Классификация сигналов виброускорения при различных усилиях затяжки болтовых соединений

E M Sukharev

doi:10.22213/2413-1172-2025-3-42-52

Authors

E. M. Sukharev Siberian State Transport University

DOI:

https://doi.org/10.22213/2413-1172-2025-3-42-52

Keywords:

threaded connections, Fourier spectrum, wavelet transform, dynamic time warping, fractal dimension, vibration acceleration, machine learning

Abstract

The paper considers the application of time proximity parameters and wavelet transform in combination with fractal and spectral characteristics for classification of vibration acceleration signals occurring at different tightening levels of bolted joints. The study is aimed at identifying the relationships between the characteristics of vibration signals and the tightening state, which allows improving the diagnostics and monitoring of the technical condition of joints. For vibration acceleration signals, proximity characteristics were calculated using dynamic transformation of the time scale, frequency and amplitude of the Fourier spectrum, Welch power spectral density parameters, spectral descriptors for the windowed Fourier transform, Higuchi fractal dimension, detrended fluctuations, and wavelet transform parameters. The use of the wavelet transform allows analyzing the time changes of signals, which helps to identify key features in the data dynamics. At the same time, fractal methods help to detect complex structures and patterns, which can significantly improve the classification accuracy. This work is aimed at developing effective approaches to the analysis of vibration signals using machine learning methods, which is important for improving the reliability and safety of bolted joints in various industries.

Author Biography

E. M. Sukharev, Siberian State Transport University

PhD in Engineering, Associate Professor

References

Сухарев Е. М. Применение методов машинного обучения для анализа зависимости сигналов виброускорения от усилий затяжки болтовых соединений // Вестник ИжГТУ имени М. Т. Калашникова. 2024. Т. 27, № 3. С. 79-85. DOI: 10.22213/2413-1172-2024- 3-79-85

Jing Lin, Liangsheng Qu (2000), Feature extraction based on morlet wavelet and its application for mechanical fault diagnosis. Journal of Sound and Vibration, vol. 234, iss. 1, pp. 135-148. DOI: 10.1006/jsvi.2000. 2864

Беляев А. А., Кононов Д. П., Кротов С. В. Проблемы диагностики современных тепловозных двигателей // Бюллетень результатов научных исследований. 2024. Вып. 1. С. 7-20. DOI: 10.20295/2223-9987-2024-01-7-20

Qarib H. and Adeli H. (2016) A comparative study of signal processing methods for structural health monitoring. Journal of Vibroengineering, vol. 18, no. 4, pp. 2186-2204. DOI: 10.21595/jve.2016.17218

Amezquita-Sanchez J.P., Adeli H. (2016) Signal Processing Techniques for Vibration-Based Health Monitoring of Smart Structures. Archives of Computational Methods in Engineering, vol. 23, pp. 1-15. DOI: 10.1007/s11831-014-9135-7

Ahmed Silik, Mohammad Noori, Wael A. Altabey, Ramin Ghiasi, Zhishen Wu. (2021) Comparative Analysis of Wavelet Transform for Time-Frequency Analysis and Transient Localization in Structural Health Monitoring, Structural Durabilityand Health Monitoring, vol. 15, iss. 1, pp. 1-22. DOI: 10.32604/sdhm.2021.012751

Gang Wang, Carlos Lopez-Molina, Guillermo Vidal-Diez de Ulzurrun, Bernard De Baets (2019) Noise-robust line detection using normalized and adaptive second-order anisotropic Gaussian kernels. Signal Processing, vol. 160, pp. 252-262. DOI: https://doi.org/10.1016/j.sigpro.2019.02.027

Guo T., Zhang T., Lim E., López-Benítez M., Ma F., Yu L. (2022) A Review of Wavelet Analysis and Its Applications: Challenges and Opportunitie. IEEE Access, vol. 10, pp. 58869-58903. DOI: 10.1109/ACCESS.2022.3179517

Гусев Г., Епин В., Цветков Р., Шестаков А. К вопросу о развитии методов измерения вибрации строительных конструкций // Вестник Пермского федерального исследовательского центра. 2023. № 4. C. 32-40. DOI: 10.7242/2658-705X/2023.4.3

Chen J., Lin C., Peng D. and Ge H. (2020) Fault Diagnosis of Rotating Machinery: A Review and Bibliometric Analysis. IEEE Access, vol. 8, pp. 224985-225003. DOI: 10.1109/ACCESS.2020.3043743

Chatterjee P. (2015). Wavelet Analysis in Civil Engineering (1st ed.). CRC Press. DOI: 10.1201/b18057

Методы обработки сигналов акселерометров на железнодорожном транспорте с использованием вейвлет-преобразования / А. М. Боронахин, А. В. Большакова, Д. М. Клионский, Д. Ю. Ларионов, Р. В. Шалымов // Известия высших учебных заведений России. Радиоэлектроника. 2024. Т. 27, № 1. С. 6-16. DOI: https://doi.org/10.32603/1993-8985-2024-27-1-6-16

Mallat S. (1999) A Wavelet Tour of Signal Processing, Cambridge University Press, New York, 1999. DOI: 10.1016/B978-0-12-374370-1.X0001-8

Agathiyan A., Fataf N.A.A., Gowrisanka A. (2023) Explicit relation between Fourier transform and fractal dimension of fractal interpolation functions. European Physical Journal Special Topics, vol. 232, pp. 1077-1091. DOI: 10.1140/epjs/s11734-023-00779-8

Gowrisankar A., Banerjee S. (2023) Framework of fractals in data analysis: theory and interpretation. European Physical Journal Special Topics, no. 232, pp. 965-967. DOI: 10.1140/epjs/s11734-023-00890-w

Yutao Liu, Yong-An Zhang, Ming Zeng, Jie Zhao (2024) A novel distance measure based on dynamic time warping to improve time series classification. Information Sciences, vol. 656, p. 119921. DOI: 10.1016/j.ins. 2023.119921

Shifaz A., Pelletier C., Petitjean F., Geofrey I. (2023) Elastic similarity and distance measures for multivariate time series. Knowledge and Information Systems, no. 65, pp. 2665-2698. DOI: 10.1007/s10115-023-01835-4

Kate R.J. (2016) Using dynamic time warping distances as features for improved time series classification. Data Mining and Knowledge Discovery, 30, pp. 283-312. DOI: 10.1007/s10618-015-0418-x

Goncharov A.V., Strijov V.V. (2018) Analysis of Dissimilarity Set Between Time Series.Computational Mathematics and Modeling, 29, pp. 359-366. DOI: 10.1007/s10598-018-9415-4

Brøns M., Thomsen J.J., Sah S.M., Tcherniak D., Fidlin A. (2021) Estimating bolt tension from vibrations: Transient features, nonlinearity, and signal processing. Mechanical Systems and Signal Processing, 150, Article 107224. DOI: 10.1016/j.ymssp.2020.107224

Куц М. С. Экспериментальное исследование влияния усилия затяжки болтов на резонансные частоты консольно закрепленной балки // Известия высших учебных заведений. Машиностроение. 2018. № 9 (702). С. 37-43. DOI: 10.18698/0536-1044-2018-9-37-43

Barbara Zaparoli Cunha, Christophe Droz, Abdel-Malek Zine, Stéphane Foulard, Mohamed Ichchou (2023) A review of machine learning methods applied to structural dynamics and vibroacoustic. Mechanical Systems and Signal Processing, vol. 200, p. 110535. DOI: 10.1016/j.ymssp.2023.110535

Namkyoung Lee, Joohyun Woo, Sungryul Kim (2024) A deep reinforcement learning ensemble for maintenance scheduling in offshore wind farms. Applied Energy, vo. 377, part A, p. 124431. DOI: 10.1016/j.apenergy.2024.124431

Xiaofeng Dong, Zhuo Miao, Yuchao Li, Huan Zhou, Wenqian Li (2024) One data-driven vibration acceleration prediction method for offshore wind turbine structures based on extreme gradient boosting. Ocean Engineering, vol. 307, p. 118176. DOI: 10.1016/j.oceaneng.2024.118176

Mendonça M.O.K., Apolinário I.F., Diniz P.S.R. (2024) Introduction to signal processing and machine learning theory. Signal Processiing and Machine Learning Theory, pp. 1-34. DOI: 10.1016/b978-0-32-391772-8.00007-7