International Journal of Advanced Engineering Research and Science最新文献

{"title":"Study on Dynamic Response Characteristics of Different Asphalt Pavement Structures Based on ALF Test","authors":"Ni Guangcong, A. N. Tiraturyan, E. V. Uglova, A. V. Vorobev","doi":"10.23947/2687-1653-2023-23-3-241-256","DOIUrl":"https://doi.org/10.23947/2687-1653-2023-23-3-241-256","url":null,"abstract":"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.","PeriodicalId":13758,"journal":{"name":"International Journal of Advanced Engineering Research and Science","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135426432","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Buckling of Rectangular Plates under Nonlinear Creep","authors":"S. B. Yazyev, A. S. Chepurnenko","doi":"10.23947/2687-1653-2023-23-3-257-268","DOIUrl":"https://doi.org/10.23947/2687-1653-2023-23-3-257-268","url":null,"abstract":"Introduction. The task of analyzing the stability of plates and shells under creep conditions is critical for structural elements made of materials with the property of aging, which are under the action of long-term loads, since the loss of stability can occur abruptly and long before the exhaustion of the strength resource of the material. Currently, the issues of joint consideration of geometric nonlinearity and creep in the problems of buckling plates remain poorly studied, existing software systems do not provide such calculations. The objective of this work is to develop an algorithm for calculating the stability of rectangular plates with initial deflection, which are subjected to loads in the middle plane, taking into account geometric nonlinearity and creep. Materials and Methods. When obtaining the resolving equations, the geometric and static equations of the theory of flexible elastic plates were taken as the basis. Physical equations were derived from the assumption that total strains were equal to the sum of elastic strains and creep deformations. Finally, the problem was reduced to a system of two differential equations, in which the desired functions were the stress and deflection functions. The resulting system of equations was solved numerically using the finite-difference method in combination with the method of successive approximations and the Euler method. As the boundary conditions for the stress function, the frame analogy was used, as in the case of a plane problem of elasticity theory. Results. The solution to the problem for a plate compressed in one direction by a uniformly distributed load has been presented. The nature of the growth of displacements at different load rates and initial deflection was studied. It has been established that when the vertical displacements reach values comparable to the thickness of the plate, their growth rate begins to decay even at a load greater than the long-term critical one. Discussion and Conclusion . The results of stability analysis using the developed algorithm show that the growth of plate deflection under the considered boundary conditions is limited, stability loss is not observed at any load values not exceeding the instantaneous critical one. This indicates the possibility of long-term safe operation of such structures with a load less than instant critical one.","PeriodicalId":13758,"journal":{"name":"International Journal of Advanced Engineering Research and Science","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135426433","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Implementation of Basic Operations for Sparse Matrices when Solving a Generalized Eigenvalue Problem in the ACELAN-COMPOS Complex","authors":"П.А. Оганесян, О.О. Штейн, P. Oganesyan, Olga Shtein","doi":"10.23947/2687-1653-2023-23-2-121-129","DOIUrl":"https://doi.org/10.23947/2687-1653-2023-23-2-121-129","url":null,"abstract":"Introduction. The widespread use of piezoelectric materials in various industries stimulates the study of their physical characteristics and determines the urgency of such research. In this case, modal analysis makes it possible to determine the operating frequency and the coefficient of electromechanical coupling of piezoelectric elements of various devices. These indicators are of serious theoretical and applied interest. The study was aimed at the development of numerical methods for solving the problem of determining resonance frequencies in a system of elastic bodies. To achieve this goal, we needed new approaches to the discretization of the problem based on the finite element method and the execution of the software implementation of the selected method in C# on the .net platform. Current solutions were created in the context of the ACELAN-COMPOS class library. The known methods of solving the generalized eigenvalue problem based on matrix inversion are not applicable to large-dimensional matrices. To overcome this limitation, the presented scientific work implemented the logic of constructing mass matrices and created software interfaces for exchanging data on eigenvalue problems with pre- and postprocessing modules.Materials and Methods. A platform was used to implement numerical methods .net and the C# programming language. Validation of the research results was carried out through comparing the values found with solutions obtained in well-known SAE packages (computer-aided engineering). The created routines were evaluated in terms of performance and applicability for large-scale tasks. Numerical experiments were carried out to validate new algorithms in small-dimensional problems that were solved by known methods in MATLAB. Next, the approach was tested on tasks with a large number of unknowns and taking into account the parallelization of individual operations. To avoid finding the inverse matrix, a modified Lanczos method was programmatically implemented. We examined the formats for storing matrices in RAM: triplets, CSR, СSC, Skyline. To solve a system of linear algebraic equations (SLAE), an iterative symmetric LQ method adapted to these storage formats was used.Results. New calculation modules integrated into the class library of the ACELAN-COMPOS complex were developed. Calculations were carried out to determine the applicability of various formats for storing sparse matrices in RAM and various methods for implementing operations with sparse matrices. The structure of stiffness matrices constructed for the same task, but with different renumbering of nodes of a finite element grid, was graphically visualized. In relation to the problem of the theory of electroelasticity, data on the time required to perform basic operations with stiffness matrices in various storage formats were summarized and presented in the form of a table. It has been established that the renumbering of grid nodes gives a significant increase in performance e","PeriodicalId":13758,"journal":{"name":"International Journal of Advanced Engineering Research and Science","volume":"133 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77066287","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Surface Quality Forming under Parts Finishing and Strengthening Treatment with an Eccentric Hardener","authors":"М.А. Тамаркин, Э.Э. Тищенко, О.С.А Хашаш, © Тамаркин, Mikhail A. Tamarkin, Elina E. Tishchenko, Omar СА Hashash","doi":"10.23947/2687-1653-2023-23-2-130-139","DOIUrl":"https://doi.org/10.23947/2687-1653-2023-23-2-130-139","url":null,"abstract":"Introduction. The formation of the quality parameters of the surface layer and the operational properties of the parts occurs throughout all stages of their manufacture. However, the decisive impact is most often exerted by the stages of finishing. Therefore, in modern digital engineering, the task of process support of high quality of the surface layer of the part is one of the challenges in solving the problem of improving the quality and reliability and increasing the life cycle of manufactured machines. Surface plastic deformation treatment is instrumental in improving the performance characteristics of machine parts. Its essence is that the required quality parameters of parts are obtained not by removing a layer of material, but by plastic deformation. During the processing, both the dimensions of the parts and the physical and mechanical properties of the surface layers are changed. In this case, the technologist has the opportunity to significantly increase the life cycle of the manufactured products through controlling the process. These studies are aimed at providing the required quality parameters of the surface layer under processing with an eccentric hardener.Materials and Methods. The article presents the results of research on a new method of surface plastic deformation treatment – with an oscillating eccentric hardener. The considered processing method enables to obtain high quality of the treated surface, to process large-sized parts in places that are stress concentrators, to process welds, small areas of surfaces, whose hardening is needed for the part to fulfill its intended service. A set of theoretical studies was carried out; their results provided determining the parameters of a single interaction of the indenter and the surface of the part, the diameter of the plastic imprint and its depth.Results. Dependences for determining the surface roughness, the depth of the hardened layer and the degree of deformation were obtained. The resulting formulas were tested for adequacy by experimental studies.Discussion and Conclusion. The obtained research results can be used in the technological design of surface plastic deformation treatment processes. Further tasks for the study of the considered processing method are determined.","PeriodicalId":13758,"journal":{"name":"International Journal of Advanced Engineering Research and Science","volume":"6 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84810749","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comprehensive Assessment of the Manufacturability of Products","authors":"P. Bochkaryov, R. Korolev, L. Bokova","doi":"10.23947/2687-1653-2023-23-2-155-168","DOIUrl":"https://doi.org/10.23947/2687-1653-2023-23-2-155-168","url":null,"abstract":"Introduction. The assessment of the manufacturability of products – as a stage of production planning and a key aspect of the development of modern industrial machining systems — is an urgent task of modern mechanical engineering. In this regard, theoretical and practical research on the development of methodological approaches to determining the weight significance of quantitative indicators in assessing the manufacturability of parts is highly relevant. The objective of the presented work was to develop an evaluation method aimed at improving the quality of part processing and the effectiveness of the performance of multiproduct manufacturing systems based on the development of additional quantitative indicators for assessing production manufacturability.Materials and Methods. To assess the impact of quantitative production indicators associated with time spent during equipment downtime, a model was created. It was aimed at predicting event flows of delivery of batches of parts for manufacturing for a specific operation and flows of processed parts using the queuing theory apparatus. This approach makes it possible to take into account both the design-engineering characteristics of parts, the features of a particular production system, and the emerging manufacturing situation.Results. The degree of influence of the manufacturability indicators at the level of the process operation was determined by assessing the possible impact on the components when calculating piece-calculation time (Тшт.к.). The interrelations between the manufacturability indicators and expenses for all items of the production cost of part processing (СОП), as well as costs associated with organizational downtime of equipment (Спр.о.i) were established. The degree of influence of the indicators of manufacturability relative to other indicators was determined by using the apparatus of paired comparisons in decision-making in relation to all structural elements of production costs.Discussion and Conclusion. The approach to the implementation of this design procedure was described, which provided taking into account the composition and capabilities of processing equipment of a particular production and the actual production situation. The developed formalized models make it possible to comprehensively predict the impact of the manufacturability indicators of parts on the performance effectiveness of machining systems during their manufacture.","PeriodicalId":13758,"journal":{"name":"International Journal of Advanced Engineering Research and Science","volume":"10 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73240983","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Analysis of Stress-Strain State of a Cylinder with Variable Elasticity Moduli Based on Three-Dimensional Equations of Elasticity Theory","authors":"J. Ismayilova","doi":"10.23947/2687-1653-2023-23-2-113-120","DOIUrl":"https://doi.org/10.23947/2687-1653-2023-23-2-113-120","url":null,"abstract":"Introduction. Functionally graded materials are of great use, because heterogeneity of properties enables to control the strength and rigidity of structures. This has caused great interest in the topic in the world scientific literature. The construction of solutions to such problems depends significantly on the type of boundary conditions. In this paper, we consider the equilibrium of a thin-walled circular cylinder whose mechanical properties change along the radius. Homogeneous boundary conditions were set on cylindrical surfaces that had not been considered before, the effect was on the ends. The mathematical formulation of the problem was carried out in the linear theory of elasticity in the framework of axisymmetric deformation. Expressions were constructed for the components of the stress-strain state of the cylinder, in which some coefficients were found from the solution to the resulting system of linear algebraic equations.Materials and Methods. The material of the cylinder was linearly elastic, the elastic modulus of which depended linearly on the radial coordinate. The basic research method was the asymptotic method, in which half the logarithm of the ratio of the outer and inner radii acted as a small parameter. Iterative processes were used to construct the characteristics of the stress-strain state of the cylinder.Results. Homogeneous solutions to the boundary value problem were obtained for a linearly elastic functionally gradient hollow thin-walled cylinder. An analysis of these solutions made it possible to reveal the nature of the stress-strain state in the cylinder wall. For this purpose, an asymptotic analysis of the solutions was carried out, relations for displacements and stresses were obtained. It was determined that those solutions corresponded to the boundary layer, while their first terms determined Saint-Venant edge effect similar to the plate theory.Discussion and Conclusion. The analytical solution to the equilibrium problem of a thin-walled cylinder inhomogeneous in radius constructed by asymptotic expansion can be used for numerical solution to a specific problem. For this, it is required to solve the obtained systems of linear algebraic equations and determine the corresponding coefficients. The resulting asymptotic representations provide analyzing the three-dimensional stress-strain state. The selection of the number of expansion terms makes it possible to calculate displacements and stresses with a given degree of accuracy. This analysis can be useful in assessing the adequacy of applied calculation methods used in engineering practice.","PeriodicalId":13758,"journal":{"name":"International Journal of Advanced Engineering Research and Science","volume":"27 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85991084","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Methods for Applying Matrices when Creating Models of Group Pursuit","authors":"A. Dubanov","doi":"10.23947/2687-1653-2023-23-2-191-202","DOIUrl":"https://doi.org/10.23947/2687-1653-2023-23-2-191-202","url":null,"abstract":"Introduction. It is obvious that in the near future, the issues of equipping moving robotic systems with autonomous control elements will remain relevant. This requires the development of models of group pursuit. Note that optimization in pursuit tasks is reduced to the construction of optimal trajectories (shortest trajectories, trajectories with differential constraints, fuel consumption indicators). At the same time, the aspects of automated distribution by goals in group pursuit were not considered. To fill this gap, the presented piece of research has been carried out. Its result should be the construction of a model of automated distribution of pursuers by goals in group pursuit.Materials and Methods. A matrix was formed to study the multiple goal group pursuit. The control parameters for the movement of the pursuers were modified according to the minimum curvature of the trajectory. The methods of pursuit and approach were considered in detail. The possibilities of modifying the method of parallel approach were shown. Matrix simulation was used to build a scheme of multiple goal group pursuit. The listed processes were illustrated by functions in the given coordinate systems and animation. Block diagrams of the phase coordinates of the pursuer at the next step, the time and distance of the pursuer reaching the goal were constructed as a base of functions. In some cases, the location of targets and pursuers was defined as points on the circle of Apollonius. The matrix was formed by samples corresponding to the distribution of pursuers by goals.Results. Nine variants of the pursuit, parallel, proportional and three-point approach on the plane and in space were considered. The maximum value of the goal achievement time was calculated. There were cases when the speed vector of the pursuer was directed arbitrarily and to a point on the Apollonius circle. It was noted that the three-point approach method was convenient if the target was moving along a ballistic trajectory. To modify the method of parallel approach, a network of parallel lines was built on the plane. Here, the length of the arc of the line (which can be of any shape) and the array of reference points of the target trajectory were taken into account. An equation was compiled and solved with these elements. On an array of samples with corresponding time values, the minimum time was found, i.e., the optimal time for simultaneous group achievement of multiple goals was determined. For unified access to the library, the control vector was expressed through a one-parameter family of parallel planes. A library of calculations of control vectors was formed. An example of applying matrix simulation to group pursuit was shown. A scheme of group pursuit of multiple goals was presented. For two goals and three pursuers, six samples corresponding to the distribution of pursuers by goals were considered. The data was presented in the form of a matrix. Based on the research results, the compute","PeriodicalId":13758,"journal":{"name":"International Journal of Advanced Engineering Research and Science","volume":"6 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87952821","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Aspects of Thermal Protection of Machine-Building and Power Equipment: Application of Oxidation-Resistant Combined Nickel-Based Coatings","authors":"V. Varavka, O. Kudryakov, V. Grishchenko","doi":"10.23947/2687-1653-2023-23-2-140-154","DOIUrl":"https://doi.org/10.23947/2687-1653-2023-23-2-140-154","url":null,"abstract":"Introduction. In the areas of power engineering where the thermal energy of superheated steam is used, an important aspect of providing the reliability and safety of equipment is the heat resistance of the materials employed. In the manufacture of induction superheaters, the optimal material for the steam pipe (coil) is copper. However, its ultimate resistance to oxidation does not exceed 400 °C, which significantly limits the efficiency of steam generators. Therefore, the objective of the work was to study the kinetics of oxidation of the combined galvanic coating of the Mo-Ni-Cr system applied to copper tubular samples and intended for thermal protection of steam generator coils.Materials and Methods. A combined electroplating of the Mo-Ni-Cr system with a total thickness of 12–35 μm was formed on the experimental copper tubular samples. A Mo sublayer with a thickness of about 1.5 μm on the surface of the copper tube was formed to prevent the diffusion of Cu into the Ni coating. A 1.5 μm thick chromium layer on the coating surface acted as an indicator of the oxidation process. A comparative analysis of the oxidation processes of the copper surface and the combined coating of the Mo-Ni-Cr system on a copper substrate was carried out using the methods of optical and electron microscopy, energy dispersive analysis, and precision determination of the growth parameters of oxide films.Results. The intervals of thermal stability of the copper substrate and nickel coating were experimentally determined. The obtained experimental dependences characterized the parabolic law of copper oxidation with the formation of a single-phase diffusion zone of CuO at temperatures above 350 °C, and nickel at temperatures above 750 °C, when the transition of NiO monoxide into oxide Ni2O3 began. The growth of oxide films according to quadratic laws provided a rapid increase in the thickness of the films, the accumulation of stresses in them, cracking, and chipping.Discussion and Conclusion. It is shown that the Mo-Ni-Cr electroplating is resistant to heating during long-term operation up to temperatures of 750–800 °C. The functional roles of Mo and Cr in the coating architecture were described. The work focused on the applied aspect of using the coating under study to increase the thermal stability of the steam pipelines of industrial induction superheaters with low and medium power.","PeriodicalId":13758,"journal":{"name":"International Journal of Advanced Engineering Research and Science","volume":"397 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76458562","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Visual Coherence for Augmented Reality","authors":"A. Gorbunov","doi":"10.23947/2687-1653-2023-23-2-180-190","DOIUrl":"https://doi.org/10.23947/2687-1653-2023-23-2-180-190","url":null,"abstract":"Introduction. The 2020s were marked by the emergence of a new generation of computer simulators using augmented reality. One of the promising advantages of augmented reality technology is the ability to safely simulate hazardous situations real-world. A prerequisite for realizing this advantage is to provide the visual coherence of augmented reality scenes: virtual objects must be indistinguishable from real ones. All IT leaders consider augmented reality as a next “big wave”; thus, the visual coherence is becoming a key issue for IT in general. However, it is in aerospace applications that the visual coherence has already acquired practical significance. An example is Boeing's development of an augmented reality flight simulator, which began in 2022. Visual coherence is a complex problem, one of the aspects of which is to provide the correct overall coloration of virtual objects in an augmented reality scene. The objective of the research was to develop a new method of such tinting.Materials and Methods. The developed method (called spectral transplantation) uses two-dimensional spectral image transformations.Results. A spectral transplantation technology is proposed that provides direct transfer of color, brightness, and contrast characteristics from the real background to virtual objects. An algorithm for automatic selection of the optimal type of spectral transformation has been developed.Discussion and Conclusion. Being a fully automatic process without recording lighting conditions, spectral transplantation solves a number of complex problems of visual coherence. Spectral transplantation can be a valuable addition to other methods of providing visual coherence.","PeriodicalId":13758,"journal":{"name":"International Journal of Advanced Engineering Research and Science","volume":"16 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91006128","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predicting the Behavior of Road Users in Rural Areas for Self-Driving Cars","authors":"S. A. Ivanov, B. Rasheed","doi":"10.23947/2687-1653-2023-23-2-169-179","DOIUrl":"https://doi.org/10.23947/2687-1653-2023-23-2-169-179","url":null,"abstract":"Introduction. The prediction module generates possible future trajectories of dynamic objects that enables a self-driving vehicle to move safely on public roads. However, all modern prediction methods evaluate their performance only under urban conditions and do not consider their applicability to the domain of rural roads. This work examined the adaptability of existing methods to work under rural unstructured conditions and suggested a new, improved approach.Materials and Methods. As a solution, we propose to use a neural network that includes the following submodules: a graph-based scene encoder, a multimodal trajectory decoder, and a trajectory filtering module. Another proposed feature is to use an adapted loss function that penalizes the network for generating trajectories that go beyond the drivable area. These elements use standard practices for solving the prediction problem and adapting it to the domain of rural roads.Results. The presented analysis described the basic features of the prediction module in the rural road domain, showed a comparison of popular models, and discussed its applicability to new conditions. The paper describes the new approach that is more adaptive to the considered domain of study. A simulation of the new domain was performed by modifying existing public datasets.Discussion and Conclusion. Comparison to other popular methods has shown that the proposed approach provides more accurate results. The disadvantages of the proposed approach were also identified and possible solutions were described.","PeriodicalId":13758,"journal":{"name":"International Journal of Advanced Engineering Research and Science","volume":"64 3 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90944675","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}