Machine equipment usually comprises many mechanical elements that can fail because of functional deterioration and friction. For tribo-elements like plane bearings, it is extremely important to diagnose the abnormal conditions and prevent such parts from breakdown caused by wear. However, diagnosing tribo-elements requires expensive diagnostic equipment and expertise. This study aims to propose a cost- and time- effective system that detect the signs of breakdown during equipment operation by using machine learning to identify abnormalities. We conducted wear tests in contaminated oil and used multiple sensors to collect data regarding the friction force, the electrical contact resistance, the acoustic emission (AE) signal, and vibration. An appropriate learning sample was selected using k-fold cross-validation. The electrical contact resistance was found to contribute relatively little to the detection of abnormalities, whereas the friction coefficient contributed greatly. Furthermore, the AE signal and the vibration detected local changes on the sliding surface. Consequently, we found that machine learning can judge whether monitoring data are normal or abnormal.
展开▼
