Share Email Print

Proceedings Paper

System for intelligent machine fault analysis
Author(s): Alok Sarwal; Dragan Filipovic
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

We present a system for intelligent machine fault detection and analysis. This system examines the signals in real-time, determines the quality of the signature for the entire set of signals and evaluates the error states of these signal combinations or signatures. This approach of continually evaluating quality of signals allows for predictive maintenance of the manufacturing system. The signals from the manufacturing system are obtained in a standard, optically isolated interface, the signals into this Remote Observation Manufacturing Equipment (ROME) system is processed and evaluated in real-time and history of these signals is stored. This system allows for the monitoring of signals in a continuous manner and these signals are recorded till a fault occurs. The graphical user interface provides user visualization control of the full family of signals at various time instants. These analog and digital signals are synchronized with the color images from two cameras and can be viewed with this GUI. The user can review both error and normal condition state using this interface.

Paper Details

Date Published: 11 November 2004
PDF: 7 pages
Proc. SPIE 5605, Intelligent Systems in Design and Manufacturing V, (11 November 2004); doi: 10.1117/12.580746
Show Author Affiliations
Alok Sarwal, PercepTek, Inc. (United States)
Dragan Filipovic, Kraft Foods (United States)

Published in SPIE Proceedings Vol. 5605:
Intelligent Systems in Design and Manufacturing V
Bhaskaran Gopalakrishnan, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?