Neural-Based Remote Health Assessment and Failure Diagnostics

As industrial competition intensifies, and more emphasis is placed on increased productivity and cost reduction, the development of a means to automatically monitor and assess the health of plant equipment becomes more important. This paper presents results of our research that integrates advances in the use of feature extraction, artificial neural networks, and communication/networking techniques for remote health assessment and failure diagnostics of laboratory and industrial rotating machinery. The key features of this effort are the ability to use internet for remote diagnostics, and combined Welch’s transformation and neural networks for signature creation and analysis.