1. Classification of Ball Bearing Faults Using Vibro-Acoustic Sensor Data Fusion.
- Author
-
Gunerkar, R.S. and Jalan, A.K.
- Subjects
- *
BALL bearings , *MULTISENSOR data fusion , *ACOUSTIC transducers , *SIGNAL processing , *DETECTORS , *FAULT diagnosis , *ACOUSTIC vibrations , *FEATURE extraction - Abstract
This paper presents the novel technique for fault diagnosis of bearing by fusion of two different sensors: Vibration based and acoustic emission-based sensor. The diagnosis process involves the following steps: Data Acquisition and signal processing, Feature extraction, Classification of features, High-level data fusion and Decision making. Experiments are carried out upon test bearings with a fusion of sensors to obtain signals in time domain. Then, signal indicators for each signal have been calculated. Classifier called K-nearest neighbor (KNN) has been used for classification of fault conditions. Then, high-level sensor fusion was carried out to gain useful data for fault classification. The decision-making step allows understanding that vibration-based sensors are helpful in detecting inner race and outer race defect whereas the acoustic-based sensor is more useful for ball defects detection. These studies based on fusion helps to detect all the faults of rolling bearing at an early stage. [ABSTRACT FROM AUTHOR]
- Published
- 2019
- Full Text
- View/download PDF