Shang Gao

As a key component of motion support, the rolling bearing is currently a popular research topic for accurate diagnosis of bearing faults and prediction of remaining bearing life. However, most existing methods still have difficulties in learning representative features from the raw data. In this paper, the Xi’an Jiaotong University (XJTU-SY) rolling bearing dataset is taken as the research object, and a deep learning technique is applied to carry out the bearing fault diagnosis research. The root mean square (RMS), kurtosis, and sum of frequency energy per unit acquisition period of the short-time Fourier transform are used as health factor indicators to divide the whole life cycle of bearings into two phases: the health phase and the fault phase. This division not only expands the bearing dataset but also improves the fault diagnosis efficiency. The Deep Convolutional Neural Networks with Wide First-layer Kernels (WDCNN) network model is improved by introducing multi-scale large convolutional kernels and Gate Recurrent Unit (GRU) networks. The bearing signals with classified health states are trained and tested, and the training and testing process is visualized, then finally the experimental validation is performed for four failure locations in the dataset. The experimental results show that the proposed network model has excellent fault diagnosis and noise immunity, and can achieve the diagnosis of bearing faults under complex working conditions, with greater diagnostic accuracy and efficiency.

In view of the phenomenon that camera imaging will appear large up close and small from afar in the eye-to-hand hand-calibration system, one hand–eye calibration is carried out. The manipulator is only suitable for grasping objects of the same height, and the calibration results cannot be applied to grasping products with variable height. Based on the study of the pinhole camera model and the rigid transformation model between coordinate systems, the introduction of the calibration height parameters, the relationship between parameters of the rigid transformation matrix between image the coordinate system and the robot coordinate system, and sampling height are established. In the experiment, firstly, through the calibration of camera parameters, the influence of camera distortion on imaging quality is eliminated, and the influence of calibration height is ignored. Then, the machine coordinate system and image coordinate system of the calibration plate at different heights are calibrated using the four-point calibration method. The parameters of the rigid transformation matrix at different heights (H) are calculated. Finally, through experimental analysis, the high linear relationship between the parameters of the rigid transformation matrix from the image coordinate system to the robot coordinate system and the calibration height is fitted. By analyzing the random error of the experiment, the linear relationship between calibration height and pixel density is further established, and the systematic error of the experimental process is deeply analyzed. The experimental results show that the hand–eye calibration system based on this linear relationship is precise and suitable for grabbing products of any height, and the positioning error is less than 0.08%.