An ARTMAP neural network‐based machine condition monitoring system
- 1 June 2000
- journal article
- Published by Emerald Publishing in Journal of Quality in Maintenance Engineering
- Vol. 6 (2) , 86-105
- https://doi.org/10.1108/13552510010328095
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.Keywords
This publication has 14 references indexed in Scilit:
- Neural-network based fault diagnosis of hydraulic forging presses in ChinaInternational Journal of Production Research, 1995
- Incipient multiple fault diagnosis in real time with application to large-scale systemsIEEE Transactions on Nuclear Science, 1994
- A neural network approach for identification and fault diagnosis on dynamic systemsIEEE Transactions on Instrumentation and Measurement, 1994
- An integrated neural network/expert system approach for fault diagnosisComputers & Chemical Engineering, 1993
- Machine fault classification: a neural network approachInternational Journal of Production Research, 1992
- ARTMAP: Supervised real-time learning and classification of nonstationary data by a self-organizing neural networkNeural Networks, 1991
- Process fault detection and diagnosis using neural networks—I. steady-state processesComputers & Chemical Engineering, 1990
- Adaptive networks for fault diagnosis and process controlComputers & Chemical Engineering, 1990
- Neural network models for pattern recognition and associative memoryNeural Networks, 1989
- ART 2: self-organization of stable category recognition codes for analog input patternsApplied Optics, 1987