In recent years, a lot of attention has been paid to deep learning methods in the context of vision-based construction site safety systems. However, there is still more to be done to establish the relationship between supervised construction workers and their essential personal protective equipment, like hard hats. A deep learning method combining object detection, head center localization, and simple rule-based reasoning is proposed in this article. In tests, this solution surpassed the previous methods based on the relative bounding box position of different instances and direct detection of hard hat wearers and non-wearers. Achieving MS COCO style overall AP of 67.5% compared to 66.4% and 66.3% achieved by the approaches mentioned above, with class-specific AP for hard hat non-wearers of 64.1% compared to 63.0% and 60.3%. The results show that using deep learning methods with a humanly interpretable rule-based algorithm is better suited for detecting hard hat non-wearers.

Optimization plays an important role in scientific and engineering research. This paper presents the effects of using the catenoidal shape to design the structure of a chimney cooling tower. The paper compares some geometrical variations of the catenoid with the reference existing hyperboloidal structure. It also compares internal forces, deformation and stability of the catenoidal structure. The comparison shows some predominance of the catenoid over the popular hyperboloid structure of the shell. The paper attempts to find an optimal shape of the cooling tower in order to reduce the amount of material and labor. The paper utilizes engineering tools and the designing process for chimney cooling towers.

Composite materials are a constantly evolving group of engineering materials, which has significantly changed their current, and potential role as structural materials over the past decades. Composites offer greater strength, stiffness, and less deformation to structural designers than previously available engineering materials. Resin matrix composites are widely used in the transportation, marine, aerospace, energy, and even sports industries. The manufacturing stage has a profound influence on the quality of the final product. This paper presents the production of composite materials by gravity casting in silicone moulds, using an epoxy/polyester resin matrix reinforced with wood chips and shredded glass fiber reinforced composite from recycled wind turbine blades. Some of the fabricated samples were degassed in a reduced-pressure chamber. The mechanical properties of the produced material were then examined. It was noted that the silicone moulds did not affect the resin self-degassing due to the large surface area to weight ratio, and the remaining small air bubbles had a limited effect on the mechanical properties of the samples. The filler used also played a significant role. Composites filled with crushed GFRC showed better strength properties than composites filled with wood chips. The conducted research is aimed at selecting materials for further testing with a view to their use in the manufacture of next-generation wood-based composite structural materials.