Skip to main content

Identification and control of induction motor stator currents using fast on-line random training of a neural network

Publication ,  Journal Article
Burton, B; Kamran, F; Harley, RG; Habetler, TG; Brooke, M; Poddar, R
Published in: Conference Record - IAS Annual Meeting (IEEE Industry Applications Society)
December 1, 1995

Artificial Neural Networks (ANNs) which have no off-line pre-training, can be trained continually on-line to identify an inverter fed induction motor and control its stator currents. Due to the small time constants of the motor circuits, the time to complete one training cycle has to be extremely small. This paper proposes and evaluates a new, fast, on-line training algorithm which is based on the method of random search training, termed the Random Weight Change (RWC) algorithm. Simulation results show that RWC training of an ANN yields performance very much the same as conventional backpropagation training. Unlike backpropagation, however, the RWC method can be implemented in mixed digital/analog hardware, and still have a sufficiently small training cycle time. The paper also proposes a VLSI implementation which one training cycle in as little as 8 μsec. Such a fast ANN can identify and control the motor currents within a few milliseconds and thus provide self-tuning of the drive while the ANN has no prior information whatsoever of the connected inverter and motor.

Duke Scholars

Published In

Conference Record - IAS Annual Meeting (IEEE Industry Applications Society)

ISSN

0197-2618

Publication Date

December 1, 1995

Volume

2

Start / End Page

1781 / 1787
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Burton, B., Kamran, F., Harley, R. G., Habetler, T. G., Brooke, M., & Poddar, R. (1995). Identification and control of induction motor stator currents using fast on-line random training of a neural network. Conference Record - IAS Annual Meeting (IEEE Industry Applications Society), 2, 1781–1787.
Burton, B., F. Kamran, R. G. Harley, T. G. Habetler, M. Brooke, and R. Poddar. “Identification and control of induction motor stator currents using fast on-line random training of a neural network.” Conference Record - IAS Annual Meeting (IEEE Industry Applications Society) 2 (December 1, 1995): 1781–87.
Burton B, Kamran F, Harley RG, Habetler TG, Brooke M, Poddar R. Identification and control of induction motor stator currents using fast on-line random training of a neural network. Conference Record - IAS Annual Meeting (IEEE Industry Applications Society). 1995 Dec 1;2:1781–7.
Burton, B., et al. “Identification and control of induction motor stator currents using fast on-line random training of a neural network.” Conference Record - IAS Annual Meeting (IEEE Industry Applications Society), vol. 2, Dec. 1995, pp. 1781–87.
Burton B, Kamran F, Harley RG, Habetler TG, Brooke M, Poddar R. Identification and control of induction motor stator currents using fast on-line random training of a neural network. Conference Record - IAS Annual Meeting (IEEE Industry Applications Society). 1995 Dec 1;2:1781–1787.

Published In

Conference Record - IAS Annual Meeting (IEEE Industry Applications Society)

ISSN

0197-2618

Publication Date

December 1, 1995

Volume

2

Start / End Page

1781 / 1787