No 3 (2024)

In connection with implementing the concept of electric airplanes, it is necessary to ensure the high reliability of electromechanical actuators (EMAs) as important components of aviation systems. The structural composition of an EMA and the types of its faults are considered. Fault diagnosis methods based either on EMA modeling or the analysis of signals received during EMA operation, as well as hybrid methods combining both these approaches, are reviewed. The advantages, disadvantages, and difficulties in applying these approaches are investigated. Special attention is paid to EMA diagnosis methods based on deep learning, which process signals in automatic mode and implement complex fault diagnosis. The concept of aircraft equipment health management (in particular, EMA health management) is presented based on assessing the technical condition and prognosticating the remaining useful life in order to prevent faults before their occurrence. Several hybrid approaches with prognostics are highlighted to solve the aircraft health management problem. Finally, Russian R&D results in the field of machine learning-based aviation health management are reviewed.

The main aspects of three concepts––human capital, innovation projects, and simulation modeling––are considered, and a simulation model is proposed to describe the role of human capital in innovation projects. This high-level abstraction model is intended to study the role of the social component in the organizational structure of an innovation project in a general context (at the level of an economic sector, an enterprise, or part of an enterprise). It is treated primarily as a tool for tracking the dynamics of projects considering the state of human capital of the system. The model consists of two main components, namely, a basic simulation model in system dynamics terms and an agent-based component of the model describing human capital dynamics. The model is a conceptual tool that requires calibration and refinement when being implemented in a particular organization.

This paper describes the approaches underlying ISAND, an information system for scientific activity analysis in the field of control theory and its applications. ISAND is being developed at the Trapeznikov Institute of Control Sciences, the Russian Academy of Sciences. The ISAND ontology is oriented toward the representation and collection of knowledge in the field of control theory and its applications, namely, scientific knowledge (the ontology of control theory) and knowledge related to the scientific activity of agents (organizations, journals, conferences, and individual researchers) in this field. Based on this ontology, the ISAND architecture is a complex program system to collect, store, and analyze publications and their metadata from external sources. The ISAND algorithm for building the thematic profiles of scientific objects (publications, researchers, organizations, journals, and conferences), as well as ISAND text processing and network analysis capabilities, are presented. Finally, the main possibilities of using ISAND are considered.

This paper presents a local path planning algorithm in the coordinate system of the roadbed. The algorithm is based on varying initial trajectory points using the potential field method and ensuring the smooth resulting path in a new coordinate system. This algorithm is executed by minimizing an objective functional. The problem is solved with application to path planning for an unmanned transport platform: it is necessary to change the vehicle’s global smooth trajectory points in real time while maintaining smoothness and avoiding emerging obstacles. Compared to the Cartesian coordinate system, the new coordinate system is advantageous in terms of the execution time of the algorithm. The algorithm is implemented in Python. With a planning horizon being specified, this approach can be combined with various path-following algorithms that have no obstacle avoidance methods. Computer simulation results are provided to demonstrate the effectiveness of the proposed algorithm.