Vol 24, No 3 (2023)

Currently, unmanned aerial vehicles are widely used with navigation based on data from onboard integrated systems including inertial and satellite sensors. In this case, to solve many target tasks, their preliminary exit to a given point of the flight route along the shortest horizontal trajectory is provided. However, in practice, there may be situations when the information received from navigation satellites may no longer be available, which leads to a decrease in navigation accuracy. Considered a technique for detecting the trajectory of unmanned aerial vehicles under conditions of loss of signals from navigation satellites using the underlying surface images. As a criterion indicating the occurrence of deviations of unmanned aerial vehicles from a specified trajectory, it is proposed to use the change in parallaxes of adjacent pairs of images. Analytical relations describing the functional relationship between changes in image parallaxes and parameters of linear and angular deviations of unmanned aerial vehicles from a specified trajectory. All possible options of these deviations are also considered. The obtained results provide an a priori estimate of the threshold value of parallax changes corresponding to the acceptable level of unmanned aerial vehicles deviations from the specified trajectory by means of modelling. Based on this estimate, it is possible to improve the accuracy of trajectory detection of unmanned aerial vehicles under conditions of loss of signals from navigation satellites.

The controlled motion of an inertial object during a high-speed maneuver in a vertical plane is investigated. The generated thrust is limited in magnitude, the control is the angle that sets its direction, the initial velocity is generally non-zero, and external forces are not considered. The goal is to maximize the horizontal velocity projection at a given final moment of time with the simultaneous fulfillment of two terminal conditions: bringing the object to a given height and damping the vertical velocity projection. Similar tasks often arise when controlling mechanical objects with modulo-limited thrust. The research is relevant, as it is aimed at ensuring both the efficiency of the desired algorithm and the simplicity of its calculation and implementation. In this case, the methods of the mathematical theory of optimal control are used. As a result, a solvability condition for the problem posed is obtained, which is related to the minimum possible time of motion in the dual timeoptimal control problem. In the law of optimal control, based on the so-called law of fractional linear tangent, an analytical relationship between two integration constants is found, which makes it possible to reduce the procedure for determining these constants to the numerical solution of only one transcendental equation. An appropriate comparative analysis of the trajectories was carried out and conclusions were drawn that one of the proposed suboptimal strategies is more effective.

A comparative analysis of 3 AI-based smartphone applications for self-service skin cancer risk assessment: ProRodinki, Skinive and Skin Vision. Analysis consists of description of applications and its ways of work, and results, such as sensitivity and specificity, done on the base of the practical experiment conducted with processing 516 images of the skin neoplasms and pathologies confirmed by histological research via each app. Every application is unique and differs from each other by its principles or work, algorithms, user experience and design, and of course AI model and the set of input data that is analyzed by neural networks. Current research and practical experiment were made with focus on images processing and the app risk assessment for each of the image, other details and mole prescription information were set neutral. This leads to a conclusion that there is a lack of methodology for testing and analysis of different AI-based applications and services. Having such methodology, the comparison analysis results can be more objective and transparent.

The requirements for the quality and accuracy of manufactured products are constantly increasing. Reliability, durability, and accuracy of machine operation largely depend on the quality of surface treatment. Study on the cutting process, in particular milling, makes it possible to find out the operating conditions of the cutting tool, determine the acting cutting forces, torques, vibrations and temperatures on it. Along with studying the influence of various parameters on the milling process, it is necessary to pay special attention to establishing the nature and degree of influence of the cutting condition (cutting speed, depth of cut and feed rate). In this paper milling operation of Al6061-T6 was performed in a dry condition. The effects of cutting parameters on cutting forces and moments in different directions and around various axes were studied. By applying Taguchi technique and performing experiments, it was shown that cutting force was significantly affected by feed rate followed by rotational speed and cutting depth. Cutting moment is mainly influenced by feed rate, cutting depth, and rotational speed. Moreover, feed rate is the most effective factor on minimizing cutting forces and moments. Finally, the optimum cutting parameters was revealed to get a minimum cutting forces and moments.