Yuriy Babay
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yuriy Babay has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Serhii Hubskyi
National Technical University “Kharkiv Polytechnic Institute”
5 shared publications - Andrii Yavtushenko3 shared publications
Andrii Yavtushenko
National Technical University “Kharkiv Polytechnic Institute”
1 shared publicationAnton Sergienko
National Technical University “Kharkiv Polytechnic Institute”
1 shared publication- Denys Baranovskyi
Rzeszów University of Technology
1 shared publication Dmytro Cherkashyn
1 shared publication
Latest Publications
- Open Access
- 13 May 2026
- Published by SAGE Publications in Journal of Low Frequency Noise, Vibration and Active Control
An integrated IoT framework for intelligent vibration-based fault diagnosis of internal combustion engines
This study presents an intelligent IoT-based approach to vibration diagnostics of internal combustion engines using a wireless sensing architecture for real-time condition monitoring. The proposed system enables continuous acquisition of vibration signals with remote data transmission to a server, where signal preprocessing, Kalman filtering, root mean square (RMS) computation, frequency-domain analysis using Fast Fourier Transform, and multidimensional feature extraction are performed. Experimental validation was conducted on a laboratory test bench under healthy and artificially induced outer-ring bearing defect conditions at rotational speeds of 500, 1000, and 1500 rpm. Classical vibration analysis revealed a consistent 34–37% increase in RMS values in the presence of a defect, along with characteristic spectral components corresponding to the calculated fault frequencies. To enhance diagnostic robustness, a supervised machine learning framework was implemented using time- and frequency-domain features. Comparative evaluation demonstrated that machine learning models significantly outperform conventional RMS threshold-based diagnostics. The Random Forest classifier achieved up to 97% classification accuracy (ROC-AUC = 0.99) under random split validation and maintained 94% accuracy under cross-speed validation, confirming strong generalization capability across varying operating regimes. The results demonstrate that integrating IoT-based sensing, advanced signal processing, and intelligent classification provides a scalable and reliable solution for predictive maintenance of ICE systems in transportation, energy, and industrial applications.
- 13 May 2026
- Published by SAGE Publications in Journal of Low Frequency Noise, Vibration and Active Control
Open AccessAn integrated IoT framework for intelligent vibration-based fault diagnosis of internal combustion engines
This study presents an intelligent IoT-based approach to vibration diagnostics of internal combustion engines using a wireless sensing architecture for real-time condition monitoring. The proposed system enables continuous acquisition of vibration signals with remote data transmission to a server, where signal preprocessing, Kalman filtering, root mean square (RMS) computation, frequency-domain analysis using Fast Fourier Transform, and multidimensional feature extraction are performed. Experimental validation was conducted on a laboratory test bench under healthy and artificially induced outer-ring bearing defect conditions at rotational speeds of 500, 1000, and 1500 rpm. Classical vibration analysis revealed a consistent 34–37% increase in RMS values in the presence of a defect, along with characteristic spectral components corresponding to the calculated fault frequencies. To enhance diagnostic robustness, a supervised machine learning framework was implemented using time- and frequency-domain features. Comparative evaluation demonstrated that machine learning models significantly outperform conventional RMS threshold-based diagnostics. The Random Forest classifier achieved up to 97% classification accuracy (ROC-AUC = 0.99) under random split validation and maintained 94% accuracy under cross-speed validation, confirming strong generalization capability across varying operating regimes. The results demonstrate that integrating IoT-based sensing, advanced signal processing, and intelligent classification provides a scalable and reliable solution for predictive maintenance of ICE systems in transportation, energy, and industrial applications.
- Open Access
- 7 May 2026
- Published by National Technical University Kharkiv Polytechnic Institute in Bulletin of the National technical university "Kharkiv Polytechnic Institute" Series: Techniques in a machine industry
- No. 2(12),p. 163-173
COMPARATIVE ANALYSIS OF VIBRATIONS USING FAST FOURIER TRANSFORM AND WAVELET TRANSFORM
The article examines the application of vibration signal processing methods for diagnosing the technical condition of rotor systems. A comparative analysis of the Fast Fourier Transform (FFT), Continuous Wavelet Transform (CWT), and Discrete Wavelet Transform (DWT) was conducted to detect anomalies and impulsive disturbances. FFT enables the evaluation of the spectral content of a signal but lacks time localization of frequency components. In contrast, CWT and DWT provide time-frequency localization and allow the identification of hidden defects, which is crucial for analyzing non-stationary processes. Experimental results obtained from the RK-4 test bench confirm the effectiveness of wavelet analysis for high-speed rotor operation and modeling of faults such as imbalance, cracks, or friction. The proposed combination of methods improves diagnostic accuracy and enables efficient condition monitoring of equipment.
- 7 May 2026
- Published by National Technical University Kharkiv Polytechnic Institute in Bulletin of the National technical university "Kharkiv Polytechnic Institute" Series: Techniques in a machine industry
- No. 2(12),p. 163-173
Open AccessCOMPARATIVE ANALYSIS OF VIBRATIONS USING FAST FOURIER TRANSFORM AND WAVELET TRANSFORM
The article examines the application of vibration signal processing methods for diagnosing the technical condition of rotor systems. A comparative analysis of the Fast Fourier Transform (FFT), Continuous Wavelet Transform (CWT), and Discrete Wavelet Transform (DWT) was conducted to detect anomalies and impulsive disturbances. FFT enables the evaluation of the spectral content of a signal but lacks time localization of frequency components. In contrast, CWT and DWT provide time-frequency localization and allow the identification of hidden defects, which is crucial for analyzing non-stationary processes. Experimental results obtained from the RK-4 test bench confirm the effectiveness of wavelet analysis for high-speed rotor operation and modeling of faults such as imbalance, cracks, or friction. The proposed combination of methods improves diagnostic accuracy and enables efficient condition monitoring of equipment.
- 30 December 2025
- Published by Admiral Makarov National University of Shipbuilding in Collection of Scientific Publications NUS
- No. 4 (502),p. 89-98
ANALYSIS OF BEARING VIBRATION SIGNALS USING THE RMS METHOD
- 30 December 2025
- Published by Admiral Makarov National University of Shipbuilding in Collection of Scientific Publications NUS
- No. 4 (502),p. 89-98
ANALYSIS OF BEARING VIBRATION SIGNALS USING THE RMS METHOD
- Open Access
- 17 July 2025
- Published by National Technical University Kharkiv Polytechnic Institute in Bulletin of the National Technical University «KhPI». Series: Automobile and Tractor Construction
- No. 1,p. 3-11
MODERN TECHNOLOGIES OF ROLL FORMING FOR 3D-BENT PROFILES AND THEIR APPLICATION IN THE AUTOMOTIVE INDUSTRY
The paper provides an analyzes modern technologies of roll forming for 3D-bent profiles and their applications in the automotive industry, construction, manufacturing, and agriculture. Approaches to optimizing the number of technological transitions are considered, contributing to reduced production time and increased productivity. Special attention is given to controlling the stress-strain state of the metal, which is crucial for ensuring high product quality. The impact of sensor technologies on real-time process monitoring is assessed, allowing for defect reduction and lower production costs. The use of advanced solutions in roll forming opens new opportunities for production optimization.
- 17 July 2025
- Published by National Technical University Kharkiv Polytechnic Institute in Bulletin of the National Technical University «KhPI». Series: Automobile and Tractor Construction
- No. 1,p. 3-11
Open AccessMODERN TECHNOLOGIES OF ROLL FORMING FOR 3D-BENT PROFILES AND THEIR APPLICATION IN THE AUTOMOTIVE INDUSTRY
The paper provides an analyzes modern technologies of roll forming for 3D-bent profiles and their applications in the automotive industry, construction, manufacturing, and agriculture. Approaches to optimizing the number of technological transitions are considered, contributing to reduced production time and increased productivity. Special attention is given to controlling the stress-strain state of the metal, which is crucial for ensuring high product quality. The impact of sensor technologies on real-time process monitoring is assessed, allowing for defect reduction and lower production costs. The use of advanced solutions in roll forming opens new opportunities for production optimization.
- Open Access
- 30 June 2025
- Published by Ukrainian State University of Science and Technologies in Theory and practice of metallurgy
- No. 2,p. 75-80
Simulation of roll forming for U-shaped bent profiles
Purpose. To develop an approach for simulating the roll forming process of U-shaped bent profiles using the QForm software package. Methodology. The study is based on the finite element method implemented in QForm. The process was simulated in a 3D environment, accounting for elastic–plastic deformation, using a single operation of the «Sheet Bulk Forming» type. A sequential forming scheme was implemented using 12 roll stands, which incorporated the elastic–plastic properties of the material. Appropriate boundary conditions were defined to replicate real technological parameters of the roll forming process. Results. The simulation yielded stress and strain distributions in the blank at various stages of its passage through the roll stands. It was found that maximum plastic strains occur in the bending zones, while the edge regions are predominantly subjected to tensile stresses. The simulation results are consistent with the physical nature of the bending process and confirm the validity of the proposed approach. Scientific Novelty. An adaptation of the QForm software package is proposed for simulating the roll forming of bent profiles, which is not covered by its standard modules. Simulation algorithm and boundary condition setup were developed, enabling the analysis of the stress–strain state of the blank during profile formation. Practical Significance. The results of the study can be used to optimize technological parameters of the roll forming process, reduce the likelihood of defect formation, and expand the functional capabilities of QForm in the field of sheet metal forming simulation. The proposed approach is valuable for technologists, engineers, designers, and researchers working in the field of metal forming.
- 30 June 2025
- Published by Ukrainian State University of Science and Technologies in Theory and practice of metallurgy
- No. 2,p. 75-80
Open AccessSimulation of roll forming for U-shaped bent profiles
Purpose. To develop an approach for simulating the roll forming process of U-shaped bent profiles using the QForm software package. Methodology. The study is based on the finite element method implemented in QForm. The process was simulated in a 3D environment, accounting for elastic–plastic deformation, using a single operation of the «Sheet Bulk Forming» type. A sequential forming scheme was implemented using 12 roll stands, which incorporated the elastic–plastic properties of the material. Appropriate boundary conditions were defined to replicate real technological parameters of the roll forming process. Results. The simulation yielded stress and strain distributions in the blank at various stages of its passage through the roll stands. It was found that maximum plastic strains occur in the bending zones, while the edge regions are predominantly subjected to tensile stresses. The simulation results are consistent with the physical nature of the bending process and confirm the validity of the proposed approach. Scientific Novelty. An adaptation of the QForm software package is proposed for simulating the roll forming of bent profiles, which is not covered by its standard modules. Simulation algorithm and boundary condition setup were developed, enabling the analysis of the stress–strain state of the blank during profile formation. Practical Significance. The results of the study can be used to optimize technological parameters of the roll forming process, reduce the likelihood of defect formation, and expand the functional capabilities of QForm in the field of sheet metal forming simulation. The proposed approach is valuable for technologists, engineers, designers, and researchers working in the field of metal forming.