Abstract
There are many production robots used at car manufacturing plants, and each of them uses several reducers. A breakdown of one of these reducers may cause a huge loss due to the stop of all production lines. Therefore, the condition based maintenance to predict failures by predetermined thresholds of average and standard deviation is being currently used. In this study, we propose a new failure prediction method using probability density function and noise removals to improve the accuracy of prediction. Evaluations of prototypes showed much better results and its performance was applicable to the actual production lines.
