Russian Engineering Academy

.

Russian-language resources for medical natural language processing (NLP) are expanding rapidly; however, their fragmentation, uneven curation, and limited clinical reliability hinder the development of safe machine learning systems for prognosis, prevention, and precision medicine. We provide the first systematic survey of Russian medical NLP datasets and analyze their suitability for clinically meaningful tasks as defined by the MedHELM taxonomy. We additionally perform expert clinical validation of three representative public corpora—RuMedPrimeData (real outpatient notes), MedSyn (synthetic clinical notes), and RuMedNLI (translated natural language inference)—assessing clinical plausibility, diagnosis accuracy, and logical consistency. Experts identified substantial reliability issues: across randomly sampled subsets of each corpus, only approximately 20% of RuMedPrimeData records, fewer than 15% of MedSyn records, and approximately 55% of RuMedNLI pairs met essential quality criteria, which can hinder downstream ML systems built on these data. To support robust applications—ranging from medical chatbots and triage assistants to predictive and preventive models—we outline practical requirements for high-quality datasets: coordinated, expert-validated, machine-readable corpora aligned with clinical guidelines and insurance logic, standardized de-identification, and transparent provenance. Strengthening these data foundations will enable the development of reliable, reproducible, and clinically relevant AI systems suitable for real-world healthcare applications.

The aim of this study is to develop an acoustic emission (AE) monitoring methodology that is invariant to the mechanical impact influence. To achieve this objective, regression and statistical analysis algorithms were employed to identify nonlinear relationships between the degree of damage in composite specimens (j) and the values of streaming AE parameters. As the most informative AE parameters correlating with the actual condition of the monitored specimens, the quantile values at the p = 0.9 level of the distribution functions of the front energy ([Eφ]p = 0.9) and specific energy ([EN]p = 0.9) of AE pulses were selected. A key stage in the implementation of the proposed methodology involves partitioning the criterion plane ([EN]p = 0.9 – [Eφ]p = 0.9) into three characteristic segments (I, II, III). Based on the values of the streaming parameters and their weighted distribution across segments I, II, and III (WI, WII, WIII), a regression model was synthesized to assess the degree of damage in composite specimens using AE monitoring results. The maximum reduced error of the developed model was γ = 9.8%, while the mean relative error did not exceed 1.1%, regardless of the initial condition of the monitored specimens.

Introduction. Increasing of the efficiency of using of the construction machinery, in particular, concrete mixers, is an important task of construction production, affecting the reduction of construction costs and increasing the efficiency of machine use. The aim is to show the possibilities of the considered method of physical large-scale modeling for determining the optimal parameters of machines under given operating conditions. Materials and methods. The optimal parameters of concrete mixers were determined by analyzing mathematical models of the working cycle duration of concrete mixers, the optimal solutions obtained were scaled to various operating conditions using the similarity theory discussed in the article. Results. The article presents graphs obtained using the proposed methods, demonstrating the presence of optimal zones of efficient use of concrete mixers under certain operating conditions. Conclusions. The considered provisions show that for concrete mixers, there are ratios between the main technical parameters m, N, q, T, l characterized by scale coefficients.

The application of artificial intelligence for structural analysis and synthesis of technical systems in mechanical engineering based on the morphological approach is discussed. A combined method is proposed that integrates advanced morphological analysis with artificial intelligence, which allows systematizing the process of generating a morphological set of solutions. As an example, the construction of morphological sets for additive technologies using artificial intelligence is considered and two platforms are compared. A conclusion is reached about the possible application of artificial intelligence.

The study is devoted to the analysis of mechanisms for managing the safety of territories and the formation of a scientifically based approach to determining the acceptable level of risk. The method of mathematical classification of data, namely hierarchical cluster analysis and the k-means method, is used as a tool. The need to solve this problem is associated with the identified methodological difficulties and inconsistencies in the use of current regulatory documents on risk assessment. The approach proposed in the work to determining the acceptable level of risk, based on the mathematical classification of data, is an important component on the way to developing a unified methodology for standardization.

A method for assessing the survivability of a pipeline at a distance from a transverse weld with a longitudinal surface semi-elliptical mode I crack is proposed, taking into account the biaxial constraint along its front. A literature review has shown that there are currently no works in which the forecast of the growth of such crack is carried out taking into account the Txx- and Tzz-stresses, which are nonsingular terms in the Williams expansion for stresses at the crack tip. To model the growth of a fatigue crack, a modified Paris formula is used, in which the range of the effective stress intensity factor (SIF) is substituted instead of the span of the usual SIF. In this case, in addition to the usual SIF, the expression for the effective SIF includes the Txx- and Tzz-stresses. The proposed two-parameter approach allows taking into account the constraint in the crack plane in the direction perpendicular to the front, due to the introduction of Txx-stresses into the expression for the effective SIF, and in the longitudinal direction due to the introduction of Tzz-stresses. The expression for the effective SIF was previously obtained by the authors by improving the fracture criterion of maximum tangential stresses. It is assumed that tangential stresses in the fracture process zone are equal to the local strength of the material. In this case, the size of the fracture process zone and the local strength of the material are determined taking into account the Txx- and Tzz-stresses. Numerical simulation was performed in the finite element environment of ANSYS Workbench. To construct a mathematical model of a pipe with a semi-elliptical crack, three types of finite elements (FE) were used: 10-node tetrahedral elements SOLID187; 20-node hexahedral FE SOLID186 and 15-node wedge FE degenerated from SOLID186. The latter of which singular FEs have a built-in function for calculating the SIF and Txx-stresses. Special macros were written in the APDL programming language to calculate the Tzz-stresses and the effective SIF along the crack front. It is shown that the use of a one-parameter approach based on the Paris formula does not allow taking into account the biaxiality of the stress state when assessing the survivability of an oil pipeline, since, unlike the effective SIF, the usual SIF for a longitudinal semi-elliptical crack depends only on circumferential stresses. It is established that for cracks of the same initial depth, the durability decreases with an increase in half-length. It is revealed that the durability predicted using the usual one-parameter Paris formula is approximately 30% underestimated, compared to the results of a two-parameter analysis.

In order to reduce the complexity and improve the quality of process design, it is proposed to draft part drawings in the form of a set of surface modules. Development of a unified element base of process tools for surface modules would make it possible to design parts manufacturing processes by simply arranging the modules.

The article discusses approaches to assessing interoperability in the joint interaction of diverse forces and means in an emergency situation. Using standardized models of interoperability and enterprise architectures, Petri nets, it is shown that it is possible to model the architecture of interoperability, the lifecycle of a network organization, and calculate the time to eliminate an emergency. As an example, a Petri net model of interaction between rescuers and doctors using telemedicine technologies in an emergency situation is presented.