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.

The kick-start is one of the commonly used block start techniques in competitive swimming. Since swimmers push off first with the rear leg and then with the front leg during the kick-start, leg extension timings relative to the rear leg push-off would affect horizontal take-off velocity. The purpose of this study was to investigate the effects of leg extension timings during kick-start on swimming start performance. Based on the empirically obtained human body kinematic data during kick-start, the whole body was modeled as nine rigid-body segments to simulate kick-start performance for five Japanese collegiate male swimmers. Front leg extension timing was adjusted by shifting the time-series data of the front foot segment, front lower segment and front thigh segment angles were shifted 0.01 to 0.04 sec (T-0.01 to T-0.04) earlier from the original data (T0). The kick-start motion was simulated using both forward and inverse kinematics under some simplifying assumptions with geometric constraints. As a result, the horizontal take-off velocity increased for three swimmers, whereas it decreased for the other two swimmers when front leg extension timing became earlier. The vertical take-off velocity and take-off angle increased as front leg extension timing became earlier. These results indicate that front leg extension timings would either positively or negatively affect horizontal take-off velocity depending on vertical take-off velocity. Therefore, for the swimmer take-off downward, earlier front leg extension timing would allow them to generate a greater horizontal take-off velocity on kick-start.

The wear acceleration mechanism of a DLC film lubricated with MoDTC solution was investigated by using in-situ and ex-situ analytical techniques: Raman spectroscopy, SEM-EDS, ToF-SIMS, and nano-indenter. From the results, the structural change of the DLC film strongly related to the formation of Mo-carbide containing tribofilms, which were much harder than DLC used in this study. Therefore, the MoDTC-induced wear acceleration of the DLC film is caused by hard Mo-carbide containing tribofilms on a counter-face steel surface.