Application of artificial neural network for condition monitoring and diagnosis of rotating machinery

Abstract EN

In this paper a neural network model is created and trained through experimental setup data for investigating misalignment and unbalance.

The trained network is validated through another experimental setup data for the faults of misalignment and unbalance.

Later, this created, trained and validated model is applied to an industrial case study data.

Vibration measurements collected from Aden Oil Refinery (AOR)are fed to the trained neural network ENN software for diagnosis.

Results obtained from the ENN software agree well with that predicted by the experts in AOR for the faults of misalignment and unbalance.