An ARTMAP neural network-based machine condition monitoring system

Document Type

Article

Publication Date

12-1-2000

Abstract

Presents a real-time neural network-based condition monitoring system for rotating mechanical equipment. At its core is an ARTMAP neural network, which continually monitors machine vibration data, as it becomes available, in an effort to pinpoint new information about the machine condition. As new faults are encountered, the network weights can be automatically and incrementally adapted to incorporate information necessary to identify the fault in the future. Describes the design, operation, and performance of the diagnostic system. The system was able to identify the presence of fault conditions with 100 percent accuracy on both lab and industrial data after minimal training; the accuracy of the fault classification (when trained to recognize multiple faults) was greater than 90 percent.

Publication Source (Journal or Book title)

Journal of Quality in Maintenance Engineering

First Page

86

Last Page

104

This document is currently not available here.

Share

COinS