Real-time implementation of an on-line trained neural network controller for power electronics converters

K. T. Chau; C. C. Chan

Real-time implementation of an on-line trained neural network controller for power electronics converters

The Hong Kong Polytechnic University

Research output: Journal article publication › Conference article › Academic research › peer-review

Abstract

Since power electronics converters behave nonlinear, conventional control strategies such as PID are incapable of obtaining good dynamical performance. This paper addresses to implement on-line trained neural networks for power electronics converters. A PWM boost converter is used for exemplification. Real-time implementation of the neutral networks is accomplished by using a powerful digital signal processor. The converter is operated as a power amplifier and a power regulator. Both computer simulation and experimental results show that good dynamical performance can be obtained.

Original language	English
Pages (from-to)	321-327
Number of pages	7
Journal	PESC Record - IEEE Annual Power Electronics Specialists Conference
Volume	1
Publication status	Published - 1994
Event	Proceedings of the 1994 25th Annual IEEE Power Electronics Specialists Conference. Part 2 (of 2) - Taipei, Taiwan Duration: 20 Jun 1994 → 24 Jun 1994

ASJC Scopus subject areas

Modelling and Simulation
Condensed Matter Physics
Energy Engineering and Power Technology
Electrical and Electronic Engineering

Cite this

@article{2fbf16598fed4f1598ecb6356ac57fe0,

title = "Real-time implementation of an on-line trained neural network controller for power electronics converters",

abstract = "Since power electronics converters behave nonlinear, conventional control strategies such as PID are incapable of obtaining good dynamical performance. This paper addresses to implement on-line trained neural networks for power electronics converters. A PWM boost converter is used for exemplification. Real-time implementation of the neutral networks is accomplished by using a powerful digital signal processor. The converter is operated as a power amplifier and a power regulator. Both computer simulation and experimental results show that good dynamical performance can be obtained.",

author = "Chau, \{K. T.\} and Chan, \{C. C.\}",

year = "1994",

language = "English",

volume = "1",

pages = "321--327",

journal = "PESC Record - IEEE Annual Power Electronics Specialists Conference",

issn = "0275-9306",

publisher = "IEEE",

note = "Proceedings of the 1994 25th Annual IEEE Power Electronics Specialists Conference. Part 2 (of 2) ; Conference date: 20-06-1994 Through 24-06-1994",

}

TY - JOUR

T1 - Real-time implementation of an on-line trained neural network controller for power electronics converters

AU - Chau, K. T.

AU - Chan, C. C.

PY - 1994

Y1 - 1994

N2 - Since power electronics converters behave nonlinear, conventional control strategies such as PID are incapable of obtaining good dynamical performance. This paper addresses to implement on-line trained neural networks for power electronics converters. A PWM boost converter is used for exemplification. Real-time implementation of the neutral networks is accomplished by using a powerful digital signal processor. The converter is operated as a power amplifier and a power regulator. Both computer simulation and experimental results show that good dynamical performance can be obtained.

AB - Since power electronics converters behave nonlinear, conventional control strategies such as PID are incapable of obtaining good dynamical performance. This paper addresses to implement on-line trained neural networks for power electronics converters. A PWM boost converter is used for exemplification. Real-time implementation of the neutral networks is accomplished by using a powerful digital signal processor. The converter is operated as a power amplifier and a power regulator. Both computer simulation and experimental results show that good dynamical performance can be obtained.

UR - https://www.scopus.com/pages/publications/0028712713

M3 - Conference article

AN - SCOPUS:0028712713

SN - 0275-9306

VL - 1

SP - 321

EP - 327

JO - PESC Record - IEEE Annual Power Electronics Specialists Conference

JF - PESC Record - IEEE Annual Power Electronics Specialists Conference

T2 - Proceedings of the 1994 25th Annual IEEE Power Electronics Specialists Conference. Part 2 (of 2)

Y2 - 20 June 1994 through 24 June 1994

ER -

Real-time implementation of an on-line trained neural network controller for power electronics converters

Abstract

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this