The paper provides an overview of research on the integration of evolutionary game theory (EGT) and multi-agent reinforcement learning (MARL). The main problems of MARL and the corresponding advantages of EGT are analyzed. As a result of the analysis, it was found that the implementation of EGT can effectively solve the problems of instability, credit allocation and partial observability in MARL, providing stable strategic convergence and a new path for group optimization. It is shown that the integration of EGT and MARL forms a promising theoretical and technical basis for a breakthrough in multi-agent control. At the same time, in order to deeply merge the two directions, integration mechanisms will have to be optimized in the future, more reliable algorithms will have to be developed, and applied research in complex heterogeneous systems will have to be strengthened. 

Keywords: evolutionary game theory, multi-agent reinforcement learning, multi-agent control, instability, credit allocation, partial observability

This article examines the practical implementation of a methodology based on Bayes' theorem in the field of technical diagnostics and residual life forecasting for industrial equipment. Emphasis is placed on the ability of this approach to support engineers' effective work under the uncertainty inherent in real-world production processes. Using a vibration monitoring system for multi-axis milling machines, which are critical for the aerospace industry in the production of high-precision aluminum aircraft components, as an example, the feasibility of quantitatively updating the probability of failures as new sensor data arrives is demonstrated. Initial signals, such as vibration, temperature, or acoustic emission levels, are transformed into probabilistic risk assessments with practical justification, providing a reliable basis for management decision-making.

 

Keywords: "Technical diagnostics, residual life forecasting, predictive maintenance, engineering systems, decision theory, aircraft engineering, repair economics, uncertainty management, probabilistic models, monitoring systems, adaptive algorithms

The search for new approaches to the design of residential complexes is relevant in many countries worldwide. A humanitarian, environmentally-oriented approach is particularly promising for implementing design solutions. This article presents a theoretical justification for the principles that correspond to this approach. Based on the general strategic directions tested during the development of the residential complex design solution, eight principles have been identified and adapted to the conditions of Russia's southern regions: cultural identity; meaningfulness; reasonable rationality; social adaptability; permeability; energy efficiency; environmental friendliness; and aesthetics. Their integrated application demonstrates the use of a humanitarian, environmentally-oriented approach in the project.

Keywords: architecture, residential buildings, energy efficiency, ecological construction, green construction, residential development, eco-urbanism

In this article a hierarchical game in a two-level system for the distribution of rolled metal products is constructed.  Stackelberg equilibria for vertically connected participants and Nash equilibria for horizontally connected participants are found. There are several dealer organizations that sell rolled metal products, purchasing them from suppliers and delivering them via carriers either to their warehouse or directly to the customer. It's preferable for a dealer to have the product in their warehouse when a customer orders it. Otherwise, to avoid losing the order, the company must arrange for additional funds to purchase the product from the supplier and transport it to the customer. However, demand is far from constant and depends on several factors, including season, weather conditions, and the current socio-economic conditions in the region. Therefore, it's difficult to predict how much product to stock and when to do it. Suppliers, in turn, set prices for their products, including discounts for dealers. The system consists of several producers at the top level, several dealers at the bottom level, and their customers. An algorithm for sequentially coordinating transactions between a specific dealer and a specific supplier is proposed.

Keywords: Knyazev I.I., Gorbaneva O.I.

In recent years, the safe operation of energy facilities has increasingly been ensured by probabilistic non-destructive testing systems. This article examines a method for predicting and estimating the number of missed defects by solving an inverse problem. A detailed analysis of indirect manifestations and prediction of an indirect parameter is conducted using the Keras deep learning library, which determines the quantitative characteristics of the facility under study. The results of the study demonstrate encouraging prediction accuracy with easily correctable signs of model overfitting.

Keywords: non-destructive testing, defects, defect detection probability distribution curves, synthetic data for deep learning, regression forecasting, Keras, structural and semantic features, non-linear dependencies

The paper theoretically substantiates and experimentally verifies the design of a combined double-acting anchor combining a pile part (compression work) and a wire with a conical tip (pulling work). It has been found that the bearing capacity of a wire anchor exceeds that of a pile by 20-25 times due to the involvement of the soil cone in the work. The influence of geometric parameters on the pulling force was determined by the method of a complete factor experiment. A support and anchor foundation with an insulating shell has been developed to ensure operation under variable loads. Technical solutions are protected by patents of the Russian Federation.

Keywords: combined anchor, two-way action, wire anchor, pile element, conical tip, mathematical planning of the experiment, support and anchor foundation, insulator, bearing capacity, pulling load

This article examines the results of computer simulations of adhesive bond tear testing. Simulation models of adhesive bond tearing were constructed taking into account two stages of sample testing, the geometric structure, and the physical and mechanical properties of the materials and adhesive. The modeling took into account the statistical dispersion of parameters at the micro-level of the process. The article describes the algorithm for the sample testing process and evaluates its behavior depending on the values ​​and variations of the material parameters.

Keywords: Computer simulation, model, tear test, adhesive bond, material strength, simulation results, stress concentration

Numerical values of the functional extrapolator of a fractal L–Markov process with a quasi-rational spectrum are obtained. The methods of correlation and regression analysis were used to calculate the predicted complex values for the lead time t. The analysis of the real and imaginary parts of the optimal extrapolator is carried out for all correct values of the lead time t. The coefficients of Pearson linear correlation and Kendall rank correlation are calculated, which indicate a high linear correlation between the real and imaginary parts of the extrapolator and their noticeable rank correlation. The representability of the optimal extrapolator for the lead time t in the form of a linear combination of the values of the fractal L–Markov process under study at five points of the L–boundary is proved. The calculated values of the beta coefficient and the Hurst index indicate the high reliability of the forecast constructed in the work.

Keywords: extrapolation, L – Markov process, fractality, trend tolerance, spectral characteristic, correlation and regression analysis, optimal extrapolator, risk

Modern retail is faced with the need to simultaneously improve customer service and optimize operating costs, which is driving the active adoption of digital solutions to automate customer interactions. This article examines the use of dialog agents to automate key processes in retail—from initial consultation to order processing and follow-up. The aim of the study is to develop and evaluate an integrated system based on a dialog agent interacting with the 1C: Trade Management corporate system. The paper presents an analysis of the retail network's domain, describes the key business processes subject to automation, and proposes a dialog agent architecture and its integration with 1C. The paper also examines CASE tools for functional modeling and analysis of company operations and presents a rule-based approach to developing conversational agents based on a dictionary-pattern concept with regular expressions and keywords. The results showed that the use of conversational agents not only reduces operating costs but also increases sales conversion. The study confirms that conversational agents are an effective tool for digital retail transformation, combining scalability, personalization, and cost effectiveness

Keywords: Sales automation, retail, conversational agent, integration, online ordering, business processes, chatbot, trade management