Fault Diagnosis of Suspension System Based on Spectrogram Image and Vision Transformer

• Autorzy: Arun Balaji , Venkatesh Naveen S , Sugumaran V

Identyfikatory

DOI

10.17531/ein/174860

• Języki publikacji: EN

Abstrakty

EN

The suspension system in an automobile is essential for comfort and control. Implementing a monitoring system is crucial to ensure proper function, prevent accidents, maintain performance, and reduce both downtime and costs. Traditionally, diagnosing faults in suspension systems has relied on specialized setups and vibration analysis. The conventional approach typically involves either wavelet analysis or a machine learning approach. While these methods are effective, they often demand specialized expertise and time consumable. Alternatively, using deep learning for suspension system fault diagnosis enables faster and more precise real-time fault detection. This study explores the use of vision transformers as an innovative approach to fault diagnosis in suspension systems, utilizing spectrogram images. The process involves extracting spectrogram images from vibration signals, which serve as inputs for the vision transformer model. The test results demonstrate that the proposed fault diagnosis system achieves an impressive accuracy rate of 98.12% in identifying faults.

Słowa kluczowe

EN

condition monitoring; vision transformer; fault diagnosis; image generation; McPherson suspension system

• Wydawca: Polskie Naukowo-Techniczne Towarzystwo Eksploatacyjne
• Czasopismo: Eksploatacja i Niezawodność
• Rocznik: 2024
• Tom: Vol. 26, no. 1
• Strony: art. no. 174860
• Opis fizyczny: Bibliogr. 29 poz., fot., rys., tab., wykr.

Twórcy

autor

Arun Balaji

• School of Mechanical Engineering (SMEC),Vellore Institute of Technology,Chennai -600127, India

• https://orcid.org/0000-0001-5008-3252

autor

Venkatesh Naveen S

• School of Mechanical Engineering (SMEC),Vellore Institute of Technology,Chennai -600127, India

• https://orcid.org/0000-0002-4034-8859

autor

Sugumaran V

• School of Mechanical Engineering (SMEC),Vellore Institute of Technology,Chennai -600127, India

• https://orcid.org/0000-0002-5323-6418

Bibliografia

• 1. Fedotov AI, Kuznetsov NY, Lysenko A V, Vlasov VG. Car suspension system monitoring under road conditions. AIP Conf Proc. 2017;1915(December 2017):1–7. https://doi.org/10.1063/1.5017362
• 2. Ferrari L, Cattini S, Rovati L, Bosi A. A simple measuring system for automotive damper wear estimation. In: 2012 IEEE I2MTC -International Instrumentation and Measurement Technology Conference, Proceedings. 2012. p. 539–43. https://doi.org/10.1109/I2MTC.2012.6229266
• 3. Lozoya-Santos J, Tudón-Martínez JC, Morales-Menendez R, Ramírez-Mendoza R, Gutierrez AM. Fault detection for an automotive MR damper. In: IFAC Proceedings Volumes (IFAC-PapersOnline). 2012. p. 1023–8. https://doi.org/10.3182/20120523-3-RO-2023.00247
• 4. Fischer D, Schöner H-P, Isermann R. Model based Fault Detection for an Active Vehicle Suspension. IFAC Proc Vol [Internet]. 2004 Apr;37(22):403–8. Available from:https://doi.org/10.1016/S1474-6670(17)30377-4
• 5. Arana C, Evangelou SA, Dini D. Series Active Variable Geometry Suspension application to comfort enhancement. Control Eng Pract [Internet]. 2017;59(November 2016):111–26. Available from: http://dx.doi.org/10.1016/j.conengprac.2016.11.011
• 6. Azadi S, Soltani A. Fault detection of vehicle suspension system using wavelet analysis. Veh Syst Dyn. 2008;47(4):403–18. https://doi.org/10.1080/00423110802094298
• 7. Ferreira C, Ventura P, Morais R, Valente ALG, Neves C, Reis MC. Sensing methodologies to determine automotive damper condition under vehicle normal operation. Sensors Actuators, A Phys. 2009;156(1):237–44. https://doi.org/10.1016/j.sna.2009.03.035
• 8. Hamed M, Tesfa B, Gu F, Ball AD. Effects of Tyre Pressure on Vehicle Suspension Performance. Int Lett Chem Phys Astron. 2015;55:102–11. https://doi.org/10.56431/p-l6t1lc
• 9. Isermann R, Wesemeier D. Indirect Vehicle Tire Pressure Monitoring with Wheel and Suspension Sensors [Internet]. Vol. 42, IFAC Proceedings Volumes. IFAC; 2009. 917–922 p. Available from: http://dx.doi.org/10.3182/20090630-4-ES-2003.00151
• 10. Zheng J, Ying W, Pan H, Feng K, Tang X, Xu Y, et al. Advantages of using statistical models for detecting faulty components in railway bogies against using simple criteria as defined in standards. Mech Syst Signal Process [Internet]. 2019 Jul 26 [cited 2022 Nov 8];1(1):1–6. Available from: https://www.mdpi.com/2075-1702/11/8/778
• 11. Miletiev R, Simeonov I, Iontchev E, Yordanov R. Time and frequency analysis of the vehicle suspension dynamics. Int J Syst Appl Eng Dev. 2013;7(5):287–94.
• 12. Hardikar N, Kulkarni A, Telang A, Kanthale VS. Analysis and Simulation of Elastomeric Strut Mount and its applications for Failure Investigation. Int J Curr Eng Technol. 2011;4(4):356–60.
• 13. Ferreira C. A New Methodology for Detection of a Loose or Worn ball joint used in vehicles suspension system. Gomes JFS, editor. Conf Theor Exp Mech Mater / 11th Natl Congr Exp Mech Porto/Portugal. 2018;10(November):1–6.
• 14. Iontchev E, Miletiev R, Bashev V, Simeonov I. Study of the dynamic response and status of the vehicle suspension elements. 2013;3(1):45–51. https://doi.org/10.1016/S1474-6670(17)58392-5
• 15. Weispfenning T, Leonhardt S. Model-Based Identification of a Vehicle Suspension Using Parameter Estimation and Neural Networks. IFAC Proc Vol. 1996;29(1):4510–5.
• 16. Jiao N, Guo J, Liu S. Hydro-Pneumatic Suspension System Hybrid Reliability Modeling Considering the Temperature Influence. IEEE Access. 2017;5:19144–53. https://doi.org/10.1109/ACCESS.2017.2751505
• 17. Melnik R, Koziak S, Dižo J, Kuźmierowski T, Piotrowska E. Feasibility Study of a Rail Vehicle Damper Fault Detection By Artificial Neural Networks. Eksploat i Niezawodn. 2023;25(1):0–3. https://doi.org/10.17531/ein.2023.1.5
• 18. Wu J, Cui J, Shu Y, Wang Y, Chen R, Wang L. Multi-level health degree analysis of vehicle transmission system based on PSO-BP neural network data fusion. Eksploat i Niezawodn. 2023;25(1):0–2. https://doi.org/10.17531/ein.2023.1.4
• 19. Liu F, Gu F, Zhao Y, Ball A. A validation study of ACS-SSI for online condition monitoring of vehicle suspension systems. In: Vibroengineering Procedia. 2016. p. 369–75.
• 20. Arun Balaji P, Sugumaran V. A Bayes learning approach for monitoring the condition of suspension system using vibration signals. IOP Conf Ser Mater Sci Eng. 2021;https://doi.org/10.1088/1757-899X/1012/1/012029
• 21. Egaji OA, Chakhar S, Brown D. An innovative decision rule approach to tyre pressure monitoring. Expert Syst Appl [Internet]. 2019;124:252–70. Available from: https://doi.org/10.1016/j.eswa.2019.01.051
• 22. Anoop PS, Sugumaran V. Classifying machine learning features extracted from vibration signal with logistic model tree to monitor automobile tyre pressure. SDHM Struct Durab Heal Monit. 2017;11(2):191–208.
• 23. Karabacak Yunus Emre. Deep learning-based CNC milling tool wear stage estimation with multi-signal analysis. Eksploat i Niezawodn –Maint Reliab. 2023;25(3):0–2. https://doi.org/10.17531/ein/168082
• 24. Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, et al. Attention is all you need. Adv Neural Inf Process Syst. 2017;2017-Decem(Nips):5999–6009.
• 25. Wang Q, Li B, Xiao T, Zhu J, Li C, Wong DF, et al. Learning deep transformer models for machine translation. ACL 2019 -57th Annu Meet Assoc Comput Linguist Proc Conf. 2020;1810–22. https://doi.org/10.18653/v1/P19-1176
• 26. Ferreira C. A New Methodology for Detection of a Loose or Worn ball joint used in vehicles suspension system. Conf Theor Exp Mech Mater / 11th Natl Congr Exp Mech Porto/Portugal. 2018;(November):1–6.
• 27. Khode SS. A Review on Independent Suspension System of Light Commercial Vehicle. IOSR J Mech Civ Eng. 2017 Mar;17(10):14–9. https://doi.org/10.9790/1684-17010061419
• 28. Muturatnam AB, Sridharan NV, Sreelatha AP, Vaithiyanathan S. Enhanced Tyre Pressure Monitoring System for Nitrogen Filled Tyres Using Deep Learning. Machines. 2023;11(4). https://doi.org/10.3390/machines11040434
• 29. Youcef Khodja A, Guersi N, Saadi MN, Boutasseta N. Rolling element bearing fault diagnosis for rotating machinery using vibration spectrum imaging and convolutional neural networks. Int J Adv Manuf Technol. 2020;106(5–6):1737–51. https://doi.org/10.1007/s00170-019-04726-7