Vacuum insulated glass (VIG) panels are becoming more and more popular due to their good thermal performance. Little information about the mechanical or strength parameters, which are crucial for the durability of a window, might be found in the published papers. The purpose of this work was to analyse the impact of different parameters on VIG panels’ mechanical properties. Parameter diversity refers to both geometrical and material characteristics. Static and dynamic analyses using the finite element method (ABAQUS program) were conducted. In addition, 101 various numerical models, created with the use of Python language, were tested. The changes of geometrical parameters were made with constant material parameters and the reverse. It has been concluded that pillars’ material and geometrical properties are crucial considering not only the static response of the VIG plates, but also the dynamic one. Moreover, it was proven that getting rid of the first row of pillars near every edge seal led to an increase in deflection of the glass panes. Additionally, considering results for dynamic response associated with out-of-phase vibrations, spacing between support pillars should be large enough in order to avoid possible damage to the glass pane due to rapidly decreasing distance between them. Further research opportunities have been described.

The subject of this study is Vacuum Insulated Glass (VIG) panels, which consist of two glass panes with an evacuated space and evenly distributed micro-support pillars between them. The deflection of panes towards the centre of the structure caused by atmospheric pressure is a mechanical problem that occurs in this type of structure. The aim of this study was to extend previous research on the optimal arrangement of support pillars in terms of eigenfrequencies and dynamics to include aesthetic aspects. Using Abaqus/CAE v2017 software, a large number of numerical models were created and subjected to a comprehensive multi-criteria analysis. Fractal analysis was employed to automatically assess the aesthetics of the proposed solutions. The study presents theoretical solutions that could be implemented in industrial production. The presented study shows that it is possible to effectively extend the criteria for optimizing the arrangement of pillars with new design criteria. Most studies focus on pillar placement, amount, or shape in terms of panes thermal or mechanical properties. Due to the increasing number of VIG panels applications in places exposed to external vibrations, other design criteria for VIG panels are also required and are provided by the following study.

This study investigates the optimization of thickness distribution in simply supported and cantilever plates to maximize gaps between adjacent natural frequencies. The research employs a genetic algorithm (GA) as the primary optimization tool, with the finite element method (FEM) integrated for structural dynamics analysis. The optimization process focuses on tailoring the plate thickness (stiffness) while maintaining fixed overall dimensions. The study considers square and rectangular plates with two boundary conditions: simply supported and cantilever. The optimization targets gaps between the first three natural frequencies. The GA-based optimizer demonstrates effectiveness in increasing the relative separation between neighboring natural frequencies, as defined by the fitness function. Compared to the reference individuals, the optimized individuals achieve objective function values from 0.25 to 2.5 times higher. The GA optimization tool is also compared with an alternative optimization tool achieving up to 35% better results. This research contributes to the field of structural dynamics by demonstrating the potential of genetic algorithms in optimizing plate designs for enhanced vibrational characteristics. Such optimization is particularly relevant in civil engineering, where plate elements are widely used, and where controlling dynamic properties can improve serviceability and reduce the risk of resonance under operational or environmental loads. The findings have implications for various engineering applications where controlling dynamic properties of plate structures is crucial.

The VIG (Vacuum Insulated Glazing) unit, composite glazing in which the space between glass panes is filled with vacuum, is one of the most advanced technologies. The key elements of the construction of VIG plates are the support pillars. Therefore, an important issue is the analysis of their mechanical properties, such as Young’s modulus and their variability over a long period of time. Machine learning (ML) methods are undergoing tremendous development these days. Among the many different techniques included in AI, neural networks (NN) and extreme gradient boosting (XGB) algorithms deserve special attention. In this study, to train selected methods of machine learning, numerical data developed in the VIG plate modelling process using Abaqus program were used. The test method proposed in this article is based on the VIG plate subjected to forced vibrations of specific frequencies and then the reading of the dynamic response of the composite plate. Such collected and pre-developed experimental data were used to obtain the mechanical parameters of the steel elements located inside the analysed vacuum glazing. In the future, the proposed research methods can be used to analyse the mechanical properties of other types of composite panels.

This study investigates the application of machine learning (ML) techniques for predicting vibration frequencies of thin rectangular plates with variable thickness. Traditional optimization methods, such as genetic algorithms, require repeated solutions of the plate vibration eigenproblem using finite element (FE) analysis, which is computationally expensive. To reduce this cost, a surrogate model based on artificial neural networks (ANNs) is proposed as an efficient alternative. The dataset includes variations in plate geometry, boundary conditions, and thickness distribution, encoded numerically for model training. ANN architecture and hyperparameters—such as the number of hidden layers, neurons per layer, and activation functions—were systematically tuned to achieve high prediction accuracy while avoiding overfitting. Data preprocessing steps, including standardization and scaling, were applied to improve model stability. Performance was evaluated using metrics such as RMSE and R². The results demonstrate that ANNs can accurately predict eigenvalues with significantly reduced computational effort compared to FE analysis. This approach offers a practical solution for integrating machine learning into structural optimization workflows.

The aim of this paper is to optimize the thickness variation function of simply supported and cantilever beams, in terms of maximizing gaps between chosen neighboring frequencies, and to analyze the obtained results. The optimization results are examined in terms of achieving the objective function (related to eigenvalue problems), but also in terms of their dynamic stiffness (forced vibrations excited by a point harmonic load). In the optimization process, a genetic algorithm was used. Problems related to structural dynamics were solved by FEM implementation into the algorithm. Sample results were presented, and the developed algorithm was analyzed in terms of the results convergence by examining several variable parameters. The authors demonstrated the validity of applying the described optimization tool to the presented problems. Conclusions were drawn regarding the correlation between stiffness and mass distribution in the optimized beams and the natural frequency modes in terms of which they were optimized.