A generalized description of the developed special model-algorithmic and software-information support for proactive control of a group of intelligent ground transport and technological means (ITTM) for servicing civil aviation aircrafts, operating in a single digital space of airport data is presented. The technology of functioning of each ITTM includes typical operations for loading/unloading mobile equipment, moving around the airfield, material, energy, information interaction with the airport infrastructure, with other ITTM, as well as aircraft. In these conditions, the tasks of proactive control of both individual ITTM and their group acquire special relevance and scientific novelty. The developed special model-algorithmic and software-information support is based on dynamic multi-variant forecasting, as well as integrated planning and operational management based on the model of interaction of systems by J. Boyd and the original poly-model logical-dynamic description of the studied subject area. A generalized structure of a poly-model complex describing the functioning of the ITTM group is presented.

As a basic concept for automating the processes of monitoring the functioning of complex agrobiotechnical objects (CABO), a transition from a reactive approach to a proactive one is proposed. Methodological foundations are proposed for automating the process of solving the problem of multi-criteria synthesis of control programs for proactive monitoring of generalized states of CABO and integrated ACS (IACS) as a process of managing the corresponding developing situation, which includes the subjects of modeling, the original object, its model, the external environment, as well as dynamic binary relations arising during their interaction. The purpose of developing the methodological foundations is to increase the efficiency of detection, localization and prevention of emergency situations. Based on the concepts of system modeling, proactive management, invariance of computational, modeling and real processes, as well as intellectualization of management, a system of interrelated fundamental principles is developed that takes into account the multi-aspect nature of the functioning of the CABO and the CABO IACS as a whole, including reflecting the relationships that were not taken into account in previous studies - between the generalized state of the computational process and the degree of interoperability. The developed concepts and fundamental principles make it possible to correctly substantiate and automate the selection of the most preferred intelligent technologies and systems for proactive monitoring of generalized states of the CABO at all stages of their life cycle, as well as to increase the indicators of efficiency and reliability of management decisions, as well as the development of appropriate recommendations that ensure increased efficiency and quality of functioning of the objects and systems under consideration in the given conditions.

The issues of automation of analysis and localization of barriers of interoperability of heterogeneous technical systems of complex agrobiotechnical objects in the conditions of ensuring the solution of the problem of integrated monitoring of their state are considered. The purpose of the study is to provide the possibility of multivariate forecasting and assessment of the functional compatibility of mating legacy and emerging promising automated systems in agricultural production based on simulation problem-oriented modeling and the use of intelligent technologies for extracting expert knowledge and manipulating it. A conceptual model of interoperability barriers localization is formed and the corresponding technical and methodological support is developed to substantiate typical solutions for overcoming interoperability barriers, automating the process of forming a summary characteristic (profile) of system interfacing, verifying, validating and testing applied interoperability models for specific sets of mating automated systems. The obtained results are of great practical importance for the technical and economic effect when choosing technical solutions to ensure interoperability of automated systems and modeling the predicted level.

The issues of solving integer, mixed-integer multicriterial optimization problems with nonlinear constraints are discussed. The aim of the study is to reduce the time costs for solving such problems using metaheuristic algorithms in a distributed heterogeneous computing environment that provides computing resources. The novelty of the proposed approach lies in the choice of a method for parallel execution of metaheuristic algorithms, the formation of computational load blocks that implement metaheuristics, and the assignment of blocks to computing resources in a heterogeneous distributed computing environment using a repository of effective algorithms. Results of an experimental study demonstrating the developed method effectiveness are presented.

The problem of classification analysis of time series data of telemetry information of a small spacecraft is considered in order to determine its technical state. Results of development and research of ensemble models of hybrid neural network classifiers based on ensembles such as bagging and AdaBoost, are presented. The basic model of a hybrid neural network classifier, obtained by automatic search using a genetic algorithm for searching hybrid neural network classifiers, is considered. This neural network model makes it possible to build and train a bagging model of an ensemble of hybrid neural network classifiers, the quality of which exceeds both the quality of the basic neural network model and the quality of ensembles of classifiers such as Random Forest, Bagging, Gradient Boosting, Adaptive Boosting (AdaBoost), Histogram-based Gradient Boosting based on decision trees.

It is proposed to use the AutoML approach to automate the creation of machine learning models predicting time series. Algorithms and technologies allowing to implement the automation of model creation are considered. A hybrid architecture of machine learning used in solving problems of automating the structural-parametric synthesis of models and optimizing hyperparameters, as well as in the automatic selection of indicators for assessing the quality of synthesized models, is chosen. The user interface for this system is implemented on the basis of the AutoGenNet platform, which embodies the No-Code development concept, which allows hiding the complexity of the processes of creating and training models from users, which reduces the entry threshold for working with the program. Using the AutoGenNet platform allows implementing a mechanism for generating software shells for operating trained models, as well as automating the processes of generating and training hybrid models, which simplifies and speeds up the process of solving time series forecasting problems using machine learning models. The results obtained can be scaled and used to create time series forecasting models in various applied problems.

A new trend is considered, namely, the formation of content using artificial intelligence tools and technologies. Active implementation of artificial intelligence technologies for data generation leads to an increase in the share of artificially generated data that must be identified automatically to prevent errors (unreliability, misleading). Approaches to identifying text data created using neural network technologies are proposed, including heuristic rules based on the criterion of dependence of the abstract volume on the abstracting threshold, which allows for automatic evaluation of text documents in monitoring and search systems when processing large volumes of unstructured data. The obtained results lay the technological basis for the implementation of a wide range of practical solutions to ensure intellectual support for the collective behavior of participants in human-machine communities through the development of theoretical and technological foundations for processing unstructured data.

The problem of refining the center of mass motion parameters of a non-cooperating spacecraft using an optical unit for measuring the spacecraft angular position relative to two navigation stars is considered. The article presents the results of development of a methodology for substantiating the requirements for the angular field of view of an optical- electronic instrument installed on board a service space robot to measure the motion parameters of a non-cooperative spacecraft subject to maintenance.

Absctact. The relevance of the scientific task of increasing the reliability of the use of a multi-satellite grouping of small spacecrafts for remote sensing of the Earth in the maintenance of geographically distributed observation objects is formulated. A method of operational change of configuration of functional elements of onboard systems of small spacecraft remote sensing equipment involved in detailed observation of an object is proposed, taking into account rational consumption of the system technical resource of the group in order to improve the reliability indicators of its application. The motion control system of small spacecraft during implementation of precise orientation and retargeting modes is considered as the main on-board system. A description of the input data for implementation of the process of planning operational change of configuration of functional elements of on-board equipment is given. The process of configuration selection consists of two stages: construction of a functional integrity scheme and formation of a probabilistic polynomial of successful operation of the motion control system and solution of the problem of selection of the optimal configuration taking into account the current mean time between failures of the functional elements of the system; the results of computational experiments are presented. The developed method is brought to the level of practical application, allowing for uniform consumption of the system technical resource of the small spacecraft group during its intended use.

A method is presented for creating multimodal data bases designed to analyze behavioral manifestations of virtual communication participants. The proposed methodology is aimed at developing database of group communication (more than two interlocutors) using teleconference systems. The technique also takes into account the peculiarities of the natural manifestations of behavioral aspects (engagement and emotions) of the participants in the conversation. The identified features constitute the novelty of the proposed technique. The technique consists of three main stages — preparatory, recording, and annotation of data. The technique is tested and validated when creating a new multimodal data corpus ENERGI, containing Russian-language audiovisual recordings of group communication of participants using teleconferencing systems. The created corpus is designed to solve the problems of recognizing the involvement of participants in communication, as well as analyzing the manifestation of emotions during a dialogue. The proposed technique is universal and can be applied to collecting various corpora of virtual communication data.