The objective of this study is to accurately, expeditiously, and efficiently identify the wear state of milling cutters. To this end, a state identification method is proposed that combines continuous wavelet transform and an improved MobileViT lightweight network. The methodology involves the transformation of the cutting force signal during the milling cutter cutting process into a time–frequency image by continuous wavelet transform. This is followed by the introduction of a Contextual Transformer module after layer 1 and the embedding of a Global Attention Mechanism module after layer 2 of the MobileViT network structure. These modifications are intended to enhance visual representation capability, reduce information loss, and improve the interaction between global features. The result is an improvement in the overall performance of the model. The improved MobileViT network model was shown to enhance accuracy, precision, recall, and F1 score by 1.58%, 1.23%, 1.92%, and 1.57%, respectively, in comparison with the original MobileViT. The experimental results demonstrate that the proposed model in this study exhibits a substantial advantage in terms of memory occupation and prediction accuracy in comparison to models such as VGG16, ResNet18, and Pool Former. This study proposes an efficient identification method for milling cutter wear state identification, which can identify the tool wear state in near real-time. The proposed method has potential applications in the field of industrial production.

In this paper, three types of air guide vanes are designed: direct-type, L-type, and logarithmic spiral type, respectively. ANSYS-FLUENT 20.0 is used to numerically simulate the internal flow field of turbo air classifier by novel different structures. The numerical results show that the guide vane structures have a good effect on the flow field stability of the annular function zone in the classifying chamber. The distribution of tangential velocity and radial velocity verified the logarithmic spiral guide vane, and makes the airflow flow along the rotor cage circumferentially uniformly. In addition, the turbulent dissipation rate and energy loss decreases in the rotor cage region, which also shows that the guide vane is beneficial to improve classification performance. The tromp curve of the numerical simulation shows that the logarithmic spiral guide vane reduced the cutting size by 6.3% and 23.7% at two different process parameters, and is obviously better than other guide vane structures in improving the classification sharpness index (K). Finally, the reliability of numerical simulation is verified by material experiment. The research results have certain theoretical significance and guidance for the structural design of the guide vanes of the turbo air classifier.

Fracturing pumpheads are typical pressure vessels that experience frequent fatigue failure under the effect of notches in their cross-bore. To enhance the fatigue life of fracturing pumpheads, the study of the notch effect is indispensable and important to establish a reliable mathematical model to predict their fatigue life. In the present paper, two novel fatigue life prediction models are proposed for notched specimens. In these models, two new geometric fatigue failure regions are defined to improve the weight function. Finally, the elaborated novel stress-field intensity approach was applied to three different types of notched specimens. Experiment results indicate that the new SFI approach achieves 47.82%, 39.48%, and 31.85% higher prediction accuracy than the traditional SFI approach, respectively. It was found that the modified SFI approach provided better predictions than the traditional SFI approach and the TCD method. The II-th novel SFI approach had the highest accuracy, and the I-th novel SFI approach was more suitable for sharply notched specimens.

Flange bolts are vital fasteners in civil, mechanical, and aerospace structures, where preload stability directly affects overall safety. Conventional methods for bolt loosening detection often suffer from missed detections, weak feature representation, and insufficient cross-scale fusion under complex backgrounds. This paper presents an integrated detection and angle estimation framework using a lightweight deep learning detection network. A MobileViT backbone is employed to balance local texture with global context. In the spatial pyramid pooling stage, large separable convolutional kernels are combined with a channel and spatial attention mechanism to highlight discriminative features while suppressing noise. Together with content-aware upsampling and bidirectional multi-scale feature fusion, the network achieves high accuracy in detecting small and low-contrast targets while maintaining real-time performance. For angle estimation, the framework adopts an efficient training-free pipeline consisting of oriented FAST and rotated BRIEF feature detection, approximate nearest neighbor matching, and robust sample consensus fitting. This approach reliably removes false correspondences and extracts stable rotation components, maintaining success rates between 85% and 93% with an average error close to one degree, even under reflection, blur, or moderate viewpoint changes. Experimental validation demonstrates strong stability in detection and angular estimation under varying illumination and texture conditions, with a favorable balance between computational efficiency and practical applicability. This study provides a practical, intelligent, and deployable solution for bolt loosening detection, supporting the safe operation of large-scale equipment and infrastructure.

In laser crack repair processes, laser parameters have significant influence on repair quality. Improper combination of laser process parameters may result in defects—such as porosity, ablation, and coarse grain size—in remelted zones. A trans-scale computational model is established by combining crystal plasticity finite elements and variable-node finite elements. The influence of microstructure characteristics such as grain size and porosity of the repair layer on the cumulative plastic slip (CPS) on the dominant slip system at the meso-scale and the J-integral at the macro-scale is studied to explore the effect of laser process parameters on repair quality. The results show that when the laser power is 1800 W and the heating time is 0.5 s, the grain size and porosity of the repaired specimen are the smallest. The J-integral of the repaired specimen is more than 8% smaller than that of the unrepaired specimen and about 3% smaller than that of the repaired specimen, with a laser power of 2000 W and a heating time of 1 s. Pores increase the CPS of the crystal around the pores, especially when a pore have sharp corners. Selecting appropriate laser process parameters can not only refine grain size but also reduce the volume fraction of pores and thus reduce the J-integral and eventually improve repair quality of repaired specimens. The study investigates the relationship of process parameter–microstructure–repair quality in the laser repair process and provides a method for studying the mechanical behavior of materials at macro and micro scales.