Abstract
ARTIFICIAL NEURAL NETWORK BASED INTELLIGENT FAULT IDENTIFICATION OF ROTATING MACHINERY
Karim Abdel-Hakam Mohamed*, Galal Ali Hassaan, Adel Abdel-Halim Hegazy
ABSTRACT
In general intelligent diagnosis is carried out when known inputs are fed into black boxes which subsequently produce outputs in accordance with machine faults. Neural networks (NN) are suitable for these tasks and have been widely researched as an artificial intelligence tool for machinery fault diagnosis. By employing such a tool, maintenance personnel need not understand or operate the internal mechanisms of a neural network. They will only be responsible for inputting the appropriate data to a neural network. The neural network will then be trained on this data so that it can diagnose faults. Artificial neural networks demonstrated to provide an effective method for fault diagnosis in rotating machinery in terms of reliability. In this paper, vibration frequency features of mechanical unbalance, angular misalignment, and mechanical looseness are discussed for rotating machinery fault diagnosis. This paper then presents an approach for rotating machinery fault diagnosis using pattern classification tool of neural networks and frequency domain vibration analysis. Finally this pattern recognition approach applied on a real world case with effective results.
[Full Text Article] [Download Certificate]