PROJECT TITLE :

Bearing fault classification using ANN-based Hilbert footprint analysis

ABSTRACT:

Ball bearings are considered as a vital part in numerous mechanical systems. Vibration signal analysis is very effective technique for finding bearing fault. Accelerometers are used to capture the multi-part vibration signal generated in the machine when it's in use. Varied ways primarily based on empirical mode decomposition (EMD) have been used for ball bearing fault diagnosis. EMD technique typically suffered from the boundary distortion of intrinsic mode operate. Classification of ball bearing fault is one amongst the difficult tasks in the sector of mechanical systems. Various classification schemes like support vector machine (SVM), K-means that clustering, extreme learning machine (ELM) have been used for the classification of ball bearing fault. In this study, footprint analysis of Hilbert transform together with the neural network has been in deep trouble ball bearing fault analysis. A comparative analysis of the proposed analysis study has been done with on the market ways like SVM and ELM. A high fault classification accuracy has been achieved using the proposed method for detection of ball bearing fault.