Xingyu Fan

Diabetic foot ulcer (DFU) progression is associated with abnormal plantar loading and pathological tissue changes. Conventional plantar pressure systems provide mechanical information only, while electrical impedance tomography (EIT) can provide tissue conductivity information but is affected by pressure-related impedance changes at the electrode–tissue interface. This study proposes a physics-constrained three-dimensional pressure-decoupled EIT (3D-pdEIT) framework to estimate pressure-dependent electrode–tissue contact impedance and incorporate it into the EIT forward model, thereby reducing the propagation of pressure-induced boundary perturbations into reconstructed tissue conductivity. Pork tissue phantoms with agar inclusions were constructed to mimic ulcer-like regions. Boundary impedance collected under loads of 1.96–49.03 N applied at 16 electrode positions. Hertz contact mechanics and Holm’s electrical contact theory were integrated to establish a pressure-dependent contact impedance model, which was embedded into the complete electrode model through Robin boundary conditions to achieve pressure decoupling in the EIT forward problem. In addition, a Gaussian mixture model (GMM) prior was introduced to improve the contrast and boundary definition of reconstructed inclusions. The multi-frequency measurements revealed a pronounced nonlinear and load-dependent boundary impedance response, with a pressure-sensitive spectral feature identified around 1.18 M Hz. The proposed framework achieved a spatial load-localization RMSE of 1.44 mm on the independent phantom test dataset, while the load-magnitude estimation achieved an average R2 > 0.938 across the electrode array. Compared with conventional Tikhonov noser EIT reconstruction, the proposed 3D-pdEIT framework reduced pressure-induced errors and improved inclusion localization. The framework provides a physics-guided approach for estimating plantar pressure distribution and characterizing tissue conductivity abnormalities.

In this study, a surface temperature mapping method based on ultrasonic guided wave signals and a two-stream attention convolutional neural network (TSACNN) is presented to address the difficulty of reconstructing the surface temperature distribution of sliding bearing liners with high accuracy under complex working conditions. By exploiting the multimodal features of ultrasonic guided wave signals, the method combines the dual-stream structure and adaptive attention mechanism to realize the effective fusion of high-frequency and low-frequency information and feature extraction, thereby enhancing the accuracy and robustness of the reconstruction of the temperature distribution. Compared with conventional convolutional networks that rely solely on raw waveform inputs, the proposed TSACNN simultaneously utilizes both waveform and envelope features, and employs a two-stream adaptive attention module (TSAAM) to selectively focus on modality-specific information, significantly improving sensitivity to subtle temperature variations. Experimental validation demonstrates that the proposed model can effectively integrate high-frequency and low-frequency features of guided wave signals to accurately reconstruct the surface temperature distribution and locate heat sources. This method provides an effective solution for high-precision temperature monitoring in confined mechanical structures, and holds great promise for engineering applications.

Bolted connections are extensively utilized in aerospace, civil, and mechanical systems for structural assembly. However, inevitable structural vibrations can induce bolt loosening, leading to preload reduction and potential structural failure. Early-stage preload degradation, particularly during initial loosening, is often undetectable by conventional monitoring methods due to limited sensitivity and poor noise resilience. To address these limitations, this study proposes an intelligent bolt preload monitoring framework that combines electromechanical impedance (EMI) signal analysis with a parallel deep learning architecture. A multiphysics-coupled model of flange joint connections is developed to reveal the nonlinear relationships between preload degradation and changes in EMI conductance spectra, specifically resonance peak shifts and amplitude attenuation. Based on this insight, a parallel convolutional neural network (P-CNN) is designed, employing dual branches with 1 × 3 and 1 × 7 convolutional kernels to extract local and global spectral features, respectively. The architecture integrates dilated convolution to expand frequency–domain receptive fields and an enhanced SENet-based channel attention mechanism to adaptively highlight informative frequency bands. Experimental validation on a flange-bolt platform demonstrates that the proposed P-CNN achieves 99.86% classification accuracy, outperforming traditional CNNs by 20.65%. Moreover, the model maintains over 95% accuracy with only 25% of the original training samples, confirming its robustness and data efficiency. The results demonstrate the feasibility and scalability of the proposed approach for real-time, small-sample, and noise-resilient structural health monitoring of bolted connections.

The geometric homogeneity of rollers, namely the dimension and shape deviations among rollers in a roller bearing, is one of the most important manufacturing errors. However, to the best of the authors’ knowledge, no specified investigation has been carried out on the effects of the geometric homogeneity of rollers on the friction torque of tapered roller bearings (TRBs). By introducing the diameter deviation of rollers and the distribution form of rollers with a diameter deviation, this study presents a mathematic model to reveal the effects of the geometric homogeneity of rollers on the friction torque of TRBs. The geometric homogeneity of the rollers, although having only a minimal influence on the overall friction torque acting on rings, can lead to a significant increase in the slide friction force between the individual rollers and the inner raceway. By comparing the distribution form of rollers with a diameter deviation, the diameter deviation value of the roller shows a significant influence on the maximum sliding friction between the roller and the inner raceway. The impact of the geometric homogeneity of rollers on the sliding friction between the roller and the inner raceway is more pronounced under light load conditions. The above-mentioned comparisons and conclusions can be used in formulating machining error criteria for TRB rollers.