Magnetic Barkhausen noise (MBN) is a magnetic signal caused by domain wall motion and is used for non-destructive testing and evaluation of ferromagnetic materials because of its sensitivity to both mechanical and magnetic properties. Recently, machine learning models have been employed to evaluate materials based on MBN; however, the application of material evaluation to low-volume targets is challenging because of their low signal-to-noise ratio, which is due to their low volume. Therefore, understanding the influence of the signal-to-noise ratio is important, particularly for low-volume objects. However, very few reports have quantitatively assessed the influence of noise in MBN analysis. In this study, we focused on noise to improve the accuracy of MBN analysis using machine learning, investigated its impact on the prediction accuracy of machine learning models, and explored methods to mitigate its effects. A method for grain size evaluation based on MBN analysis was adopted and performed for Fe-Co alloy wires with different grain sizes. After the measurement of MBN, the relationship between the extracted features from the analysis of MBN by fast Fourier transform and grain size was learned using a gradient boosting decision tree to create a grain size evaluation model, and the coefficient of determination was used to evaluate the prediction accuracy of the grain size evaluation. The machine learning model demonstrated high prediction accuracy (R² = 0.926) across the entire grain size range. Using the model to assess the effect of signal-to-noise ratio, experiments were also conducted using MBN time-series data with artificially applied Gaussian noise. Additionally, from the insight of the distribution of predicted grain sizes, we confirmed that a noise reduction method by averaging the MBN prediction results can improve the prediction accuracy by reducing the effect of noise as expected. This research will lead to the adoption of MBN applications, which are simple and practical methods of material evaluation, for the micro–nano discipline.

1. [1] S. Yamaura, Y. Furuya, and T. Watanabe, “The effect of grain boundary microstructure on Barkhausen noise in ferromagnetic materials,” Acta Materialia, Vol.49, Issue 15, pp. 3019-3027, 2001. https://doi.org/10.1016/S1359-6454(01)00189-6
2. [2] J. Gauthier, T. W. Krause, and D. L. Atherton, “Measurement of residual stress in steel using the magnetic Barkhausen noise technique,” NDT & E Int., Vol.31, No.1, pp. 23-31, 1998. https://doi.org/10.1016/S0963-8695(97)00023-6
3. [3] C. Gatelier-Rothea, J. Chicois, R. Fougeres, and P. Fleischmann, “Characterization of pure iron and (130 p.p.m.) carbon–iron binary alloy by Barkhausen noise measurements: study of the influence of stress and microstructure,” Acta materialia, Vol.46, No.14, pp. 4873-4882, 1998. https://doi.org/10.1016/S1359-6454(98)00205-5
4. [4] N. Chukwuchekwa, A. J. Moses, and P. Anderson, “Effects of strip thickness and silicon content on Magnetic Barkhausen Noise of non-oriented electrical steel at 50 Hz,” Int. J. of Applied Electromagnetics and Mechanics, Vol.39, Nos.1-4, pp. 541-545, 2012. https://doi.org/10.3233/JAE-2012-1508
5. [5] H. Barkhausen, “Two phenomena revealed with the help of new amplifiers,” Phys. Z, Vol.29, No.6, pp. 401-403, 1919.
6. [6] D. M. Stewart, K. J. Stevens, and A. B. Kaiser, “Magnetic Barkhausen noise analysis of stress in steel,” Current Applied Physics, Vol.4, Issues 2-4, pp. 308-311, 2004. https://doi.org/10.1016/j.cap.2003.11.035
7. [7] J. Pal’a and J. Bydžovský, “Barkhausen noise as a function of grain size in non-oriented FeSi steel,” Measurement, Vol.46, Issue 2, pp. 866-870, 2013. https://doi.org/10.1016/j.measurement.2012.10.014
8. [8] A. Dhar, L. Clapham, and D. L. Atherton, “Influence of uniaxial plastic deformation on magnetic Barkhausen noise in steel,” NDT & E Int., Vol.34, Issue 8, pp. 507-514, 2001. https://doi.org/10.1016/S0963-8695(00)00079-7
9. [9] T. Yamazaki, Y. Furuya, S. Hata, and W. Nakao, “Stress-driven magnetic Barkhausen noise generation in FeCo magnetostrictive alloy,” IEEE Trans. on Magnetics, Vol.58, No.1, 2022. https://doi.org/10.1109/TMAG.2021.3126898
10. [10] T. Yamazaki, Y. Furuya, and W. Nakao, “Experimental evaluation of domain wall dynamics by Barkhausen noise analysis in Fe₃₀Co₇₀ magnetostrictive alloy wire,” J. of Magnetism and Magnetic Materials, Vol.475, pp. 240-248, 2019. https://doi.org/10.1016/j.jmmm.2018.11.011
11. [11] R. Ranjan, D. C. Jiles, O. Buck, and R. B. Thompson, “Grain size measurement using magnetic and acoustic Barkhausen noise,” J. of Applied Physics, Vol.61, Issue 8, pp. 3199-3201, 1987. https://doi.org/10.1063/1.338900
12. [12] A. Ktena, E. Hristoforou, G. J. Gerhardt, F. P. Missell, F. J. Landgraf, D. L. Rodrigues Jr., and M. Alberteris-Campos, “Barkhausen noise as a microstructure characterization tool,” Physica B: Condensed Matter, Vol.435, pp. 109-112, 2014. https://doi.org/10.1016/j.physb.2013.09.027
13. [13] A. Ktena, M. Hasicic, F. J. Landgraf, E. Moudilou, S. Angelopoulos, and E. Hristoforou, “On the use of differential permeability and magnetic Barkhausen Noise Measurements for Magnetic NDT Applications,” J. of Magnetism and Magnetic Materials, Vol.546, Article No.168898, 2022. https://doi.org/10.1016/j.jmmm.2021.168898
14. [14] A. Sorsa, K. Leiviskä, S. Santa-aho, and T. Lepistö, “Quantitative prediction of residual stress and hardness in case-hardened steel based on the Barkhausen noise measurement,” NDT & E Int., Vol.46, pp. 100-106, 2012. https://doi.org/10.1016/j.ndteint.2011.11.008
15. [15] M. Unterberg, J. Stanke, D. Trauth, and T. Bergs, “A time series classification approach to non-destructive hardness testing using magnetic Barkhausen noise emission,” Production Engineering, Vol.15, pp. 509-517, 2021. https://doi.org/10.1007/s11740-021-01034-6
16. [16] Y. Ji, Q. Lu, and Q. Yao, “Short communication: A case study of stress monitoring with non-destructive stress measurement and deep learning algorithms,” Mechanical Sciences, Vol.13, No.1, pp. 291-296, 2022. https://doi.org/10.5194/ms-13-291-2022
17. [17] Y. Yamashita, K. Yoshida, Y. Kishita, and Y. Umeda, “Defect Detection in Multiple Product Variants Using Hammering Test with Machine Learning,” Int. J. Automation Technol., Vol.16, No.6, pp. 783-794, 2022. https://doi.org/10.20965/ijat.2022.p0783
18. [18] K. Omae, T. Yamazaki, C. Oka, J. Sakurai, and S. Hata, “Stress measurement based on magnetic Barkhausen noise for thin films,” Microelectronic Engineering, Article No.112057, 2023. https://doi.org/10.1016/j.mee.2023.112057
19. [19] T. Yokoyama, T. Takezawa, and Y. Higashida, “On the 550^◦ Change of FeCo Superlattice Alloy,” Trans. of the Japan Institute of Metals, Vol.12, Issue 1, pp. 30-34, 1971.
20. [20] B. Alessandro, C. Beatrice, G. Bertotti, and A. Montorsi, “Phenomenology and interpretation of the Barkhausen effect in ferromagnetic materials (invited),” J. Appl. Phys., Vol.64, pp. 5355-5360, 1988. https://doi.org/10.1063/1.342370
21. [21] D. C. Jiles, L. B. Sipahi, and G. Williams, “Modeling of micromagnetic Barkhausen activity using a stochastic process extension to the theory of hysteresis,” J. Appl. Phys., Vol.73, pp. 5830-5832, 1993. https://doi.org/10.1063/1.353541
22. [22] D. C. Jiles, “Dynamics of domain magnetization and the Barkhausen effect,” Czechoslov. J. Phys., Vol.50, pp. 893-924, 2000. https://doi.org/10.1023/A:1022846128461
23. [23] C. Lo, S. Lee, L. Li, L. Kerdus, and D. Jiles, “Modeling stress effects on magnetic hysteresis and Barkhausen emission using a hysteretic-stochastic model,” IEEE Trans. Magn., Vol.38, No.5, pp. 2418-2420, 2002. https://doi.org/10.1109/TMAG.2002.803612
24. [24] L. Mierczak, D. C. Jiles, and G. Fantoni, “A New Method for Evaluation of Mechanical Stress Using the Reciprocal Amplitude of Magnetic Barkhausen Noise,” IEEE Trans. Magn., Vol.47, Issue 2, pp. 459-465, 2011. https://doi.org/10.1109/TMAG.2010.2091418
25. [25] Y. Wang, T. Meydan, and Y. Melikhov, “Quantitative Evaluation of the Effect of Temperature on Magnetic Barkhausen Noise,” Sensors, Vol.21, No.3, Article No.898, 2021. https://doi.org/10.3390/s21030898
26. [26] J. H. Friedman, “Greedy function approximation: a gradient boosting machine,” Annals of Statistics, Vol.29, No.5, pp. 1189-1232, 2001. https://doi.org/10.1214/aos/1013203451
27. [27] G. Ke, Q. Meng, T. Finley, T. Wang, W. Chen, W. Ma, Q. Ye, and T. Y. Liu, “Lightgbm: A highly efficient gradient boosting decision tree,” Advances in Neural Information Processing Systems 30, 2017.