The main task of the operation of engineering structures is to ensure the stability of structures with aggressive external influences, which have a complex probabilistic nature. The reliable functioning of bridge structures requires the development and application of modern systems for inspection and assessment of the technical condition of the structure to take timely measures to ensure the safe operation of the structure in changing operating conditions. With the rapid development of AI, modern approaches are increasingly adopted, offering distinct advantages compared to classical methods. The article aims to develop an AI-based model for quantifying the technical condition of bridge structural components based on data obtained from the survey. To achieve this goal, the authors analyzed existing approaches to the inspection and assessment of bridges and studied the experience of using AI in bridge assessment. Based on the Polish Principles of Bridge Technical Condition Assessment, three datasets were formed to quantify the condition of the bridge components made from reinforced concrete: bridge deck, span structures, and piers and abutments. This study created and compared the performance of five AI-based models: XGBoost, Decision Trees, Random Forest, Support Vector Regression, and Artificial Neural Networks (ANNs). The initial comparison revealed relatively low performance across all models, with the ANN model showing a slight advantage. Subsequently, nine ANN models were optimized to achieve higher performance levels. The performance of models was conducted based on a comparison of mean absolute percentage error (MAPE) and R² metrics. The ANN model with ReLU activation functions for hidden layers and the RMSprop optimizer achieves optimal performance at 100 epochs (MAPE = 3.5%; R² = 0.994). The practical implementation of such a model can considerably reduce uncertainties stemming from subjective expert judgments and enhance the accuracy of assessments.

In the article the stress-strain state of thick-walled structurally anisotropic composite cylindrical shells under thermal power load, which are protected by a functionally graded material, are analysed. Based on the interrelations of the spatial theory of elasticity, a system of inhomogeneous differential equations in three-dimensional formulation, which describes the stress-strain state of thick-walled anisotropic cylindrical shells, was obtained. To reduce the dimensionality of this system, the Bubnov-Galerkin analytical method was used. Thus, the obtained one-dimensional system of twelve equations of normal Cauchy form was implemented using the numerical method of discrete orthogonalization. To represent the possibilities of the proposed approach, there were used stress-strain states of two, four and five-layered anisotropic cylindrical shells of fibrous composites, protected from temperature by a layer of transversely isotropic functionally graded material.

In this study, the Hu–Washizu variational principle was employed to derive a three-dimensional system of partial differential equations, which governs the stability of an anisotropic body. This system was expressed in the cylindrical coordinate system. The analytical Bubnov–Galerkin method was employed to reduce it to a one-dimensional one. The solution of the one-dimensional problem in the direction of the normal to the median surface of the shell structure was carried out using the numerical method of discrete orthogonalisation. The present study investigates the values of critical loads of external lateral pressure for an anisotropic cylindrical shell made of a fibrous composite and the same shell with a layer of a functionally graded material. The study investigates the dependence of the critical loads on the angle of rotation of the main elastic directions of the unidirectional fibrous material and the number of its layers. The findings of this study demonstrate that incorporating a functionally graded material layer has the potential to enhance the critical loads of the structure.

The article presents an approach to the calculation of free oscillations of thick-walled elastic layered anisotropic cylindrical shells. Anisotropy is due to the use of material whose elastic characteristics are in one plane parallel to the middle surface of the shell. This type of anisotropy arises due to the non-coincidence of the main directions of elasticity of the orthotropic fibrous composite with the axes of the cylindrical coordinate system. Calculations describing the free oscillations of thick-walled cylindrical anisotropic shells are implemented by deriving a system of six differential equations of motion in partial derivatives of the spatial linear theory of elasticity. For this purpose, the authors modified the Hu-Washizu variational principle accordingly, which allows writing not only the equations of motion, but also the boundary conditions corresponding to them. When using the Bubnov-Galyorkin analytical method, an infinite one-dimensional system of differential equations of the normal Cauchy form is obtained, which allows finding the frequencies of free oscillations of thick-walled layered anisotropic cylindrical shells. The unknowns in the system of equations of motion describing the parameters of the stress-strain state of the shells are selected in the radial direction. To implement a one-dimensional solving system of differential equations of cylindrical shells, the numerical method of discrete orthogonalization was used, which was adapted accordingly by the authors. On this basis, an algorithm was written and a software complex was created for personal computers, which allows solving problems related to setting parameters of free oscillations of thick-walled layered anisotropic composite cylindrical shells. The solutions of problems on the influence on the frequencies of free oscillations of an anisotropic thick-walled cylindrical shell are presented, taking into account: the angle of rotation of the main directions of elasticity of an orthotropic fibrous composite; increasing the number of cross-stacked layers; changes in the geometric parameters of the structure; four types of boundary conditions.