The efficiency and performance of rotating machinery is of major concern in any industrial system. Proper machine condition monitoring is really crucial for identifying the health of machines. The detection and diagnosis of faults in the machinery is important in proper machine condition monitoring. In this paper the multicomponent fault diagnosis in mechanical systems is formulated as machine learning based pattern classification problem. A machine fault simulator setup with different fault conditions induced in its shaft-bearing assembly is utilised for the purpose. The machine is made to run in various good and faulty environments and the vibration signals are extracted from them using an accelerometer. The statistical features extracted from the vibration signals were used for representing the signal in the feature space. The decision tree algorithm is used for selecting the major features that contribute towards classification. Later those features are classified using regularized least squares algorithm for identifying the good and faulty shaft-bearing conditions of the machine. The results were obtained with different kernel functions and accuracies are compared. © Research India Publications.
Neethu Mohan, Ambika, P. S., S. Kumar, S., Dr. Saimurugan M., and Soman, K. P., “Multicomponent fault diagnosis using statistical features and regularized least squares”, International Journal of Applied Engineering Research, vol. 10, no. 20, pp. 19074-19080, 2015.