Skip to main content

A fast on-line neural-network training algorithm for a rectifier regulator

Publication ,  Journal Article
Kamran, F; Harley, RG; Burton, B; Habetler, TG; Brooke, MA
Published in: IEEE Transactions on Power Electronics
December 1, 1998

This paper addresses the problem of deadbeat control in fully controlled high-power-factor rectifiers. Improved deadbeat control can be achieved through the use of neural-network-based predictors for the input-current reference to the rectifier. In this application, on-line training is absolutely required. In order to achieve sufficiently fast on-line training, a new random-search algorithm is presented and evaluated. Simulation results show that this type of network training yields equivalent performance to standard backpropagation training. Unlike backpropagation, however, the random weight change (RWC) method can be implemented in mixed digital/analog hardware for this application. The paper proposes a very large-scale integration (VLSI) implementation which achieves a training epoch as low as 8 μs.

Duke Scholars

Published In

IEEE Transactions on Power Electronics

DOI

ISSN

0885-8993

Publication Date

December 1, 1998

Volume

13

Issue

2

Start / End Page

366 / 371

Related Subject Headings

  • Electrical & Electronic Engineering
  • 4009 Electronics, sensors and digital hardware
  • 4008 Electrical engineering
  • 0906 Electrical and Electronic Engineering
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Kamran, F., Harley, R. G., Burton, B., Habetler, T. G., & Brooke, M. A. (1998). A fast on-line neural-network training algorithm for a rectifier regulator. IEEE Transactions on Power Electronics, 13(2), 366–371. https://doi.org/10.1109/63.662857
Kamran, F., R. G. Harley, B. Burton, T. G. Habetler, and M. A. Brooke. “A fast on-line neural-network training algorithm for a rectifier regulator.” IEEE Transactions on Power Electronics 13, no. 2 (December 1, 1998): 366–71. https://doi.org/10.1109/63.662857.
Kamran F, Harley RG, Burton B, Habetler TG, Brooke MA. A fast on-line neural-network training algorithm for a rectifier regulator. IEEE Transactions on Power Electronics. 1998 Dec 1;13(2):366–71.
Kamran, F., et al. “A fast on-line neural-network training algorithm for a rectifier regulator.” IEEE Transactions on Power Electronics, vol. 13, no. 2, Dec. 1998, pp. 366–71. Scopus, doi:10.1109/63.662857.
Kamran F, Harley RG, Burton B, Habetler TG, Brooke MA. A fast on-line neural-network training algorithm for a rectifier regulator. IEEE Transactions on Power Electronics. 1998 Dec 1;13(2):366–371.

Published In

IEEE Transactions on Power Electronics

DOI

ISSN

0885-8993

Publication Date

December 1, 1998

Volume

13

Issue

2

Start / End Page

366 / 371

Related Subject Headings

  • Electrical & Electronic Engineering
  • 4009 Electronics, sensors and digital hardware
  • 4008 Electrical engineering
  • 0906 Electrical and Electronic Engineering