Tire Hardness Modeling Based on Longitudinal Ultrasonic Velocity Using the Gaussian Process Regression

Document Type : Research Article

Authors

1 Department of mechanical engineering, Birjand University of Technology,Birjand

2 Department of mechanical engineering, University of Birjand

3 Department of computer engineering, Birjand University of Technology

4 Department of chemical engineering, Birjand University of Technology

Abstract

Non-destructive tests have capabilities to investigate and identify the defects and properties of the test piece without changing the physical and mechanical properties of the sample. The non-destructive ultrasonic test has been used in many investigations to study different material properties such as mechanical and structural properties. The ultrasonic wave propagation velocities have been widely used for metal hardness measurement. In this study, for the first time, non-destructive ultrasonic testing has been employed to measure the hardness of rubber compounds using Gaussian process regression. Eighty-seven samples with different formulations were prepared and vulcanized. After the vulcanization, the compound hardness of the samples and the longitudinal ultrasonic wave velocity through them was measured. The result of Gaussian process regression model shows that this model performs well and able to predict tire hardness. Also, investigating repeatability shows that this method can be a good alternative for conventional hardness testing method in measuring the hardness of rubbers. According to the low time of the test in this method and no need to sample preparation, the proposed method can be used in tire production lines.

Keywords

Main Subjects

References

[1] V. Rajendran, S.M. Kumaran, T. Jayakumar, P. Palanichamy, P. Shankar, B. Raj, Microstructure and ultrasonic behaviour on thermal heat-treated Al–Li 8090 alloy, Journal of Alloys and Compounds, 478(1) (2009) 147-153.
[2]  H.A. Afifi, A.M. El Sayed, Ultrasonic properties of ENR- EPDM rubber blends, Polymer bulletin, 50(1-2) (2003) 115-122.
[3]  A. Higazy, H. Afifi, A. Khafagy, M. El-Shahawy, A. Mansour, Ultrasonic studies on polystyrene/styrene butadiene rubber polymer blends filled with glass fiber and talc, Ultrasonics, 44 (2006) e1439-e1445.
[4]   M.A. El-Hadek, Fracture Mechanics of Rubber Epoxy Composites, Metallurgical and Materials Transactions A, 45(9) (2014) 4046-4054.
[5] P. Kerdtongmee, C. Pumdaung, S. Danworaphong, Quantifying dry rubber content in latex solution using an ultrasonic pulse, Measurement Science Review, 14(5) (2014) 252-256.
[6] M.  Taheri,  A.  Foorginejad,  M.  Shiva,  S.M.  Emam, Haddadi,  Investigation  of  rubber  formulation  by measuring   ultrasonic  propagation  velocity,  Journal  of Solid and Fluid Mechanics, 6(2) (2016) 285-294.
[7]  F. Uzun, A.N. Bilge, Application of  ultrasonic  waves in measurement of hardness of welded carbon steels, Defence Technology, 11(3) (2015) 255-261.
[8]    N. Korde, T. Kundu, Material hardness and ageing measurement using guided ultrasonic waves, Ultrasonics, 53(2) (2013) 506-510.
[9]  A.B. Bouda, A. Benchaala, K. Alem, Ultrasonic characterization of materials hardness, Ultrasonics, 38(1) (2000) 224-227.
[10] R.S. Michalski, J.G. Carbonell, T.M. Mitchell, Machine learning: An artificial intelligence approach, Springer Science & Business Media, 2013.
[11]  T. Hastie, R. Tibshirani, J. Friedman, Overview of supervised learning, in: The elements of statistical learning, Springer, 2009, pp. 9-41.
[12] R.J. Carroll, D. Ruppert, L.A. Stefanski, J. Buonaccorsi, Measurement error in nonlinear models, Metrika, 45(3) (1997) 182-183.
[13] M. Ebden, Gaussian processes for regression: A quick introduction, The Website of Robotics Research Group in Department on Engineering Science, University of Oxford, (2008).
[14] R.M. Neal, Bayesian learning for neural networks, Springer Science & Business Media, 2012.
[15] C.K. Williams, C.E. Rasmussen, Gaussian processes for regression, in: Advances in neural information processing systems, 1996, pp. 514-520.
[16] C.M. Bishop, Pattern recognition and machine learning, springer, 2006.
[17] C.E. Rasmussen, C.K. Williams, Gaussian processes for machine learning, MIT press Cambridge, 2006.
[18]   D.J. MacKay, Introduction to Gaussian processes,
NATO ASI Series F Computer and Systems Sciences, 168 (1998) 133-166.
[19] R. Fletcher, Conjugate gradient methods for indefinite systems, Numerical analysis, (1976) 73-89.
[20] D.M. Olsson, L.S. Nelson, The Nelder-Mead simplex procedure for function minimization, Technometrics, 17(1) (1975) 45-51.
[21]  B. Hull, V. John, Non-destructive testing, (1988).
[22] J. Weston, A. Elisseeff, G. Bakir, F. Sinz, The spider machine learning toolbox, Software available at http:// www. kyb. tuebingen. mpg. de/bs/people/spider, (2005).
Amirkabir Journal of Mechanical Engineering
Volume 51, Issue 5
November and December 2019
Pages 1005-1016

Files

Share

How to cite

Statistics