A novel method for cage whirl motion capture of high-precision bearing inspired by U-Net

To solve the problem of cage whirl motion capture and evaluation, this paper developed an efficient non-contact measurement method based on semantic segmentation technology. An encoder–decoder network whose backbone is U-Net is constructed by introducing residual learning and attention mechanism for cage motion state segmentation. A random move augmentation strategy is used to simulate the random movement of cage mass center. The network is trained with 1368 high-speed cage rotational images using the augmentation strategy. Additionally, 150 images are validation set, and 5000 images under different operating conditions are test set. A trained network is applied to the cage whirl motion capture under different operating conditions by matching the suitable parameters during the training phase. The results show that our method effectively predicts the trend of cage whirl motion, with the predicted cage whirl orbit used for the accurate analysis of cage rotational stability.