With the rapid development of smart manufacturing, data-driven deep learning (DL) methods are widely used for bearing fault diagnosis. Aiming at the problem of model training crashes when data are imbalanced and the difficulty of traditional signal analysis methods in effectively extracting fault features, this paper proposes an intelligent fault diagnosis method of rolling bearings based on Gramian Angular Difference Field (GADF) and Improved Dual Attention Residual Network (IDARN). The original vibration signals are encoded as 2D-GADF feature images for network input; the residual structures will incorporate dual attention mechanism to enhance the integration ability of the features, while the group normalization (GN) method is introduced to overcome the bias caused by data discrepancies; and then the model is trained to complete the classification of faults. In order to verify the superiority of the proposed method, the data obtained from Case Western Reserve University (CWRU) bearing data and bearing fault experimental equipment were compared with other popular DL methods, and the proposed model performed optimally. The method eventually achieved an average identification accuracy of 99.2% and 97.9% on two different types of datasets, respectively.

To address the problems of existing methods that struggle to effectively extract fault features and unstable model training using unbalanced data, this paper proposes a new fault diagnosis method for rolling bearings based on a Markov Transition Field (MTF) and Mixed Attention Residual Network (MARN). The acquired vibration signals are transformed into two-dimensional MTF feature images as network inputs to avoid the loss of the original signal information, while retaining the temporal correlation; then, the mixed attention mechanism is inserted into the residual structure to enhance the feature extraction capability, and finally, the network is trained and outputs diagnostic results. In order to validate the feasibility of the MARN, other popular deep learning (DL) methods are compared on balanced and unbalanced datasets divided by a CWRU fault bearing dataset, and the proposed method results in superior performance. Ultimately, the proposed method achieves an average recognition accuracy of 99.5% and 99.2% under the two categories of divided datasets, respectively.

To study the variation law of static tensile properties and damage mechanism of fiber metal laminates, this paper conducted static tensile tests on six types of GLARE specimens. During the testing process, the full-field strain data of the specimen were captured using Digital Image Correlation technology. A comparative analysis was conducted on the elastic modulus, tensile strength, stress-strain curve, and Poisson's ratio change curve. The fracture morphology of the specimen, strain cloud map before final fracture, and the process of strain difference formation were compared and analyzed. The results show that the bridging effect of fibers needs to be properly considered when using the hybrid model method to predict the tensile strength of the ±45°fiber-metal laminates. The role of the prepreg layer in the GLARE sample gradually increases after the metal material yields. For the same type of prepreg, the damage forms in different layers of the board are not exactly the same. Using the DIC method is helpful to study the damage process and boundary effects inside the fiber metal laminate.