Abstract
Bearings are one of the crucial components of any machine having rotary parts. They are employed to support and ensure smooth operations of the shafts in the rotary machinery. Therefore, any fault in the bearings can lead to a decline in the level of production and equipment. For this reason, it is important to monitor the bearing health. This paper presents a signal analysis technique for machine health monitoring using the Hilbert-Huang Transform (HHT). HHT is a time domain approach which extracts instantaneous frequency data from a signal by decomposing the signal into Intrinsic Mode Functions (IMF) using the Empirical Mode Decomposition (EMD). The Least Absolute Shrinkage and Selection Operator (LASSO) is used as feature ranking method which is used to improve the prediction accuracy by reducing input data to machine learning model by aiding to select only a subset of the feature vector rather than using all of the features. In the present work, training and tenfold cross-validation accuracy or two classifiers have been compared. The comparative analysis presented in this paper reveals that the utilization of LASSO as a feature ranking method shows a substantial decrease in the data to be handled and improving the diagnosis accuracy.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have