Speed Sensorless Control with ANN-MRAS Based on Modified ACO for Induction Motor Drives

Abstract:

In the speed sensorless induction motor drives system, Model Reference Adaptive System (MRAS) is the most common strategy. It suffers from parameter sensitivity and flux pure integration problems which may cause DC drift. As a result, it leads to the deterioration of estimation at low speed. To overcome these problems, an Artificial Neural Networks (ANN) is presented as a Rotor Flux (RF) observer to replace the conventional voltage model used in RF-MRAS speed observer. Simultaneously, in order to solve the trap of local minimum value of algorithm, and enhance the ANN convergence speed, we used the modified Ant Colony Optimization (ACO) to optimize the weights and thresholds value of neural networks. The results of the simulation show that, by this method, the speed of motor can be identified accurately in different situations, and the result is reliable.

• Periodical: Applied Mechanics and Materials (Volume 705)
• Pages: 341-344
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.705.341
• Online since: December 2014
• Authors: Kai Xu, He Lin Li, Shan Chao Liu
• Keywords: Ant Colony Optimization (ACO), Artificial Neural Network (ANN), Induction Motor (IM), Model Reference Adaptive System (MRAS), Speed Identification

References

[1] J. Holtz and J. Quan, Drift and parameter compensated flux estimator for persistent zero stator frequency operation of sensorless controlled induction motors, IEEE Trans. Industry Applications, 39(4), (2003), pp.1052-1060.

DOI: 10.1109/tia.2003.813726

[2] M. Rashed, A stable back-EMF MRAS-based sensorless low speed induction motor drive insensitive to stator resistance variation, IEE Proc. Electr. Power Appl., 151(6), (2004), pp.685-693.

DOI: 10.1049/ip-epa:20040609

[3] Zhang Pengcheng, Chen Jian, Kang Yong. On-line speed recognizing with the reactive power of magnetizing current for asynchronous motor, [J]. Electric drive, 33(5), (2003), pp.12-14. (in Chinese).

[4] P. Vas, Sensorless vector and direct torque control, Oxford University Press, New York(1998).

[5] Y. Yusof , Simulation and modelling of stator flux estimator for induction motor using ANN technique, in Proceedings of National Power and Energy Conf. (PECon), (2003), pp.11-15.

[6] B. Karanayil, An implementation of a programmable cascaded low-pass filter for a rotor flux synthesizer for an induction motor drive, IEEE Trans. on Power Electron., 19(2), (2004), pp.257-263.

DOI: 10.1109/tpel.2003.823181

[7] Suman Maiti, An dadptive speed sensorless induction motor drive with artificial neural network for stability enhancement, IEEE Trans. on Industrial Informatics., 8(4), (2012), pp.757-766.

DOI: 10.1109/tii.2012.2210229

[8] T. Orlowska-Kowalska, FPGA implementation of the multilayer neural network for the speed estimation of the two-mass drive system, IEEE Trans. Ind. Informat., 7(3), (2011). p.436–445.

DOI: 10.1109/tii.2011.2158843