vector control , electronic speed control , stator , matlab , permanent magnet synchronous motor , control engineering , torque , voltage , control (management) , induction motor , artificial intelligence , engineering , mechanical engineering , biochemistry , chemistry , electrical engineering , gene , operating system , physics , thermodynamics
In this paper, an improved robust vector control strategy is designed to drive the Permanent magnet synchronous motor in a wide speed range mode. The designed control method guarantees the precision and robustness of speed regulation performance by using recurrent neural network architecture. The stator current controller parameter tuning problems, which characterize this control strategy, are resolved using a bacterial foraging optimization algorithm to find the optimal parameters of the current controllers used. A field weakening control algorithm generates an adaptive magnetizing current command to achieve the desired high speed mode. The robustness and effectiveness of the global control scheme are verified through computer simulations established under a Matlab-Simulink environment