The article substantiates the relevance of optimization algorithms research for solving various applied problems and for the science of artificial intelligence. The need to solve problems of optimizing the thermal-hydraulic modes of buildings (as part of the project "Smart City") is explained. The paper presents a mathematical formulation of the problem of optimizing the temperature mode of rooms using adjustable devices. Existing work provides two methods for solving the posed problem. They are the coordinates search method and the genetic algorithm. The article contains the description of the above mentioned algorithms (including the mathematical apparatus used). The results of the computational experiment (for the considered optimization methods) are presented. These experimental results show that the genetic algorithm provides better optimization results than the coordinates search method, but it has a large computational cost. The hypothesis was confirmed that in order to increase the efficiency of solving the considered class of problems it is necessary to combine the genetic algorithm and the coordinates search method.

The relevance of solving energy-saving problems using mathematical optimization methods is approved. An overview of Russian and foreign works on the topic of energy conservation and energy optimization is given. The need for solving the problems of optimizing the thermos-hydraulic regimes of buildings as part of the Smart City project is explained. The article presents the mathematical formulation of the problem of optimizing the temperature regime of rooms using adjustable devices, as well as two methods for solving the problem: the directed search method and the genetic algorithm. The above algorithms are described, including the mathematical apparatus used. The objective function is described as the standard deviation of the temperature of the heated rooms. A method for calculating air temperature in a heated room is presented by solving the heat balance equation, including a method for calculating incoming heat flows from a radiator and outgoing heat flows through building envelopes. Calculation formulas are given. The idea of improving these methods through preliminary measures, which will consist in installing additional sections of radiators in “cold” rooms, is considered. An algorithm for the automated issuing of recommendations for installing additional sections of radiators in the required rooms is described. The results of a numerical experiment for the considered optimization methods are presented. The calculations were carried out for a typical building under average design conditions of the city of Izhevsk, taking into account the actual condition of the building envelope, the heating system of the building, including heating appliances premises. A comparative analysis of the convergence of the iterative process of the directed search method and the genetic algorithm is carried out. In conclusion, it was concluded that the introduction of preliminary measures improves the convergence of the iterative process of the optimization problem.

Одним из важных направлений исследования в области искусственного интеллекта можно назвать методы оптимизации, в том числе стохастические алгоритмы. Данная технология используется для решения различных задач во многих областях деятельности. Целью приведенного в статье исследования является улучшение обучения нейронной сети методом генетического алгоритма путем фильтрации входных данных с использованием технологии цифровой обработки сигналов. В качестве входных данных взяты биржевые котировки. Нейронная сеть представляет собой совокупность слоев нейронов, где каждый нейрон является функцией от суммы входных сигналов, умноженных на коэффициенты. В данной статье используется сигмовидная передаточная функция. Для улучшения качества обучения входные данные подвергаются фильтрации. В обзорной части рассмотрен технический анализ, метод автоматической регрессии и применение нейронных сетей. Выдвинута и проверена гипотеза возможности улучшения качества обучения нейронной сети за счет подавления шума в исходных данных с использованием методов ЦОС. Проверена гипотеза зависимости качества обучения нейронной сети от статистических характеристик выборки. Рассмотрен метод фильтрации биржевых котировок с использованием скользящей средней и медианной фильтрации. Приведены результаты эксперимента и численная оценка качества обучения, а также статистических характеристик выборки, тем самым подтверждена зависимость между статистическими характеристиками выборки и качеством обучения нейронной сети. Подтверждено положительное влияние предварительной фильтрации данных на качество обучения нейронной сети.

On the territory of the Amur region, many agricultural producers from among various agricultural organizations, farms and individual entrepreneurs, and households of the population are registered and operate. The most suitable for agriculture in the region are the territories of the Southern Agricultural Zone, where the soil is extremely diverse and fertile. At the same time, in the period 2019-2021. a significant reduction in acreage has been established, which is mainly due to changes in climatic conditions in the region, the condition and production load of the machine and tractor fleet. The article analyzes the effectiveness of the crop industry and the level of mechanization of agriculture in the Amur region, suggests the most important directions in the development of agriculture in the region, which will increase the production of cereals and legumes, as well as expand the possibilities of interregional cooperation. Keywords: ACREAGE, CROP PRODUCTION, LEVEL OF MECHANIZATION, DEVELOPMENT, COOPERATION, EFFICIENCY

To increase the traction properties of a wheeled power vehicle, one of the classic solutions is to implement the entire weight load that falls on its propellers. The most rational and applied method in tractor construction is the 4K4 wheel formula, which allows the maximum weight of the tractor to be realized in the coupling. This is especially true when performing transport work in conditions where the implementation of traction properties largely depends on the condition of the base on which the movement takes place. When moving a transport unit on a horizontal surface, various additional methods of increasing traction properties are also known and widely used, often used of which are the installation of additional loads and increasing the contact area of the mover with the base on which the power vehicle moves (twin wheels, half-track, etc.). At the same time, when performing transport operations on roads with a significant longitudinal slope (ascent or descent) these methods of increasing the coupling weight are not always effective due to the unstable nature of the movement. This article presents experimental studies to improve the longitudinal stability of a tractor-transport unit (TTA) by using an original towing-distributing device, which allows simultaneously adjusting the longitudinal stability of the energy vehicle by redistributing the coupling weight inherent in the design characteristics in the tractor-transport unit system during its movement. Keywords: HEADING STABILITY, STABILIZATION, TRACTOR-TRANSPORT UNIT, TOW-DISTRIBUTING DEVICE, EFFICIENCY