Rolling bearing fault diagnosis is significant to the stable operation of rotating machinery systems. However, the fault data collected in practical engineering is seriously imbalanced, which degrades the diagnosis performance. A DRNet intelligent fault diagnosis model was proposed in this paper based on the probabilistic diffusion model to enhance fault diagnosis performance under imbalanced data. This paper utilized a probabilistic diffusion model to learn a deep semantic representation of fault data, which in turn generates high-quality fault features to balance the number of fault samples. Moreover, we utilized the deep features of fault signals to build a feature metric module that optimized the features of the generated samples. This enhances the accuracy and diversity of the generated data. Finally, the fault categories of the samples were identified using the residual network after data enhancement. The experimental results indicate that compared to other common methods, our method can more effectively fit the feature distribution of real samples resulting in generated samples with higher similarity and exhibiting good stability and accuracy when processing bearing unbalanced fault data.

In this paper, the evaporation of a single droplet (water, ethanol) levitated by ultrasonic was investigated experimentally at various environmental temperatures from 100°C to 400°C. The evaporation history of the droplets was recorded by a high-speed camera. The initial droplet diameter ranges from 0.1 mm to 1.0 mm. We calculated the surface area, volume, aspect ratio, and the equivalent-diameter of a single droplet during evaporation. The evaporation constant of each droplet was estimated, and the effects of ambient temperature, initial droplet diameter, and liquid droplet physicochemical properties on evaporation characteristics were discussed. It is found that when the ambient temperature is below the critical temperature, the higher the ambient temperature results in a higher evaporation rate; the droplet evaporation conforms to the D ² law. Under the same conditions, the lower latent heat of the droplet leads to a higher evaporation rate.

In tunnel boring projects, wear and tear in the tooling system can have significant consequences, such as decreased boring efficiency, heightened maintenance costs, and potential safety hazards. In this paper, a fault diagnosis method for TBM tooling systems based on SAV−SVDD failure location (SSFL) is proposed. The aim of this method is to detect faults caused by disk cutter wear during the boring process, which diminishes the boring efficiency and is challenging to detect during construction. This paper uses SolidWorks to create a complete three−dimensional model of the TBM hydraulic thrust system and tool system. Then, dynamic simulations are performed with Adams. This helps us understand how the load on the propulsion hydraulic cylinder changes as the TBM tunneling tool wears to different degrees during construction. The hydraulic propulsion system was modeled and simulated using AMESIM software. Utilizing the load on the hydraulic propulsion cylinder as an input signal, pressure signals from the two chambers of the hydraulic cylinder and the system’s flow signal were acquired. This enabled an in−depth exploration of the correlation between these acquired signals and the extent of the tooling system failure. Following this analysis, a collection of normal sample data and sample data representing different degrees of disk cutter abrasions was amassed for further study. Next, an SSFL network model for locating the failure area of the cutter was established. Fault sample data were used as the input, and the accuracy of the fault diagnosis model was tested. The test results show that the performance of the SSFL network model is better than that of the SAE−SVM and SVDD network models. The SSFL model achieves 90% accuracy in determining the failure area of the cutter head. The model effectively identifies the failure regions, enabling timely tool replacement to avoid decreased boring efficiency under wear conditions. The experimental findings validate the feasibility of this approach.

External vertical prestressing rebars (EVPRs) can effectively improve shear strength of concrete structures by the way of providing vertical compressive stress to the concrete and acting as stirrups. The objective of this study is to obtain a shear strength prediction model of EVPRs strengthening concrete beam without transverse reinforcement enhanced by modifying the ACI-318 and Critical Shear Crack Theory (CSCT). At the same time, this article analyzes the contribution of the strength of the shear strength, including the EVPRs as stirrups, compression zone of concrete, dowelling action, aggregate interlock and residual tensile strength. The results indicate that the shear strength prediction model can fit well with the experimental data and EVPRs can effectively enhance shear strength.

The ability to decode between subjects without the additional data recorded for training is crucial for brain-computer interface (BCI) applications. However, electroencephalogram (EEG) data have cross-session and cross-subject variability due to external factors and individual differences. Therefore cross-domain EEG signal recognition remains challenging. To solve this problem, we propose a feature relation contrastive network (FRCN) in this article. First, we use covariance matrices to align the data distribution between in source and target domains to reduce the difference. Second, we extract feature representations by the pretrained embedding network and align the correlations of the features using a nonlinear transformation. Then, we propose a source domain selection method to measure the similarity of motion-related data distributions between domains by utilizing resting-state data from different domains and the selected appropriate source domain data for fine-tuning. Finally, we propose a metric learning-based interdomain relation contrastive module (RCM) to learn multiple nonlinear distance metrics based on different levels of features simultaneously, which enables interdomain comparison learning and accurately compares the relations between samples to reduce the negative migration. For testing the target task, effective matching and similarity comparison function from multiple abstraction-level features jointly alleviates the reliance on the embedded ability to generate linearly separable features. The experimental results show that the FRCN achieves better results on the BCI Competition IV II-a and II-b dataset, and the ablation experiments validate the effectiveness of the method.