Application of Artificial Neural Network and Multi-magnetic NDE Methods to Determine Mechanical Properties of Plain Carbon Steels Subjected to Tempering Treatment

Document Type : Original Article

Authors

1 Department of Electrical and Bioelectric Engineering, Sadjad University of Technology, Mashhad, Iran

2 Department of Mechanical and Materials Engineering, Sadjad University of Technology, Mashhad, Iran

3 Center of Nondestructive Evaluation (CNDE), Sadjad University of Technology, Mashhad, Iran

Abstract

The present paper shows the results of applying an artificial neural network to three non-destructive magnetic methods including magnetic hysteresis loop (MHL), eddy current (EC), and magnetic flux leakage (MFL) techniques to determine mechanical features of plain carbon steels with unknown carbon contents subjected to tempering treatment. To simultaneously evaluate the effects of carbon content and microstructure on the magnetic and mechanical properties, four grades of hypoeutectoid steel samples containing 0.30, 0.46, 0.54, and 0.71 wt.% carbon were austenitized in the range of 830-925 °C and then subjected to quench-tempering treatments at 200, 300, 400, 500 and 600 °C. In the next step, mechanical properties including tensile strength, elongation, and hardness were measured using tensile and hardness tests, respectively. Finally, to study the electromagnetic parameters, MHL, MFL and EC non-destructive electromagnetic tests were applied to the heat-treated samples and their outputs were fed to a generalized neural network designed in this work. The results revealed that using a proper combination of electromagnetic parameters as the ANN input for each mechanical parameter enables us to determine the hardness, UTS and elongation of hypoeutectic carbon steel parts after tempering treatment with high accuracy.

Keywords


1.     Altpeter, I., R. Tschuncky, and Szielasko, K. Electromagnetic techniques for materials characterization, in the book: Materials Characterization Using Nondestructive Evaluation (NDE) Methods, Elsevier (2016). 225-262. DOI: 10.1016/B978-0-08-100040-3.00008-0
2.     Kashefi, M. and Kahrobaee, S. “On the application of non-destructive eddy current method for quality control of heat treated parts”, in 18th Congress IFHTSE, International Federation for Heat Treatment and Surface Engineering, Rio de Janeiro, (2010).
3.     Nezhad, K.K., Kahrobaee, S., and Akhlaghi, I. A. “Application of magnetic hysteresis loop method to determine prior austenite grain size in plain carbon steels.” Journal of Magnetism and Magnetic Materials, Vol. 477, (2019), 275-282. DOI: https://doi.org/10.1016/j.jmmm.2019.01.074
4.     Seyfpour, M., Ghanei, S., Mazinani, M., Kashefi, M. and Davis, C. “Nondestructive examination of recovery stage during annealing of a cold-rolled low-carbon steel using eddy current testing technique.” Nondestructive Testing and Evaluation, Vol. 33, No. 2, (2018), 165-174. DOI: 10.1080/10589759.2017.1409746
5.     Zhang, C., Bowler, N. and Lo, C. “Magnetic characterization of surface-hardened steel.” Journal of Magnetism and Magnetic Materials, Vol. 321, No. 23, (2009), 3878-3887. DOI: https://doi.org/10.1016/j.jmmm.2009.07.065
6.     Kobayashi, S., Takahashi, H. and Kamada, Y. “Evaluation of case depth in induction-hardened steels: magnetic hysteresis measurements and hardness-depth profiling by differential permeability analysis.” Journal of Magnetism and Magnetic Materials, Vol. 343, (2013), 112-118. DOI: 10.1016/j.jmmm.2013.04.082
7.     Kahrobaee, S., Hejazi, T. H. and Akhlaghi, I. A. “Electromagnetic methods to improve the nondestructive characterization of induction hardened steels: A statistical modeling approach.” Surface and Coatings Technology, Vol. 380, (2019) 125074. DOI: https://doi.org/10.1016/j.surfcoat.2019.125074
8.     Kahrobaee, S., Torbati, M. K. and Amiri, M. S. Surface Characterization of Carburized Steel by Eddy Current, in the book: Nondestructive Testing of Materials and Structures, Springer (2013), 559-564. DOI: 10.1007/978-94-007-0723-8_80
9.     Kahrobaee, S., Kashefi, M. and Alam, A. S. “Magnetic NDT Technology for characterization of decarburizing depth.” Surface and Coatings Technology, Vol. 205, No. 16, (2011), 4083-4088. DOI: https://doi.org/10.1016/j.surfcoat.2011.02.060.
10.   Zhu, W., Yin, W., Dewey, S., Hunt, P., Davis, C. L., and Peyton, A. J. “Modeling and experimental study of a multi-frequency electromagnetic sensor system for rail decarburization measurement.” NDT & E International, Vol. 86, (2017), 1-6. https://doi.org/10.1016/j.ndteint.2016.11.004
11.   Falahat, S., Ghanei, S. and Kashefi, M. “Nondestructive examination of decarburised layer of steels using eddy current and magnetic Barkhausen noise testing techniques.” Nondestructive Testing and Evaluation, Vol. 33, No. 2, (2018), 154-164. DOI: https://doi.org/10.1080/10589759.2017.1397144
12.   Kahrobaee, S. and Kashefi, M. “Microstructural characterization of quenched AISI D2 tool steel using magnetic/electromagnetic nondestructive techniques.” IEEE Transactions on Magnetics, Vol. 51, No. 9, (2015), 1-7. DOI: 10.1109/TMAG.2015.2428673
13.   Kahrobaee, S., Ghanei, S. and Kashefi, M. “Using an Artificial Neural Network for Nondestructive Evaluation of the Heat Treating Processes for D2 Tool Steels.” Journal of Materials Engineering and Performance, Vol. 28, No. 5, (2019), 3001-3011. DOI: 10.1007/s11665-019-04057-4
14.   Kahrobaee, S., Norouzi, S. H. and Akhlaghi, I. A. “Nondestructive Characterization of Microstructure and Mechanical Properties of Heat Treated H13 Tool Steel Using Magnetic Hysteresis Loop Methodology.” Research in Nondestructive Evaluation, Vol. 30, No. 5, (2019), 303-315. DOI: https://doi.org/10.1080/09349847.2019.1574942
15.   Mirzaee, A., Kahrobaee, S. and Akhlaghi, I. A. “Non-destructive determination of microstructural/mechanical properties and thickness variations in API X65 steel using magnetic hysteresis loop and artificial neural networks.” Nondestructive Testing and Evaluation, Vol. 35, No. 72, (2019), 1-17, DOI: 10.1080/10589759.2019.1662901
16.   Akhlaghi, I. A., Salkhordeh-Haghighi, M. Kahrobaee, S. and Hojati, M. “Prediction of chemical composition and mechanical properties in powder metallurgical steels using multi-electromagnetic nondestructive methods and a data fusion system.” Journal of Magnetism and Magnetic Materials, Vol. 498, (2020), 166246. DOI: https://doi.org/10.1016/j.jmmm.2019.166246
17.   Kahrobaee, S. and Zohourvahid-Karimi, E. “Characterisation of work-hardening in Hadfield steel using non-destructive eddy current method.” Nondestructive Testing and Evaluation, Vol. 34, No. 2, (2019), 178-192. DOI: https://doi.org/10.1080/10589759.2019.1581190
18.   Tandon, K., “MFL tool hardware for pipeline inspection.” Materials Performance, Vol. 36, No. 2, (1997), 75-79. DOI: 10.1016/s0963-8695(98)90832-5
19.   Haines, H., Porter, P. C., and Barkdull, L. “Advanced MFL signal analysis aids pipe corrosion detection.” Pipe Line & Gas Industry, Vol. 82, No. 3, (1999), 49-57.
20.   Li, Y., Tian, G. Y. and Ward, S. “Numerical simulation on magnetic flux leakage evaluation at high speed.” NDT & E International, Vol. 39, No. 5, (2006) 367-373. DOI: https://doi.org/10.1016/j.ndteint.2005.10.006
21.   Ricken, W., Schoenekess, H. and Becker, W. J. “Improved multi-sensor for force measurement of pre-stressed steel cables by means of the eddy current technique.” Sensors and Actuators A: Physical, Vol. 129, No. 1-2, (2006), 80-85. DOI: https://doi.org/10.1016/j.sna.2005.11.056
22.   Hassoun, M. H., Fundamentals of artificial neural networks. MIT Press, 1995.
23.   Aggarwal, C. C., Neural networks and deep learning. Springer, 2018.
24.   Specht, D. F., “A general regression neural network.” IEEE Transactions on Neural Networks, Vol. 2, No. 6, (1991), 568-576. DOI: 10.1109/72.97934
25.   Handbook, A., Heat treating. ASM International Materials Park (OH), 1991.