Abstract—The paper presents an online trained NN-PI (Neural Network-Proportional Integral) speed controller employed in a SVM-DTC (Space Vector Modulation- Direct-Torque-Control) based Interior Permanent Magnet Synchronous Motor (IPMSM) drives. Back propagation (BP) algorithm is applied in training process to tune the parameters of PI speed controller. The proposed control method has been tested in simulation. Simulation results demonstrate that SVM-DTC scheme combined with the proposed NN-PI speed controller can improve performance with very fast speed response, smaller overshoot, robustness and low ripples in flux linkage and torque
 

Index Terms—neural network, back propagation algorithm, PI controller, SVM-DTC, IPMSM

Cite: Zhenyu Jia and Byeongwoo Kim, "Online Trained Neural Network-PI Speed Controller for DTC based IPMSM Drives," International Journal of Electrical and Electronic Engineering & Telecommunications, Vol. 7, No. 3, pp. 108-113, July 2018. Doi: 10.18178/ijeetc.7.3.108-113