<![CDATA[Rolling bearings are a common machine element found in rotary machines. The components in the rolling bearing such as the inner race, outer race, rolling element, and cage are the parts that are often damaged. Traditionally spectrum analysis is used to diagnose bearing defects. However, spectrum analysis is not effectively applied to bearings with early defects because the vibration signal generated is dominated by frequency components from other machine elements, so the frequency of bearing defects cannot be observed. This study proposes an alternative method of detecting bearing defects based on vibration signals using machine learning with a decision tree algorithm. This method is more effective than the spectrum analysis method because machine learning is based on feature extraction and pattern recognition of vibration signal data, therefore, providing classification results directly without further analysis. Vibration signals were recorded using an accelerometer mounted on a bearing housing on a test rig. Nine-time domain statistical parameters and six frequency domain statistical parameters were extracted from the vibration signal and then used as input for decision trees. The results show that the decision trees algorithm gives an accuracy of 94.4% for classifying three rolling bearing conditions using the input of 6 selected frequency domain statistical parameters.]]>
Copyrights © 2023
