Nonlinear autoregressive moving average (NARMA-L2) controller for advanced ac motor control

In this paper, speed controllers based on artificial neural networks for vector control of AC motors are used. Tracking of the rotor speed is realized by adjusting the new weights of the network depending on the difference between the actual speed and the commanded speed. The controller is adaptive and is based on a nonlinear autoregressive moving average (NARMA-L2) algorithm. A comparative study between the proposed controllers and the conventional PI one will be presented and the advantages of the proposed solution over the conventional one will be shown. The rotor speed tracks the commanded one smoothly and rapidly, without overshoot and with very negligible steady state error. Computer simulation results are carried out to prove the claims.

[1]  Hirofumi Akagi,et al.  Instantaneous power theory and applications to power conditioning , 2007 .

[2]  Haitham Abu-Rub,et al.  Comprehensive analysis and comparative study of several sensorless control systems of asynchronous motors , 2001 .

[3]  Moleykutty George.  Artificial Intelligence Based Three-Phase Unified Power Quality Conditioner , 2007 .

[4]  H.A. Toliyat,et al.  Artificial-neural-network-based sensorless nonlinear control of induction motors , 2005, IEEE Transactions on Energy Conversion.

[5]  Snehasis Mukhopadhyay,et al.  Adaptive control using neural networks and approximate models , 1997, IEEE Trans. Neural Networks.

[6]  M. Hagan,et al.  TRAINING RECURRENT NETWORKS FOR FILTERING AND CONTROL , 1999 .

[7]  K. P. Basu,et al.  Three-Phase Shunt Active Power Filter , 2008 .

[8]  Md. Al-Amin Bhuiyan,et al.  Structural Composition Based on Diameter and Height Class Distribution of a Deforested Area of Chittagong, Bangladesh , 2005 .

[9]  M.A. Rahman.  High Efficiency IPM Motor Drives for Hybrid Electric Vehicles , 2007, 2007 Canadian Conference on Electrical and Computer Engineering.

[10]  Roger L. Schultz,et al.  Training Recurrent Neural Networks for Filtering and Control , 1999 .

[11]  H. Abu-Rub,et al.  Artificial Intelligence Sensorless Control of Induction Motor , 2007, 2007 Compatibility in Power Electronics.

[12]  B.K. Bose,et al.  Neural network based estimation of feedback signals for a vector controlled induction motor drive , 1994, Proceedings of 1994 IEEE Industry Applications Society Annual Meeting.

[13]  Moleykutty George,et al.  Speed Control of Separately Excited DC Motor , 2008 .

[14]  Bimal K. Bose,et al.  Artificial neural network applications in power electronics , 2001, IECON'01. 27th Annual Conference of the IEEE Industrial Electronics Society (Cat. No.37243).

[15]  G. Griva,et al.  Neural networks applied for induction motor speed sensorless estimation , 1995, 1995 Proceedings of the IEEE International Symposium on Industrial Electronics.

[16]  Peter Norvig,et al.  Artificial intelligence - a modern approach: the intelligent agent book , 1995, Prentice Hall series in artificial intelligence.