Training of a neural network controller for indirect field orientation control

This paper presents the design of an improved neural network controller for the stator current command in an indirect field oriented control system of an induction motor. This controller is superior to a previously proposed controller in that another step is added to the training of the neural network so that the controller is more stable and also the voltage feedbacks are eliminated. Also the number of neurons are reduced which helps practical implementation of the network.

[1]  S. W. Piche,et al.  Steepest descent algorithms for neural network controllers and filters , 1994, IEEE Trans. Neural Networks.

[2]  Kumpati S. Narendra,et al.  Identification and control of dynamical systems using neural networks , 1990, IEEE Trans. Neural Networks.

[3]  Toshio Fukuda,et al.  Theory and applications of neural networks for industrial control systems , 1992, IEEE Trans. Ind. Electron..

[4]  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.

[5]  Robert D. Lorenz,et al.  One-step optimal space vector PWM current regulation using a neural network , 1994, Proceedings of 1994 IEEE Industry Applications Society Annual Meeting.

[6]  J. Theocharis,et al.  Neural network observer for induction motor control , 1994, IEEE Control Systems.

[7]  R.D. Lorenz,et al.  Design and implementation of neural networks for digital current regulation of inverter drives , 1991, Conference Record of the 1991 IEEE Industry Applications Society Annual Meeting.

[8]  P. Werbos,et al.  Beyond Regression : "New Tools for Prediction and Analysis in the Behavioral Sciences , 1974 .

[9]  E. P. Nowicki,et al.  A neural network controller for indirect field orientation control , 1995, IAS '95. Conference Record of the 1995 IEEE Industry Applications Conference Thirtieth IAS Annual Meeting.