Condition-based predictive maintenance using neural networks
Abstract
In this study, a motor condition diagnostic was achieved through the implementation of an Artificial Neural Network, successfully applying neural network into a predictive maintenance system. Electrical DC motors were monitored to obtain data to train the ANN. Out of these monitoring, vibration signatures were used as the input layer, and the motor condition was used as the expert training information. The main objectives were to apply neural networks to a condition based predictive maintenance, analyze how different neural configurations respond to the problem exposed and analyze pros and cons of the use of neural networks in this field.
Subject Area
Computer science|Artificial intelligence|Mechanical engineering
Recommended Citation
De La Fuente, Rafael, "Condition-based predictive maintenance using neural networks" (2003). ETD Collection for University of Texas, El Paso. AAIEP10535.
https://scholarworks.utep.edu/dissertations/AAIEP10535