Recognition of safety helmets wearing by construction workers is a common target detection topic in applications of deep learning-based image processing. This paper provides a study of an enhanced YOLOv5-based method, in which the challenges caused by complicated construction environment backgrounds, dense targets, and the irregular shape of safety helmets are addressed. In a trunk network, feature extraction is more based on the target shape by using the Deformable Convolution Net instead of the conventional convolution; in the Neck, a Convolutional Block Attention Module is introduced to weaken feature extraction of complex backgrounds by giving weights to enhance the characterization ability of target features; and the original network's Generalized Intersection over Union Loss is replaced by Distance Intersection over Union Loss to overcome the problem of erroneous location when the population is dense. The dataset for the training network is created by mixing open-source datasets with autonomous collecting to evaluate the effectiveness of the algorithm. We observed that the improved model has a detection accuracy of 91.6%, up 2.3% over the original network model, and a detection speed of 29 frames per second, which is compliant with most security cameras' capture frame rate.

Planetary gear transmission is widely used in roadhead, crane and other transmission equipment, its reliability and stability are related to the service life and work efficiency of equipment, but the current research on planetary gear transmission device is not comprehensive, lack of accurate analysis of gear meshing process load. Therefore, in this paper, ANSYS software as a platform, through the construction of dynamics module, to solve the gear teeth surface, gear teeth root and gear teeth tip stress analysis and deformation and displacement, the finite element analysis. The research results provide necessary technical support for the design and production of planetary gear transmission. Aims: Through finite element analysis of planetary gear transmission, the dynamic parameters of planetary gear transmission are solved, and the reliability and stability of planetary gear transmission equipment are improved. Study Design: By constructing the dynamics module of planetary gear, the stress analysis, deformation and displacement of gear tooth surface, gear tooth root and gear tooth top are solved, and the finite element analysis is carried out. Place and Duration of Study: North China University of Water Resources and Electric Power, from March to July 2022. Methodology: The finite element analysis was carried out on the model of planetary gear transmission mechanism, and the model was established and simplified by using SolidWorks software. The modal analysis and dynamic analysis were carried out by using ANSYS software, and the meshes were divided and constraints were added. Finally, the parameters such as stress, strain and displacement of the meshing position were solved. Results: The result of model meshes is 357575 units and 204871 nodes. The algorithm has 219 iterations and 15 convergence points. The experimental results show that there is a meshing position with the worst contact fatigue strength in the contact area between the outer ring gear and the planetary gear tooth surface. At this position, the contact stress value of the tooth surface is 22626Pa. Conclusion: In this paper, the planetary gear device is modeled by SolidWorks software, and the finite element analysis is carried out by ANSYS software to obtain the stress and strain parameters in the transmission process of the device, as well as the worst meshing point of the gear, the most vulnerable point of fatigue and other dangerous points. It lays a certain technical foundation for the optimization and improvement of gear and the design and production of planetary gear transmission device.