Artificial Neural Networks for Ball Bearing Remaining Useful Life Prediction Based on Acoustic Emission

In this research, the efficiency of feedforward neural network in improving the remaining use-ful life of angular contact ball bearing based on acoustic emission signals are investigated. To capture the bearing acoustic emission signals, an appropriate laboratory setup is used. Acoustic emission signal processing is carried out in the time domain. Count, mean and square mean root features are selected for RUL investigation. The results indicate that acoustic emission is a good method for bearing RUL prediction. It was shown that neural networks with Levenberg Marquardt training algorithm had the SSE error of ۷.۳۲ for the prediction of bearing remaining useful life based on the selected features.

Keywords:

Artificial intelligence , Remaining useful life , Angular contact bearing , Acoustic emission.