Donghai Liu

Construction workers of long tunnel projects are confronted with numerous safety hazards such as fall from height (FFH) and object strike due to the harsh jobsite environment, limited space, and complex working conditions. And the absence of protective guardrails is identified as the primary cause of falling accidents from height. In order to automatically detect the safety protection status of working-at-high workers, a computer vision-based recognition method for working-at-high operation safety protection according to target detection and spatial relationship was proposed in this study. Firstly, the Cycle-consistent Generative Adversarial Networks (CycleGAN) was used to preprocess construction site images to enhance the image quality. Secondly, a YOLOv8 model integrated with the coordinate attention (CA) module was established to rapidly detect targets such as workers, trolleys, and guardrails in the tunnel. Furthermore, an identification method for working-at-high operation safety protection is proposed based on the detected targets and their spatial relationships. Finally, a case study was conducted, revealing that the model achieves an accuracy and recall rate of 95.89% and 97.22%, respectively, in identifying the safety protection status of working-at-high workers. The result indicates that the proposed method provides a new way for intelligent identification of working-at-high operation safety protection and assisting on-site management personnel to prevent the risk of FFH in the tunnel.

The cross‐scale approach based on the finite element method (FEM) and discrete element method (DEM) was employed to investigate the effects of different particle shapes and stress conditions on axial deviatoric stress during wetting. A DEM modeling framework was proposed to simulate the wetting tests considering different particle shapes. The Effect of varying particle shapes on the stress‐strain and volumetric strain behavior of rockfill materials during the wetting process was investigated. Moreover, the study analyzed macroscopic characteristics such as axial and volumetric wetting deformation under triaxial test conditions. Furthermore, the mesoscopic mechanisms influencing the wetting behavior of rockfill materials were investigated using internal sample features such as Euler angles, coordination number, and contact fabric distribution. Finally, a wetting constitutive model incorporating particle shape characterization indices was proposed and validated across multiple scales. This study provides a novel approach for the accurate evaluation and safety control of the structural behavior of high rockfill dams.