Introduction. This paper studies the capability of different types of artificial neural networks (ANN) to predict the modulus of elasticity of pavement layers for flexible asphalt pavement under operating conditions. The falling weight deflectometer (FWD) was selected to simulate the dynamic traffic loads and measure the flexural bowls on the road surface to obtain the database of ANN models.Materials and Methods. Artificial networks types (the feedforward backpropagation, layer-recurrent, cascade back- propagation, and Elman backpropagation) are developed to define the optimal ANN model using Matlab software. To appreciate the efficiency of every model, we used the constructed ANN models for predicting the elastic modulus values for 25 new pavement sections that were not used in the process of training, validation, or testing to ensure its suitability. The efficiency measures such as mean absolute error (MAE), the coefficient of multiple determinations R2, Root Mean Square Error (RMSE), Mean Absolute Percent Error (MAPE) values were obtained for all models results.Results. Based on the performance parameters, it was concluded that among these algorithms, the feed-forward model has a better performance compared to the other three ANN types. The results of the best four models were compared to each other and to the actual data obtained to determine the best method.Discussion and Conclusions. The differences between the results of the four best models for the four types of algorithms used were very small, as they showed the closeness between them and the actual values. The research results confirm the possibility of ANN-based models to evaluate the elastic modulus of pavement layers speedily and reliably for using it in the structural assessment of (NDT) flexible pavement data at the appropriate time.

Introduction. One of the most significant tasks facing road experts is to maintain the transport network in good condition. The process of selecting an appropriate approach to providing such condition is quite complex since it requires considering many parameters, such as the existing condition of the pavement, road category, weather conditions, traffic volume, etc. Recently, the rising trend of digitization in the industry has contributed to the use of artificial intelligence to address problems in several fields, including the bodies in charge of operational control over the status of roadways. Within the context of any control system, the main task of the control system is to carry out reliable forecasting of the operational state of the road in the medium and long term.Materials and Methods. This study investigated the possibility of using artificial neural networks to assess existing pavement characteristics and their potential application in developing road maintenance strategies. A back-propagation neural network was implemented, trained using data from 1,614 investigated sections of the M4 «DON» highway in the road network of the Russian Federation in the period from 2014 to 2018. Several models were developed and trained using the MATLAB application, each with a different number of neurons in the hidden layers.Results. The results of the models showed a convergence between the inferred paving state values and the actual values, as the multiple correlation coefficient (R2) values exceeded 92 % for most of the models during all learning stages.Discussion and Conclusions. The findings suggest that public road authorities may utilize the established models to choose the best road maintenance strategy and assign the most efficient steps to restore road bearing capacity and operation.

The article is devoted to solving the urgent problem of improving the method of nondestructive testing of the condition of non-rigid road clothes. In addition to the previously developed approach to determining the mechanical parameters of materials of structural layers of nonrigid road coverings based on solving the inverse coefficient problem of restoring operational elastic modules providing specified displacement fields, an approach was developed that allows determining the parameters of energy dissipation in the structure of multilayer road pavement based on the correction of dynamic hysteresis loops recorded in the field and calculated using mathematical model of dynamic VAT. The article presents the results of numerical simulation of dynamic hysteresis loops for two different variants of multilayer structures. The possibilities of correcting the shape of hysteresis loops and their area by varying the tangents of the energy loss angles in layers of a multilayer medium and the elastic modulus of a homogeneous half-space are shown. The complex correction of the elastic modulus values of the structural layers of road clothes and the calculated loops of dynamic hysteresis made it possible to fully take into account the processes of energy attenuation at a distance from the point of application of the load. During the correction, it was found that the values of the elastic modulus of the road layers and the tangents of the loss angles in them have a complex effect on the areas of dynamic hysteresis loops and the nature of energy attenuation at a distance from the point of application of the load. At the same time, the elastic modulus of the underlying half-space is not limited in thickness to the greatest extent on the area of dynamic hysteresis loops (which led to an increase in the elastic modulus of the underlying half-space from 120 and 150 MPa for road construction variants with a reinforced and non-reinforced base to 170 and 160 MPa, respectively), and a decrease in the dissipated energy at a distance from the point of application This is primarily due to the tangent of the angle of energy loss in the half-space. The obtained values of the tangents of the loss angles are obviously related to the patterns of energy dissipation at the boundaries of the contacting layers of the pavement, and also take into account all possible anomalies and delaminations in the calculated structures. Within the framework of this article, calculated hysteresis loops on the surface of the pavement were obtained for the first time, the deformation energy was calculated based on their areas, and the possibility of their comparison with those registered experimentally was proved.

Introduction. The design of road pavements for highways is a key stage of project development, directly impacting their durability and operational costs. In recent years, in the context of increasing traffic intensity and dynamic loads, technologies for strengthening roadbeds and bases, such as geosynthetic reinforcement and stabilized layers, have become widespread, making the study on their efficiency a challenge. Literature notes the practical advantages of reinforced layers — increased load-bearing capacity and reduced deformation. However, models for energy dissipation under dynamic impacts in structures with such layers are underdeveloped. Theoretical approaches to analyzing energy dissipation, including linear-elastic and viscoelastic models and finite element methods, have been primarily applied to traditional structures. Their adaptation to reinforced and stabilized layers requires further development, as there remain gaps in the quantitative comparison of efficiency by location and rigidity of reinforcements. The objective of the presented work is to analyze the dissipation of deformation energy in the structure of road pavements with different options for the arrangement of reinforced layers, and to determine optimal design solutions that contribute to increasing the durability of road pavements. To achieve this, it is required to formalize an energy dissipation model for structures with reinforcements, conduct a comparative analysis of different locations and rigidity levels of the layers. Materials and Methods . The research utilized a comprehensive approach to the analysis of deformation processes in layered media using road pavements as an example, involving both a calculation tool and modern experimental equipment. As a calculation tool, a mathematical model of a layered half-space in an axisymmetric formulation in a cylindrical coordinate system was used. It was based on the solution to the system of dynamic Lame equations and allowed for the construction of amplitude-time characteristics of vertical displacements and impact loading impulse, on the basis of which it was possible to construct dynamic hysteresis loops. The FWD PRIMAX 1500 shock loading unit was used as experimental equipment, which made it possible to register similar characteristics of the road pavement response under field conditions at a load equivalent to the calculated one. Results. The study involved numerical modeling of road pavement structures traditionally used in the Russian Federation and so-called full-depth road pavements, which were composed almost entirely of materials reinforced with binders. Dynamic hysteresis loops were constructed, and a comparative analysis of the results was provided. A numerical experiment revealed that strengthening only the subgrade layer, even without installing a reinforced base layer beneath the asphalt concrete, reduced the amount of dissipated deformation energy. It was also concluded that the elastic modulus of the underlying half-space simulating the subgrade had the greatest impact on the amount of dissipated energy. Discussion. The greatest effect, both technical and economic, can be reached by strengthening the top of the roadbed while preserving the loose layers in the base of the road structure. This solution will bring the functioning of the road surface closer to the elastic stage and at the same time reduce the risk of cracks appearing on the surface of the pavement due to an excessively rigid layer of reinforced base. Conclusion. On the basis of the constructed dynamic hysteresis loops, it is shown that a reduction in the magnitude of deformation energy can be obtained both by installing reinforced layers of the road surface throughout its entire depth, and by locally strengthening the underlying half-space layer and an additional base layer made of sand. The numerical experiment demonstrated that the use of reinforced base layers reduced the amount of deformation energy dissipation in the pavement structure by more than 2–3 times. Qualitative agreement between the experimental results and the numerical simulation results was shown.

Introduction. In recent years, one of the main trends in the field of testing road structures has become field study of their large-scale models at the accelerated load facility (ALF). It can significantly reduce the cost of selecting the most economical and durable pavement designs. However, the results obtained on the ALF are often relative, since they practically do not correlate with the results of laboratory and field tests on real objects. This study is aimed at a comprehensive investigation of the response of a road structure to a dynamic load, the establishment of patterns of fatigue failure of asphalt concrete layers during the accelerated testing and full-scale tests on real objects.Materials and Methods. During testing, an accelerated load facility was used, located on the territory of the ShanDong Transport University. When conducting field tests, a dynamic loading unit with a falling weight FWD Primax 1500 was used, which recorded the deflection bowl on the surface of the structure under study. To record the dynamic response in the arrangement of the road structure, a complex of strain gauge sensors was used, which made it possible to register both compressive stresses and tensile strains in different layers. The results obtained under natural conditions were compared to the results obtained on the mathematical FEM model.Results. The research results have shown that the thickness of the lower coating layer is the main factor affecting the amount of vertical deformation of the pavement, which must be taken into account at the design stage of the pavement structure. Thus, with a thickness of the upper layer of the base of 10 cm, the vertical deformation was 100 µm, and with a thickness of 20 cm – 55 µm, provided that the overall strength of the structure was ensured. The number of load application cycles on the ALF had a minimal effect on the selected asphalt concrete samples during split tensile tests.Discussion and Conclusion. The adequacy of the results obtained in the course of accelerated testing of road structures was shown through a comprehensive comparison of numerical simulation data and full-scale tests, and the adequacy of the applied calculation methods was validated. The results of the study can be further applied in the road industry to develop and improve the regulatory framework for the design of non-rigid pavement under conditions of increased loads and heavy traffic.