Modeling of the Vibration Characteristics of Leaf Spring Systems using Radial Based Artificial Neural Networks

Öz

In this work, a Radial Basis Artificial Neural Network (RBANN) structure was proposed to model the acceleration effects occurring on leaf spring systems. In the experimental studies, pressure values of 25, 31.25, 37.5, 43.75 and 50 bar were applied to the steel leaf spring system by a hydraulic piston for 4 and 22 seconds and the acceleration effects that occur have been measured by a uniaxial accelerometer. From the experimental results, it was observed that the magnitude of acceleration was increasing at high pressure values. After the experimental studies, the acceleration data measured from the leaf spring system under the relevant working conditions were analyzed with RBANN structures having spread constant values of 0.5 and 1.0. From the simulation results, it was observed that the RBANN structure with a spread constant value of 0.5 predicts the real-time accelerations in the leaf spring system with higher accuracy. Consequently, it was observed that the real-time acceleration effects occurring on a leaf spring system can successfully be predicted with the proposed RBANN structure.

Anahtar Kelimeler

• Radial Basis Artificial Neural Networks
• Vibration Analysis
• Leaf Spring System

Radyal Tabanlı Yapay Sinir Ağları Kullanılarak Yaprak Yay Sistemi Titreşim Karakteristiğinin Modellenmesi

Öz

Bu çalışmada, yaprak yay sistemleri üzerinde oluşan ivme etkilerini modellemek amacıyla Radyal Tabanlı Yapay Sinir Ağı (RTYSA) yapısı önerilmiştir. Deneysel çalışmalarda, bir hidrolik piston tarafından çelik yaprak yay sistemine 4 ve 22 saniyelik sürelerde 25, 31.25, 37.5, 43.75 ve 50 bar basınç değerleri uygulanmış ve ardından oluşan ivme etkileri tek eksenli ivme sensörü kullanılarak ölçülmüştür. Deneysel sonuçlardan, yüksek basınç değerlerinde ivme genliklerinin arttığı gözlemlenmiştir. Deneysel çalışmalardan sonra, yaprak yay sisteminden ilgili çalışma şartları altında ölçülen ivme verileri yayılma sabiti 0.5 ve 1.0 olan RTYSA yapıları ile analiz edilmiştir. Simülasyon sonuçlarından, 0.5 yayılma sabitine sahip RTYSA yapısının yaprak yay sisteminde meydana gelen gerçek zamanlı ivme değerlerini daha yüksek doğrulukla tahmin edebildiği gözlemlenmiştir. Sonuç olarak, önerilen RTYSA yapısı ile bir yaprak yay sisteminde meydana gelen gerçek zamanlı ivme etkilerinin başarılı bir şekilde tahmin edilebildiği görülmüştür.

Anahtar Kelimeler

• Radyal Tabanlı Yapay Sinir Ağları
• Titreşim Analizi
• Yaprak Yay Sistemi

Kaynakça

1. Younesian, D., Fallahzadeh, M. S., 2014. Numerical and Experimental Analysis of Nonlinear Parabolic Springs Employed in Suspension System of freight cars, Automotive Science and Engineering, Cilt. 4, s. 812-826.
2. İşci, M. 2020. CNC Torna Tezgahlarda 5 Eksende Titreşim Ölçümü ve Yapay Sinir Ağlarıyla Modellenmesi, Erciyes Üniversitesi Fen Bilimleri Enstitüsü, Yüksek Lisans Tezi, 108s, Kayseri.
3. Shokrieh, M.M., Rezaei, D., 2003. Analysis and Optimization of a Composite Leaf Spring, Composite Structure, Cilt. 60, s. 317–325. DOI: 10.1016/S0263-8223(02)00349-5.
4. Odabaşı, V., Maglio, S., Martini, A., Sorrentino, S. 2019, Static Stress Analysis of Suspension Systems for a Solar-Powered Car, FME Transaction, Cilt. 47, s. 70-75. DOI: 10.5937/fmet1901070O
5. Ali, K. A., Manuel, D. J., Balamurugan, M., Murugan, M. S. 2021. Analysis of Composite Leaf Spring Using ANSYS Software, Materials Today: Proceedings, Cilt. 37, s. 2346-2351. DOI: 10.1016/j.matpr.2020.08.068
6. Venkatesan, M., Devaraj, D. H. 2012. Design and Analysis of Composite Leaf Spring in Light Vehicle, International Journal of Modern Engineering Research, Cilt. 2, s. 213-218.
7. Kong, Y.S., Abdullah, S., Omar, M.Z., Haris, S.M. 2016, Failure Assessment of a Leaf Spring Eye Design under Various Load Cases, Engineering Failure Analyses, Cilt. 63, s. 146–159. DOI:10.1016/j.engfailanal.2016. 02.017
8. Cheng, G., Chen, K., Zhang, Y., Chen, Y. 2022. The Fracture of Two-Layer Leaf Spring: Experiments and Simulation: Engineering Failure Analysis, Cilt. 133, DOI: 10.1016/j.engfailanal.2021.105971

9. Zhou, J., Hu, C., Wang, Z., Ren, Z., Wang, X., Mao, K. 2021. Study on Dynamic Characteristics of Leaf Spring System in Vibration Screen, Journal of Low Frequency Noise, Vibration and Active Control, Cilt. 40, s. 1818-1832. DOI: 10.1177/14613484211022974
10. Oztoprak, N., Gunes, M.D., Tanoglu, M., Aktas, E., Egilmez, O.O., Senocak, C., Kulac, G. 2018. Developing Polymer Composite-Based Leaf Spring Systems for Automotive Industry, Science Engineering Composite Materials, Cilt. 25, s. 1167–1176. DOI: 10.1515/secm-2016-0335
11. Koçhan, C., Belevi, M. 2017. Experimental Investigation of Fiber Reinforced Composite Leaf Springs, Materials Testing. Cilt. 59, s. 853– 858. DOI: 10.3139/120.111078
12. Lakshmi, B.V., Satyanarayana, I. 2012. Static and Dynamic Analysis on Composite Leaf Spring in Heavy Vehicle, International Journal of Advanced Engineering Research and Studies, Cilt. 2, s. 80–84.
13. Abdullah, L., Singh, S. S. K., Azman, A. H., Abdullah, S., Ihsan, A. K. A. M., Kong, Y. S. 2019. Fatigue Life-Based Reliability Assessment of a Heavy Vehicle Leaf Spring, International Journal of Structural Integrity, Cilt. 10, s. 726-736. DOI: 10.1108/IJSI-04-2019-0034
14. Çetinkaya, M. B., İşci, M. 2022. Analysis of the Vibration Characteristics of a Leaf Spring System Using Artificial Neural Networks, Sensors, Cilt. 22. DOI: 10.3390/s22124507
15. Jung, W. S., Bae, D. H., Song, G. W., Hyun, J. S., Kim, B. S. 2006. Fatigue Design of Leaf Spring Using Artificial Neural Network, In Key engineering materials. Cilt. 326, s. 1083-1086. Trans Tech Publications Ltd.
16. Juliyana, S. J., Prakash, J. U., Pallavi, P., Sadhana, A. D. 2017. Finite Element Analysis of Mono Composite Leaf Spring of Varying Thickness and Varying Width Used in Automotives, International Journal of Mechanical and Production Engineering Research and Development, Cilt. 7, s. 247-254. DOI: 10.24247/ijmperddec201727
17. Aher, V.K., Sonawane, P.M. 2012. Static and Fatigue Analysis of Multi Leaf Spring Used in the Suspension System of LCV, International Journal of Engineering Research and Applications, Cilt. 2, s. 1786–1791.
18. Topaç, C. 2019. Araçlarda Makas Sistemlerinin Uzun Ömür Testine Yönelik Stant Tasarımı ve Prototip Uygulaması, Erciyes Üniversitesi Fen Bilimleri Enstitüsü, Yüksek Lisans Tezi, 61s, Kayseri.
19. Haykin, S. S. 2009. Neural Networks and Learning Machines, Pearson: Upper Saddle River, NJ.
20. Broomhead, D. S., Lowe, D., 1988. Radial Basis Functions, Multi-Variable Functional Interpolation and Adaptive Networks, Royal Signals and Radar Establishment Malvern, United Kingdom.