Черепанська Ірина Юріївна

DESIGN OF AN INFORMATION AND COMPUTER SYSTEM FOR AUTOMATED CONTROL OVER TRANSPORT FLOWS AT MACHINERY AND INSTRUMENT MANUFACTURING ENTERPRISES

I. Cherepanska et al., “DESIGN OF AN INFORMATION AND COMPUTER SYSTEM FOR AUTOMATED CONTROL OVER TRANSPORT FLOWS AT MACHINERY AND INSTRUMENT MANUFACTURING ENTERPRISES,” Eastern-European Journal of Enterprise Technologies, vol. 3, no. 3, pp. 54–64, 2026, doi: 10.15587/1729-4061.2026.361146.

This study investigates the process of managing transport flows at machine-building and instrument-building enterprises. The task addressed relates to the need for fast and effective information processing and making correct and justified logistics decisions, their automated adjustment in real time throughout the entire production life cycle. To that end, an information and computer system (ICS) has been designed for automated management of transport flows at machine-building and instrument-building enterprises. Its operation is to determine, coordinate, and adjust technological routes for a set of transportation means (TrMs) under an automated mode and in real time when organizing production environment. It is noteworthy that the newly designed ICS covers both internal and external shop logistics levels, ensuring synchronization of territorially distributed elements of flexible production systems of machine-building and instrument-building. Owing to the use of the ant algorithm for task distribution between TrMs and the modified A* algorithm with spatial-temporal graph expansion, the ICS capability to make operational decisions based on the "concept of compromises" has been implemented. The newly designed ICS also demonstrates high performance – preventing deadlocks in 24.9 ms and balancing the TrMs load in 500 ms. In addition, it has been experimentally proven that the total length of technological routes has been reduced by 1.3 times, and the idle runs of TrMs by 2.5 times. It is obvious that route optimization contributes to reducing the carbon footprint, which corresponds to the Sustainable Development Goals by 2030. Also, reducing the labor intensity of work and the intellectual load on the operator has an obvious social effect Copyright

Quaternion Model of System Elements for Automatic Orientation of Production Objects in Mechanical Engineering and Instrument Manufacturing

I. Cherepanska, A. Sazonov, P. Melnychuk, A. Zhuchenko, L. Mohelnytska, and D. Melnychuk, “Quaternion Model of System Elements for Automatic Orientation of Production Objects in Mechanical Engineering and Instrument Manufacturing,” Lecture Notes in Electrical Engineering, vol. 1570 LNEE, pp. 220–228, 2026, doi: 10.1007/978-3-032-18415-3_23.

Modern production rates require more flexibility, productivity and accuracy of systems forautomatic orientation of production objects (SAOPO). SAOPO represent a specific technological environment of functionally interacting sets of automatic orientation devices (OD) and PO. The necessary conditions for increasing the flexibility, productivity and accuracy of SAOPO are the determination of OD optimal models in terms of the balance between the probable effects and costs of their use, as well as the functional compatibility of the OD with PO for their automatic orientation, and compatibility with other technological equipment. Modern PO represent software and hardware and are characterized by significant variability in structure, functionality and dynamic properties regarding the implementation of PO automatic orientation. The automated solution of these tasks is carried out by a previously developed information and computer system for automated modeling of SAOPO. The basis of the ICS functioning for the SAOPO automated modeling is mathematical models of the SAOPO elements. A mathematical model of the OD functional capabilities and dynamic characteristics is described, which is based on the mathematical apparatus of quaternions. The correspondence between previously developed quaternion models for determining the geometric parameters of the PO orienting movements and the first developed mathematical model of the orientating function components is established. The results of theoretical research and computer modeling are presented. The operability and efficiency of the developed quaternion model are shown. The obtained results are significant and show that the productivity and the speed of the work performed increase by approximately 40%. The social effect is important as well, it is manifested in the reduction of fatigue and the intellectual load on workers.

S3PM: Entropy-Regularized Path Planning for Autonomous Mobile Robots in Dense 3D Point Clouds of Unstructured Environments

A. Sazonov, O. Kuchkin, I. Cherepanska, and A. Lipnickas, “S3PM: Entropy-Regularized Path Planning for Autonomous Mobile Robots in Dense 3D Point Clouds of Unstructured Environments,” Sensors, vol. 26, no. 2, 2026, doi: 10.3390/s26020731.

Autonomous navigation in cluttered and dynamic industrial environments remains a major challenge for mobile robots. Traditional occupancy-grid and geometric planning approaches often struggle in such unstructured settings due to partial observability, sensor noise, and the frequent presence of moving agents (machinery, vehicles, humans). These limitations seriously undermine long-term reliability and safety compliance—both essential for Industry 4.0 applications. This paper introduces S3PM, a lightweight entropy-regularized framework for simultaneous mapping and path planning that operates directly on dense 3D point clouds. Its key innovation is a dynamics-aware entropy field that fuses per-voxel occupancy probabilities with motion cues derived from residual optical flow. Each voxel is assigned a risk-weighted entropy score that accounts for both geometric uncertainty and predicted object dynamics. This representation enables (i) robust differentiation between reliable free space and ambiguous/hazardous regions, (ii) proactive collision avoidance, and (iii) real-time trajectory replanning. The resulting multi-objective cost function effectively balances path length, smoothness, safety margins, and expected information gain, while maintaining high computational efficiency through voxel hashing and incremental distance transforms. Extensive experiments in both real-world and simulated settings, conducted on a Raspberry Pi 5 (with and without the Hailo-8 NPU), show that S3PM achieves 18–27% higher IoU in static/dynamic segmentation, 0.94–0.97 AUC in motion detection, and 30–45% fewer collisions compared to OctoMap + RRT* and standard probabilistic baselines. The full pipeline runs at 12–15 Hz on the bare Pi 5 and 25–30 Hz with NPU acceleration, making S3PM highly suitable for deployment on resource-constrained embedded platforms.

DESIGN OF AN INFORMATION-COMPUTER SYSTEM FOR THE AUTOMATED MODELING OF SYSTEMS FOR AUTOMATIC ORIENTATION OF PRODUCTION OBJECTS IN THE MACHINE AND INSTRUMENT INDUSTRIES

I. Cherepanska et al., “DESIGN OF AN INFORMATION-COMPUTER SYSTEM FOR THE AUTOMATED MODELING OF SYSTEMS FOR AUTOMATIC ORIENTATION OF PRODUCTION OBJECTS IN THE MACHINE AND INSTRUMENT INDUSTRIES,” Eastern-European Journal of Enterprise Technologies, vol. 3, no. 2(129), pp. 6–19, 2024, doi: 10.15587/1729-4061.2024.306516.

An information-computer system has been developed for the automated modeling of systems for automatic orientation of production objects, which is one of the most important and complex creative flexible production systems of machine and instrument engineering. The proposed information-computer system for automated modeling of systems of automatic orientation of production objects is an effective tool for solving an important task of a scientific and applied nature. Its use makes it possible to increase the speed and efficiency of information processing and to make correct and well-founded decisions when determining the composition and method of organization of systems of automatic orientation of production objects. The structure of this information-computer system is a specific set of software and hardware and information and telecommunication tools and interactive functional modules. This structure reproduces a certain paradigm that conditions the integrity and integration of the information-computer system for automated modeling of systems for automatic orientation of production objects in flexible production systems. In addition, uniformity, extensibility, the possibility of modernization and changeability of software components, protection ofinformation from unauthorized access and preservation of commercial secrets are ensuredaccordingto international criteria for evaluating the protection of the computer system. Neuro-fuzzy network information processing and computer vision algorithms have been implemented for automatic identification of production objects and orientation devices, which are components of automatic orientation systems of production objects. The developed information-computer system processes information in real time with high accuracy and speed Copyright

DESIGN OF AN INTELLIGENT MODULE FOR DETECTING SIGNS OF INFORMATION SECURITY THREATS AND THE EMERGENCE OF UNRELIABLE DATA

I. Cherepanska et al., “DESIGN OF AN INTELLIGENT MODULE FOR DETECTING SIGNS OF INFORMATION SECURITY THREATS AND THE EMERGENCE OF UNRELIABLE DATA,” Eastern-European Journal of Enterprise Technologies, vol. 6, no. 2(132), pp. 49–63, 2024, doi: 10.15587/1729-4061.2024.317000.

At the stage of production preparation, there is an urgent need for an automated system that wouldtimely detectsigns ofthreats to information security and the emergence of unreliable data. To solve this problem, an intelligent module capable of detecting such threats and unreliable and/or anomalous data has been designed. The proposed intelligent module is the state-of-art, original, and effective toolkit. It can be recommended for practical use as part of the well-known information and computer system for automated modeling of the system of automatic orientation of production objects at the stage of technological preparation of machine and instrument-building production. Its application makes it possible to increase information security and reliability of important production data at the stage of technological preparation of production, in particular, when modeling systems for automatic orientation of production objects. In addition, the use of the proposed intelligent module makes it possible to obtain a number of important social and economic effects. Some of these effects are manifested in the prevention or reduction of material, intellectual and time costs for saving and restoring information, etc. Automated analysis of important production data regarding their reliability and abnormality is carried out by machine learning methods using a specially designed advanced variational autoencoder based on classification algorithms and using wavelet transformation. The designed intelligent module for detecting signs of a threat to information security and the emergence ofunreliable and/or anomalous data works in real time with a high accuracy of 97.53 %. It meets the requirements of modern production Copyright

Quaternion Model of Workpieces Orienting Movements in Manufacturing Engineering and Tool Production

I. Cherepanska, A. Sazonov, D. Melnychuk, P. Melnychuk, and Y. Khazanovych, “Quaternion Model of Workpieces Orienting Movements in Manufacturing Engineering and Tool Production,” Lecture Notes in Mechanical Engineering, pp. 127–135, 2024, doi: 10.1007/978-3-031-42778-7_12.

One of the most significant requirements in modern mechanical engineering and instrument-making productions is workpieces’ orientation systems productivity and their simulation speed. Workpieces’ orientation systems simulation, in particular their orientation movements, is one of the most challenging and essential pre-production tasks. The complexity of the mathematical model equations, its accuracy, and computational complexity affect simulation effectiveness. The article describes the mathematical model of the workpiece orienting movements, which relies upon the mathematical apparatus of quaternions. Moreover, the article shows the principal properties of quaternions and the rules for working with them. Theoretical and experimental studies of the workpiece orienting movements quaternion model are presented, particularly the sequence and results of determining the geometric parameters of these movements, i.e., rotation angle and direction of the vector, which is collinear to the workpiece’s axis of rotation. The model has been studied for an arbitrary workpiece. The results show that the performed works’ productivity and speed increased by approximately 40%. At the same time, computational costs and intellectual efforts are significantly reduced compared to the traditional methods of the workpiece’s movement description.

Research Of Dual-Channel Capacity Mems Sensitive Element Of Automated Gravimetric System With Artificial Intelligence Elements

O. Bezvesilna, I. Cherepanska, Y. Kyrychuk, A. Sazonov, and O. Sivaieva, “Research Of Dual-Channel Capacity Mems Sensitive Element Of Automated Gravimetric System With Artificial Intelligence Elements,” International Conference on Electrical, Computer, and Energy Technologies, ICECET 2022, 2022, doi: 10.1109/ICECET55527.2022.9873513.

The work is devoted to such current problem as gravimetric studies of the Earth for the presence of mineral deposits. To solve the problem, a system of automated intelligent determination of gravimetric information for the search for minerals was developed. The system uses a two-channel capacitive MEMS gravimeter as a sensitive element. There are some advantages of this system, such as: speed of measurement, possibility of work in hard-to-reach regions of the globe, high accuracy due to the use of a new two-channel capacitive MEMS gravimeter by reducing the main errors by using two channels. A method for determining minerals depending on the value of gravity acceleration has been developed. According to engraving, conducted using the proposed automated gravimetric system with elements of artificial intelligence, we can with some probability talk about the presence of minerals such as copper, magnetite, coal, and others. At the same time information processing time is reduced. Further clarification of the depth and size of the mineral deposit requires additional geological and geophysical research, such as the use of remote spectral and structural analysis of minerals with the involvement of satellite exploration.

Ring Laser for Angle Measurement Devices

I. Cherepanska, O. Bezvesilna, A. Sazonov, P. Melnychuk, and V. Kyrylovych, “Ring Laser for Angle Measurement Devices,” Lecture Notes in Mechanical Engineering, pp. 775–784, 2021, doi: 10.1007/978-3-030-68014-5_75.

Angle measurement means are one of the advanced directions for the application of gas ring lasers. The requirements of ring lasers used in angle measurement devices are different, in many respects, from those used in navigation. A simple ring laser developed for implementation in high-precision angle measurement instruments is described. The main specifications are presented. Theoretical and experimental studies and computer simulation of ring laser parameters are presented. The studies were carried out, taking into account changes in the Earth’s rotation speed around the axis and without taking into account changes in the Earth’s rotation speed. The obtained results indicate that the change in the speed of rotation of the Earth affects the accuracy of a ring laser. In order to reduce this error, it is necessary to fulfill the requirements of the rotational axis of the ring laser relative to the rotational axis of the Earth. Methods of the accelerated tests are imperfect for determining a term of storage. Therefore, tests during a real storage term remain the most reliable. The operation of the ring lasers in angle measuring instruments for more than 20 years has demonstrated their high stability. Using the ring laser, the angle measurement means of accuracy that exceeds the accuracy of the existing National Standards for a plane angle can be developed.

Artificial neural network as a part of intelligent precise goniometric system for analysis of spectral distribution intensity and definition of chemical composition of metal-containing substances

I. Cherepanska, Y. Koval, O. Bezvesilna, A. Sazonov, and S. Kedrovskyi, “Artificial neural network as a part of intelligent precise goniometric system for analysis of spectral distribution intensity and definition of chemical composition of metal-containing substances,” Metallofizika i Noveishie Tekhnologii, vol. 42, no. 10, pp. 1441–1454, 2020, doi: 10.15407/mfint.42.10.1441.

An artificial neural network (ANN) is proposed, which allows to make express-analysis of the chemical composition of production objects metalcontaining materials in automatic mode with high accuracy and real-time performance. The proposed ANN for automatic recognition of chemicals (ANN ARoC) is an alternative to traditional high-cost and time-consuming physical and chemical methods and labelling analysis, which are significantly complicate and slow down technological processes, as well as environmentally hazardous to human health and environment. The mean square error of proposed ANN ARoC does not exceed 5%, the time of determining the chemical composition of production objects metal-containing materials is not more than 2.5 s. ANN ARoC is built on the principle of a multilayer perceptron with a tunable structure of neurons and practically implemented in the form of an appropriate software product. The latter ensures its versatility in terms of the possibility of retraining and readjustment when new tasks arise in accordance with the rapidly changing conditions of modern dynamic production.

Physical and technical bases of experiment and diagnostics

I. Cherepanska, O. Bezvesilna, Yu. Koval, and A. Sazonov, “Physical and technical bases of experiment and diagnostics,” Metallofizika i Noveishie Tekhnologii, vol. 41, no. 2, pp. 263–278, 2019, doi: 10.15407/mfint.41.02.0263.

The article dedicated to urgent task—definition of chemical composition of metal-containing substances. The new precise intelligent goniometric system, which contains laser goniometer, CMOS image sensor, and artificial neural network, is proposed. This system combines the advantages such as safety for humans and environment, high productivity, usage simplicity, universality, automated processing of the measuring data.

Development of artificial neural network for determining the components of errors when measuring angles using a goniometric software-hardware complex

I. Cherepanska, O. Bezvesilna, A. Sazonov, S. Nechai, and O. Pidtychenko, “Development of artificial neural network for determining the components of errors when measuring angles using a goniometric software-hardware complex,” Eastern-European Journal of Enterprise Technologies, vol. 5, no. 9-95, pp. 43–51, 2018, doi: 10.15587/1729-4061.2018.141290.

We have developed an artificial neural network to determine the components of error in measuring the angles by automated goniometric systems whose change over time is a non-stationary random process. There are known techniques for processing measurement results and normalizing the systematic and random components of measurement errors, they have been applied for many years, they are well justified, maximally formalized, fundamentally different and are governed by respective regulations. However, it is still a rather difficult and labor-intensive procedure to determine exactly which component of an error is present in the measurement results. A given procedure is based on using the Fisher's dispersion criterion. In order to automate this procedure and improve performance efficiency of performed operations, we have developed an artificial neural network (ANN) and examined its functioning. It was determined that the proposed ANN could be successfully employed instead of known analytical-computational procedure using the Fisher's dispersion criterion. The application of ANN could significantly reduce labor intensity and improve the efficiency of determining the systematic and random components of measurement errors. This is predetermined by the capability of ANN to perform parallel processing of measurement data in real time. The practical implementation of ANN is based on using the neuro-simulator Neural Analyzer, analytical software Deductor Professional developed by BaseGroupLabs. We trained ANN and tested its functionality on the set of simulation results and actual multiple observations when measuring the plane angle of a 24-facet prism. The ability of ANN to quickly and correctly determine components of measurement errors at the stage of analysis of measurement information makes it possible to subsequently define methods for its further processing in accordance with regulatory requirements. That would improve the accuracy and reliability of measurement results as it could help avoid incorrect and inaccurate calculations when normalizing measurement errors.

Artificial neural network as a basic element of the automated goniometric system

I. Cherepanska, E. Bezvesilna, and A. Sazonov, “Artificial neural network as a basic element of the automated goniometric system,” Advances in Intelligent Systems and Computing, vol. 543, pp. 43–51, 2017, doi: 10.1007/978-3-319-48923-0_6.

The approach to automatic definition of components of the systematic error and the sources of its appearing in the automated goniometric system that is based on artificial neural networks are proposed in the article. In particular, the input and output vectors and the structure of artificial neural network are defined. For this propose systematic error of automated goniometric system is presented as a totality of instrumental, methodic and subjective components, and each of them has defined primary components. These components form the structure and content of the artificial neural network input vector. The structure and the content of the output vector allow to detect the causes of errors and to correct measuring result in future. Generalized methodics of the proposed “back-propagation” neural network is given. The last one will be trained by the supervised learning.

The procedure for determining the number of measurements in the normalization of random error of an informationmeasuring system with elements of artificial intelligence

I. Cherepanska, O. Bezvesilna, A. Sazonov, S. Nechai, and T. Khylchenko, “The procedure for determining the number of measurements in the normalization of random error of an informationmeasuring system with elements of artificial intelligence,” Eastern-European Journal of Enterprise Technologies, vol. 5, no. 9-89, pp. 58–67, 2017, doi: 10.15587/1729-4061.2017.109957.

Features of estimation and normalization of random components of the errors occurring in measurements with the help of goniometric systems were considered. A general procedure has been formulated that makes it possible to soundly determine the necessary and sufficient number of measurement repetitions to ensure accuracy and reliability of the obtained results. The procedure is based on application of mathematical apparatus of the probability theory, mathematical analysis and statistics, as well as the assumption that random errors obey the normal law of distribution of random quantities. Operatioability of the proposed procedure and effectiveness of its use have been experimentally confirmed. In particular, when comparing the obtained results with those in a similar work [7], the time taken to carry out measurements decreased by 1.3 times. That is, the effect of applying the proposed procedure is greater than the measurement costs while a high accuracy of 0.012 and reliability of 0.95 are maintained. The obtained results indicate the possibility of further extensive laboratory and industrial applications.