Sensorless PMSM Speed Control Based on NN Adaptive Observer
The AC motor control by neural networks includes the reconstruction errors in a certain degree, which can cause the non-convergence in the control results. To learn the complete system dynamics of the sensorless PMSM, a neural network adaptive speed control strategy is proposed to eliminate the NN reconstruction errors. A robust modification term, which is a function of estimation error and an additional tunable parameter, is introduced to guarantee the asymptotic stability of the speed estimation. A rotor-flux-oriented vector control is employed as the basic control strategy for the sensorless PMSM drive system. The simulation results demonstrated the validity and feasibility of the proposed control strategy.
KeywordsNeural network adaptive speed control Permanent magnet synchronous motor (PMSM) NN reconstruction error Robust modification term Speed estimation
Unable to display preview. Download preview PDF.
- 1.Schroedl, M.: An improved position estimator for sensorless control permanent magnet synchronous motor. In: EPE 1991, Florence, Italy, vol. 3, pp. 418–423 (1991)Google Scholar
- 10.Wang, L.M., Li, X.B.: Position sensorless control for PMLSM using Elman neural network. Rec. IEEE IAS Annu. Meeting 4, 1–4 (2009)Google Scholar
- 11.Shady, M.G., Damian, G., John, W.F.: Stator current model reference adaptive systems speed estimator for regenerating-mode low-speed operation of sensorless induction motor drives. IET Electr. Power Appl. 7(7), 597–606 (2012)Google Scholar
- 12.Jagannathan, S.: Neural network control of nonlinear discrete-time systems. CRC Press (2006)Google Scholar
- 13.Dierks, T., Thumati, B.T., Jagannathan, S.: Adaptive dynamic programming based optimal control of unknown affine nonlinear discrete-time systems. In: Proceedings of the IEEE Inter. J. Con. Neu. Net. (2009)Google Scholar