Применение методов машинного обучения для анализа зависимости сигналов виброускорения от усилий затяжки болтовых соединений

E M Sukharev

doi:10.22213/2413-1172-2024-3-79-85

Authors

E. M. Sukharev Siberian Transport University

DOI:

https://doi.org/10.22213/2413-1172-2024-3-79-85

Keywords:

threaded connections, Detrended fluctuations, fractal dimension, vibration acceleration, machine learning

Abstract

The article is devoted to the application of machine learning methods for the analysis of vibration acceleration signals in bolted joints that occur under impact. The relevance of the work is due to the need to ensure the reliability and operability of bolted joints under loads. One of the promising areas of non-destructive testing is the analysis of the characteristics of vibration acceleration signals that change with changes in the state of structures, for example, with an increase in the tightening torque. This allows for the timely detection of possible defects and the prevention of emergency situations, ensuring the safety and durability of structures. The vibration acceleration signals under impact action on a bolted joint were analyzed. After calculating the signal characteristics, data sets were formed, including the values of tightening torques and the corresponding calculated signal characteristics, a search for a correlation between the tightening torque of bolted joints and the obtained set of vibration signal parameters was carried out. The frequency spectrum of signals, the Higuchi fractal dimension, detrended fluctuations, spectral power density and position of signal peaks were calculated. Machine learning models such as decision trees, the nearest neighbor method, the k-means method and neural networks were used for the analysis. For these methods, an optimal set of parameters correlating with the tightening torque was searched for. The main results show that machine learning methods are effective in classifying signals and finding correlations with stress state parameters. They allow us to detect the relationship between a set of signal characteristics and tightening torque, which opens up opportunities for more accurate and reliable monitoring of the condition of bolted connections. This should help to increase their operational reliability and durability, as well as reduce the likelihood of failures and accidents. The use of such methods can improve the quality of monitoring and diagnostics of bolted connections.

Author Biography

E. M. Sukharev, Siberian Transport University

PhD in Engineering, Associate Professor

References

Qiu S., Cui X., Ping Z., Shan N., Li Z., Bao X., Xu X. (2023) Deep Learning Techniques in Intelligent Fault Diagnosis and Prognosis for Industrial Systems: A Review. Sensors, no. 23, p. 1305. https://doi.org/10.3390/s23031305

Zou F., Zhang H., Sang S. (2021) Bearing fault diagnosis based on combined multi-scale weighted entropy morphological filtering and bi-LSTM. Applied Intelligence, vol. 51, pp. 6647-6664. DOI: 10.1007/s10489-021-02229-1

Wang Haiya, Zhongqing Yu., Guo Lu. (2020) Real-time Online Fault Diagnosis of Rolling Bearings Based on KNN Algorithm. Journal of Physics: Conference Series, 1486, 032019. DOI: 10.1088/1742-6596/1486/3/032019

Gana M., Achour H., Belaid K., Chelli Z., Laghrouche M., Chaouchi A. (2022) Non-invasive intelligent monitoring system for fault detection in induction motor based on lead-free-piezoelectric sensor using ANN. Measurement Science and Technology, vol. 33. DOI: 10.1088/1361-6501/ac4b8f

Joshuva A., Sugumaran V. (2018) A machine learning approach for condition monitoring of wind turbine blade using autoregressive moving average (ARMA) features through vibration signals: a comparative study. Progress in Industrial Ecology: An International Journal, vol. 12, no. 14, pp. 14-34. DOI: 1504/PIE.2018.10016959

Altaf M., Akram T., Khan M.A., Iqbal M., Ch M.M.I., Hsu C.-H. (2022) A New Statistical Features Based Approach for Bearing Fault Diagnosis Using Vibration Signals. Sensors, vol. 22. DOI: 10.3390/s22052012

Wang L., Zhang C., Zhu J., Xu F. (2022) Fault Diagnosis of Motor Vibration Signals by Fusion of Spatiotemporal Features. Machines, vol. 10, p. 246. https://doi.org/10.3390/machines10040246

Jin Z., Han Q., Zhang K., Zhang Y. (2020) An intelligent fault diagnosis method of rolling bearings based on Welch power spectrum transformation with radial basis function neural network. Journal of Vibration and Control, no. 26(9-10), pp. 629-642. DOI: 10.1177/1077546319889859

Salim Lahmiri, Chakib Tadj, Christian Gargour, Stelios Bekiros (2022) Optimal tuning of support vector machines and k-NN algorithm by using Bayesian optimization for newborn cry signal diagnosis based on audio signal processing features, Chaos, Solitons & Fractals, vol. 167, p. 112972. DOI: 10.1016/j.chaos.2022.112972

Li J.-M., Wei H.-J., Wei, L.-D., Zhou, D.-P., Qiu Y. (2020) Extraction of Frictional Vibration Features with Multifractal Detrended Fluctuation Analysis and Friction State Recognition. Symmetry, no. 12, p. 272. DOI: 10.3390/sym12020272

Medina R., Sánchez R.-V., Cabrera D., Cerrada M., Estupiñan E., Ao W., Vásquez R.E. (2024) Scale-Fractal Detrended Fluctuation Analysis for Fault Diagnosis of a Centrifugal Pump and a Reciprocating Compressor. Sensors, 24, p. 461. DOI: 10.3390/s24020461

Agathiyan A., Nur Aisyah Abdul Fataf, Gowrisankar A. (2023) Explicit relation between Fourier transform and fractal dimension of fractal interpolation functions. The European Physical Journal Special Topics, 232:7, pp. 1077-1091. DOI: 10.1140/epjs/s11734-023-00779-8

Xue R., Liu J., Tang H. (2020) Two-Dimensional Jamming Recognition Algorithm Based on the Sevcik Fractal Dimension and Energy Concentration Property for UAV Frequency Hopping Systems. Information, no. 11, p. 520. DOI: 10.3390/info11110520

Shi C.-T. (2018) Signal Pattern Recognition Based on Fractal Features and Machine Learning. Applied Science, 8, p. 1327. DOI: 10.3390/app8081327

Setty V.A., Sharma A.S. (2015) Characterizing detrended fluctuation analysis of multifractional Brownian motion. Physica A: Statistical Mechanics and its Applications, vol. 419, pp. 698-706. DOI: 10.1016/j.physa.2014.10.016

Wanliss J. (2023) Fractal Methods in Nonequilibrium Systems. Fractal Analysis - Applications and Updates.Intech Open, Jul. 13, 2023. DOI: 10.5772/intechopen.1002058

Yang X., Xiang Y., Jiang B. (2022) On multi-fault detection of rolling bearing through probabilistic principal component analysis denoising and Higuchi fractal dimension transformation. Journal of Vibration and Control, no. 28(9-10), pp. 1214-1226. DOI: 10.1177/1077546321989527

Golmankhaneh A.K., Welch K., Tunç C. (2023) Classical mechanics on fractal curves. European Physical Journal Special Topics, vol. 232, pp. 991-999. DOI: 10.1140/epjs/s11734-023-00775-y

Gowrisankar A., Banerjee S. (2023) Framework of fractals in data analysis: theory and interpretation. European Physical Journal Special Topics, vol. 232, pp. 965-967. DOI: 10.1140/epjs/s11734-023-00890-w

Lei Li, Zhong Luo, Fayong Wu, Fengxia He, Kai Sun (2023) Frequency spectrum analysis of the rotor system with bolted joint: Numerical and experimental verification. Applied Mathematical Modelling, vol. 118, pp. 745-761. DOI: 10.1016/j.apm.2023.02.003

Brons M., Thomsen J.J., Sah S.M., Tcherniak D., Fidlin A. (2020) 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

Неразрушающий контроль : справочник : в 8 т. / под общ. ред. В. В. Клюева. Т. 7 : в 2 кн. Кн. 2 : Вибродиагностика / Ф. Я. Балицкий, А. В. Барков, Н. А. Баркова [и др.]. - 2-е изд., испр. М. : Машиностроение, 2006. 829 с.