Search Results (3)

This study employed multiple machine learning and hyperparameter optimization techniques to analyze and predict the mechanical properties of self-drilling screw connections in thin-walled steel–ply–bamboo shear walls, leveraging the renewable and eco-friendly nature of bamboo to enhance structural sustainability and reduce environmental impact. The dataset, which included 249 sets of measurement data, was derived from 51 disparate connection specimens fabricated with engineered bamboo—a renewable and low-carbon construction material. Utilizing factor analysis, a ranking table recording the comprehensive score of each connection specimen was established to select the optimal connection type. Eight machine learning models were employed to analyze and predict the mechanical performance of these connection specimens. Through comparison, the most efficient model was selected, and five hyperparameter optimization algorithms were implemented to further enhance its prediction accuracy. The analysis results revealed that the Random Forest (RF) model demonstrated superior classification performance, prediction accuracy, and generalization ability, achieving approximately 61% accuracy on the test set (the highest among all models). In hyperparameter optimization, the RF model processed through Bayesian Optimization (BO) further improved its predictive accuracy to about 67%, outperforming both its non-optimized version and models optimized using the other algorithms. Considering the mechanical performance of connections within TWS composite structures, applying the BO algorithm to the RF model significantly improved the predictive accuracy. This approach enables the identification of the most suitable specimen type based on newly provided mechanical performance parameter sets, providing a data-driven pathway for sustainable bamboo–steel composite structure design. Full article

The versatility of steel, its high resistance in relation to its low mass, as well as the easily accessible technology in the context of using recyclable materials and the low negative impact on the environment represent important arguments in using thin-walled steel profiles to make structures for buildings with a low height regime. This paper presents the results of an experimental program that investigated the behavior of three types of joints in a T-shape form made of thin-walled steel profiles to make shear wall panels or truss beam floors. Due to the small dimensions of the C-profiles of 89 × 41 × 12 × 1 mm, and of the technology of their joining, manufacturers prefer the hinged connections of elements with self-drilling screws. The purpose of the research presented in this paper is to assess the maximum capacity of the joints, the elastic and post-elastic behavior until failure, and also the mechanisms failure. The types of joints analyzed are commonly used in the production of structural systems for houses. The experimental program, which consisted of testing 5 specimens for each type of joint in tension (shear on screws), showed different behavior in terms of load-displacement. The experimental, tested models were analyzed by finite element simulations in an ANSYS nonlinear static structure with 3D solid models. The materials were defined by a bilinear true stress–strain curve obtained after some experimental tensile tests of the steel. The results of the experimental tests showed that the main failure mechanism is a yielding of the holes where the screws were mounted and a shearing of the profile walls. Adding an additional screw on each side increases the capacity of the joints, but not until a yield loss is obtained. In conclusion, it is shown that the solution is suitable for a low level of loading in a static manner; however, additional studies are necessary in order to develop and verify other solutions, thus improving the strength of the connection. Full article

Timber platform-frame shear walls are characterized by high ductility and diffuse energy dissipation but limited in-plane shear resistance. A novel lightweight constructive system composed of steel columns braced with oriented strand board (OSB) panels was conceived and tested. Preliminary laboratory tests were performed to study the OSB-to-column connections with self-drilling screws. Then, the seismic response of a shear wall was determined performing a quasi-static cyclic-loading test of a full-scale specimen. Results presented in this work in terms of force-displacement capacity show that this system confers to shear walls high in-plane strength and stiffness with good ductility and dissipative capacity. Therefore, the incorporation of steel columns within OSB bracing panels results in a strong and stiff platform-frame system with high potential for low- and medium-rise buildings in seismic-prone areas. Full article