The 2524-T3 aluminum alloy was subjected to fatigue tests under the conditions of R = 0, 3.5% NaCl corrosion solution, and the loading cycles of 10⁶, and the S-N curve was obtained. The horizontal fatigue limit was 169 MPa, which is slightly higher than the longitudinal fatigue limit of 163 MPa. In addition, detailed microstructural analysis of the micro-morphological fatigue failure features was carried out. The influence mechanism of corrosion on the fatigue crack propagation of 2524-T3 aluminum alloy was discussed. The fatigue source characterized by cleavage and fracture mainly comes from corrosion pits, whose expansion direction is perpendicular to the principal stress direction. The stable propagation zone is characterized by strip fractures. The main feature of the fracture in the fracture zone is equiaxed dimples. The larger dimples are mixed with second-phase particles ranging in size from 1 to 5 μm. There is almost a one-to-one correspondence between the dimples and the second-phase particles. The fracture mechanism of 2524 alloy at this stage is transformed into a micro-holes connection mechanism, and the nucleation of micropores is mainly derived from the second-phase particles.

Water jet technology is widely used in various fields, in which the nozzle is an important element to form the jet. To solve the problem of low water jet operation efficiency of square nozzles, the internal flow channel structure of the nozzle of the key jet device is studied. Through the combination of computational fluid dynamics (CFD) and particle image velocimetry (PIV) experiments, the influence of main structural parameters such as the contraction angle and length-to-diameter ratio of the inner flow channel on the velocity and length of the constant-velocity core region is explored. Since the jet flow structure is a symmetrical structure along the axial direction, the model of the jet flow structure was built half of the model along the axial direction. The results show that a smaller length-to-diameter ratio and a smaller contraction angle of the nozzle result in better jet cohesion and lower dynamic pressure in the constant-velocity core area, which is more suitable for long-distance, low-pressure water jet operations.

In contemporary industrial machinery, bearings are a vital component, so the ability to diagnose bearing faults is extremely important. Current methodologies face challenges in feature extraction and perform suboptimally in environments with high noise levels. This paper proposes an enhanced, multimodal, feature-fusion-bearing fault diagnosis model. Integrating a 1DCNN-dual MLP framework with an enhanced two-way cross-attention mechanism enables in-depth feature fusion. Firstly, the raw fault time-series data undergo fast Fourier transform (FFT). Then, the original time-series data are input into a multi-layer perceptron (MLP) and a one-dimensional convolutional neural network (1DCNN) model. The frequency-domain data are then entered into the other multi-layer perceptron (MLP) model to extract deep features in both the time and frequency domains. These features are then fed into a serial bidirectional cross-attention mechanism for feature fusion. At the same time, a GCOS learning rate scheduler has been developed to automatically adjust the learning rate. Following fifteen independent experiments on the Case Western Reserve University bearing dataset, the fusion model achieved an average accuracy rate of 99.83%. Even in a high-noise environment (0 dB), the model achieved an accuracy rate of 90.66%, indicating its ability to perform well under such conditions. Its accuracy remains at 86.73%, even under 0 dB noise and variable operating conditions, fully demonstrating its exceptional robustness.