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.

A wire arc additive manufacturing system, based on cold metal transfer technology, was utilized to manufacture the Al-Mg alloy walls. ER5556 wire was used as the filler metal to deposit Al-Mg alloys layer by layer. Based on the orthogonal experiments, the process parameters of the welding current, welding speed and gas flow, as well as interlayer residence time, were adjusted to investigate the microstructure, phase composition and crystal orientation as well as material properties of Al-Mg alloyed additive. The results show that the grain size of Al-Mg alloyed additive becomes smaller with the decrease of welding current or increased welding speed. It is easier to obtain the additive parts with better grain uniformity with the increase of gas flow or interlayer residence time. The phase composition of Al-Mg alloyed additive consists of α-Al matrix and γ (Al₁₂Mg₁₇) phase. The eutectic reaction occurs during the additive manufacturing process, and the liquefying film is formed on the α-Al matrix and coated on the γ phase surface. The crystal grows preferentially along the and orientations. When the welding current is 90 A, the welding speed is 700 mm/min, the gas flow is 22.5 L/min and the interlayer residence time is 5 min, the Al-Mg alloy additive obtains the highest tensile strength. Under the optimal process parameters, the average grain size of Al-Mg alloyed additive is 25 μm, the transverse tensile strength reaches 382 MPa, the impact absorption energy is 26 J, and the corrosion current density is 3.485 × 10⁻⁶ A·cm⁻². Both tensile and impact fracture modes of Al-Mg alloyed additive are ductile fractures. From the current view, the Al-Mg alloys manufactured by WAAM-CMT have a better performance than those produced by the traditional casting process.

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.

TiCrAlN hard films based on TiN or CrN show superior properties in terms of hardness, wear resistance, and thermal stability due to the addition of alloying elements. AlCrTiN films based on AlN may have higher thermal shock properties, but the knowledge of AlCrTiN films with high Al content has been insufficient until now. In this study, two sets of AlCrTiN hard films with different Al contents of 48 at.% and 58 at.% among metal components were prepared via multi-arc ion plating so as to investigate the effect of Al content on the phase composition, hardness, and thermal shock resistance of the films. The same microstructures, morphologies, and thicknesses of the fabricated film samples were achieved by changing the combination of cathode alloy targets and adjusting the arc source current during deposition. The surface chemical composition, cross-sectional elemental distribution, microstructure, morphology, phase composition, surface hardness, film/substrate adhesion strength, and thermal shock performance of the AlCrTiN films were examined. The obtained results reveal that the two sets of AlTiCrN hard films are face-centered cubic solid solutions with a columnar fine grain structure and a preferred growth orientation of (200) crystal plane. The hardness of the AlCrTiN films can be improved up to HV2850 by properly reducing the Al content from 58 at.% to 48 at.%. Meanwhile, the film/substrate adhesion performance is strong enough in terms of critical loads greater than 200 N. Furthermore, the AlCrTiN films maintain high thermal shock resistance at 600 °C when the Al content decreases from 58 at.% to 48 at.%. The optimal composition of the AlCrTiN hard films is 25:13:15:47 (at.%), based on the consideration of hardness, adhesion, and thermal shock cycling resistance. This optimal AlCrTiN hard film can be suggested as an option for protective coatings of hot process die tools.

An easy approach is described for the preparation of ZrO₂-coated Y₂O₃ nanopowder from a solution of zirconium nitrate with commercial Y₂O₃ nanopowder. The evolution process of the ZrO₂ coating layer upon calcination, such as the phase and microstructure of the particles’ surface, was studied. Calcination of the powder at 700 °C resulted in ZrO₂-coated Y₂O₃ nanopowder. The rheological properties of the suspensions of ZrO₂-coated Y₂O₃ powders were studied. A well-dispersed suspension with a solid loading of 35.0 vol% using ZrO₂-coated Y₂O₃ nanopowder was obtained. The consolidated green body obtained by the centrifugal casting method showed improved homogeneity with a relative density of 50.2%. Transparent ceramic with high transparency and an average grain size of 1.7 µm was obtained by presintering at 1500 °C for 16 h in air, followed by post-HIP at 1550 °C for 2 h under 200 MPa pressure. The in-line transmittance at the wavelength of 1100 nm (1.0 mm thick) reached 81.4%, close to the theoretical transmittance of Y₂O₃ crystal.

In this study, we address the effect of vacuum heat treatment on the morphology of Al₂O₃-3wt.%TiO₂ coating, element diffusion behavior, coating hardness, and corrosion resistance. The pores, cracks, and non-liquefied particles on the as-heat treated coating surface of the vacuum-heat-treated coating were observed and compared with the as-sprayed coating using a scanning electron microscope. The diffusion behavior of the elements in the coating was demonstrated by using a line scanning of a cross-section of the coating. Hardness and corrosion-resistance test results were used to judge the effect of a vacuum heat treatment on the coating. The research results show that compared with atmospheric heat treatment, the vacuum heat treatment had less effect on the pores, cracks, and non-liquefied particles on the surface of the coating. However, in the absence of new oxide formation, the pores and cracks in the cross-section of the coating were significantly improved by the vacuum heat treatment. The surface hardness and corrosion resistance of the coating were significantly improved. The crack defects were eliminated, and the uniformity of TiO₂ distribution was improved, which are the main factors that improved the coating performance after vacuum heat treatment. The combination of the coating and the substrate is strengthened, and an Al₂O₃ and TiO₂ interdiffusion zone is formed when the coating undergoes vacuum heat treatment, which is the main mechanism improving the performance of the AT3 coating.