Abstract

Many commercial and military transport systems have fault diagnostic functions implemented to help protect the device when a severe fault occurs. However, most present systems do not contain prognostics capability which would allow operators to observe an unhealthy system component in its prefault condition. in industry applications, scheduled downtime can result in considerable cost avoidance. the next technology step is self-healing system components which observe not only potential problems but can also take steps to continue operation under abnormal conditions - whether due to long-term normal wear-and-tear or sudden combat damage. in this paper, current and voltage information using the double-layer gate drive concept is fed to intelligent networks to identify the type of fault and its location. These intelligent networks are based on unsupervised and supervised learning networks (self-organizing maps and learning vector quantization networks respectively). the proposed concept allows the reconfiguration of the electric machinery system for continued normal operation of the machine. This paper presents an intelligent health monitoring and self-healing control strategy for a multi-phase multilevel motor drive under various types of faults. © 2007 IEEE.

Department(s)

Electrical and Computer Engineering

Keywords and Phrases

Computational intelligence; Fault diagnosis; Fault prognosis; Motor drives; Power converters

International Standard Book Number (ISBN)

978-142440364-6

International Standard Serial Number (ISSN)

0197-2618

Document Type

Article - Conference proceedings

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 2024 Institute of Electrical and Electronics Engineers, All rights reserved.

Publication Date

01 Dec 2007

Download

Full Text Link

Share

 
COinS