Rotor Time Constant Identification Approaches Based on Back-Propagation Neural Network for Indirect Vector Controlled Induction Machine

Nowadays, indirect field oriented control (IFOC) is a promising induction machine control method which leads to excellent motor dynamic performances. It is well known that in this IFOC scheme, the induction machine parameters change widely during the operation of the drive especially the value of rotor time constant which varies with rotor temperature and flux level of the machine. Therefore, the quality of the drive system decreases if no means for compensation or identification is applied. This paper deals with rotor time constant identification for vector controlled induction motor based on measurement of the stator voltages, currents and speed by applying the back-propagation neural networks approach in order to implement a robust control law for industrial application. A convenient formulation is in order to compute physical parameters of the machine. The back-propagation learning process algorithm is briefly presented and tested with different configuration of motor induction. Verification of the validity and feasibility of the technique is obtained from simulation results.

[1]  S. Mayaleh,et al.  On-line estimation of rotor-time constant of an induction motor using recurrent neural networks , 1998, COM.P.EL.98. Record 6th Workshop on Computer in Power Electronics (Cat. No.98TH8358).

[2]  S. Mayaleh,et al.  On-line estimation of rotor resistance of an induction motor using recurrent neural networks , 1998 .

[3]  Scott D. Sudhoff,et al.  Analysis of Electric Machinery and Drive Systems , 1995 .

[4]  David Leggate,et al.  Indirect field-oriented control of an induction motor in the field-weakening region , 1992 .

[5]  I. Kioskeridis,et al.  Thermal and slip effects on rotor time constant in vector controlled induction motor drives , 2006, IEEE Transactions on Power Electronics.

[6]  Chih-Hung Chang,et al.  The learning problem of multi-layer neural networks , 2013, Neural Networks.

[7]  Mohamed Benbouzid,et al.  A Fuzzy Method for Rotor Time Constant Estimation for High-Performance Induction Motor Vector Control , 2003 .

[8]  I A Basheer,et al.  Artificial neural networks: fundamentals, computing, design, and application. , 2000, Journal of microbiological methods.

[9]  Leon M. Tolbert,et al.  An online rotor time constant estimator for induction machine , 2007, IEEE International Conference on Electric Machines and Drives, 2005..

[10]  P. C. Sen,et al.  Decoupling control of induction motor drives , 1988 .

[11]  Donald W. Novotny,et al.  The Influence of Motor Parameter Deviations in Feedforward Field Orientation Drive Systems , 1985, IEEE Transactions on Industry Applications.

[12]  Wenzhong Gao,et al.  A simple model-based online rotor time constant estimator for an induction machine , 2004 .

[13]  G. A. Capolino,et al.  Recursive Least Squares Rotor Time Constant Identification for Vector Controlled lnduction Machine , 1992 .

[14]  Faa-Jeng Lin,et al.  A high-performance induction motor drive with on-line rotor time-constant estimation , 1997 .

[15]  R. Krishnan,et al.  Electric Motor Drives: Modeling, Analysis, and Control , 2001 .

[16]  A. Ba-razzouk,et al.  A neural networks based field oriented control scheme for induction motors , 1997, IAS '97. Conference Record of the 1997 IEEE Industry Applications Conference Thirty-Second IAS Annual Meeting.