The lateraltorsional buckling (LTB) performance assessment of laminated glass (LG) beams is a remarkably critical issue becauseamong othersit can involve major consequences in terms of structural safety. Knowledge of LTB load-bearing capacity (in terms of critical buckling load Fcr and corresponding lateral displacement dLT), in this regard, is, thus, a primary step for more elaborated design considerations. The present study examines how machine learning (ML) techniques can be used to predict the response of laterally unrestrained LG beams in LTB. The potential and accuracy of artificial neural networks (ANN), based on ML methods, are addressed based on validation toward literature data. In particular, to detect the best-performing data-driven ML model, the load-bearing capacity of LG beams (i.e., Fcr and dLT) is set as output response, while geometric properties (length, width, thickness) and material features (for glass and interlayers) are used as input variables. A major advantage is taken from a literature database of 540 experiments and simulations carried out on two-ply LG beams in LTB setup. To determine the best-performing ANN model, different strategies are considered and compared. Additionally, the Bayesian regularization backpropagation (trainbr) algorithm is used to optimize the inputoutput relationship accuracy. The suitability of present modeling strategy for LG beams in LTB is quantitatively discussed based on error and performance trends.
The study explores if tempered or strengthened with wire meshes, a single glass layer can be termed protective glass. Tempered glass demolishes into small fragments with harsh corners when it fractures. Because of the fracture pattern (fractures in pieces), heat- or chemically pre-stressed glass panel cannot be called safety glass panel until laminated. Bending experiments were run, and the bending strength of single-layer tempered and float glass panel was calculated using well-known formulae. In the context of float and tempered glass panel, the computed values for surface complexation using ultimate strain were matched to the bending strength findings. The following question arises: are the strains measured in the centre of the glass and towards the edge comparable? Strain measurements were also taken on the surface of packed samples in the centre and towards the edge of the glass. Fractures with tiny sharp points characterize glass errors. Despite careful manufacturing and maintenance of glass panes, hits by sharp particles or environmental effects can produce surface flaws. Glass manufacturing processes, such as edge polishing, have an impact on glass strength and can produce defects that spread during the glass’s lifespan. The study explores if tempered or strengthened with wire meshes, a single glass layer can be termed protective glass. Tempered glass demolishes into small fragments with harsh corners when it fractures. Because of the fracture pattern (fractures in pieces), heat- or chemically pre-stressed glass panel cannot be called safety glass panel until laminated. Bending experiments were run, and the bending strength of single-layer tempered and float glass panel was calculated using well-known formulae. In the context of float and tempered glass panel, the computed values for surface complexation using ultimate strain were matched to the bending strength findings. The following question arises: are the strains measured in the centre of the glass and towards the edge comparable? Strain measurements were also taken on the surface of packed samples in the centre and towards the edge of the glass. Fractures with tiny sharp points characterize glass errors. Despite careful manufacturing and maintenance of glass panes, hits by sharp particles or environmental effects can produce surface flaws. Glass manufacturing processes, such as edge polishing, have an impact on glass strength and can produce defects that spread during the glass’s lifespan.
24 May 2023 in Pertanika Journal of Science and Technology
Commonly, the columns and beams of glass panels are frequently subjected to in-plane loading, in which their joints will transfer the in-plane forces. Therefore, it is necessary to investigate the spring constants of the joints of these glass panels for the mechanical analysis of the structures. However, few issues were published on this subject, so estimating the spring constants of glass structure joints is important. Devote themselves to proposing methods to evaluate the spring constants of the joints of structural glass panels. This study tests two types of glass panels with thicknesses of 12 mm and 19 mm based on static and cycling loading. In addition, two types of Cushions: (1) aluminum and (2) rubber with a hardness of 65 and 90 degrees, are set between steel bolt(s) and glass panel(s) for the experiments. The spring constants are determined by the ratios of measured loads and the displacements between the glass panels and bolts. In addition, the authors proposed an equation to evaluate the bending spring constant from its axial spring constant determined by the loading tests. The experimental results showed that the joints with the aluminum cushion appear exactly non-linear elasticity while loading and unloading. Also, the pin junction within the central region (no Curve) is 0.6mm. It is also determined that aluminum (cushion) slides of approximately ±0.3mm under compression and tension. While loading (Tension/compression) is incremental, rubber acts nonlinearly but linear as unloaded.