Research on characteristic quantity and intelligent classification prediction of metal magnetic memory detection signal

Kai Guo; Chencan Sun; Wenjie Pan; Wenying Fan; Hongsheng Zhang; Kai Guo; Chencan Sun; Wenjie Pan; Wenying Fan; Hongsheng Zhang

doi:10.3934/math.2024645

AIMS Mathematics

2024, Volume 9, Issue 5: 13224-13244. doi: 10.3934/math.2024645

Previous Article Next Article

Research article

Research on characteristic quantity and intelligent classification prediction of metal magnetic memory detection signal

1.
School of Environmental and Chemical Engineering, Yanshan University, Hebei 066004, China
2.
Zhejiang Academy of Special Equipment Science, Hangzhou, Zhejiang 310020, China

Received: 27 January 2024 Revised: 20 March 2024 Accepted: 01 April 2024 Published: 10 April 2024
MSC : 65K05, 68T11

Metal magnetic memory (MMM) is an innovative, nondestructive testing method. It can detect both stress concentrations and macroscopic defects. The three-dimensional force-magnetic coupling model was established by the ANSYS simulation software, the evolution process of different defect depths was studied in detail, and the change of the signal characteristic was analyzed. The results showed that the variation trend and amplitude characteristic of MMM signals resulted in obvious differences among different defect types. Meanwhile, the impacts caused by the defect parameters and the type are complex, which cannot be decoupled or calculated by a certain formula. The accuracy of the simulation data was verified by experiments. To solve the classification prediction problem in MMM detection, the signal peak and valley H_p-v, the signal width W, the gradient K_y, and the peak energy H_y were selected as characteristic parameters to evaluate different defect types according to the change in the signal waveform. Finally, using these vectors as the input variables, the radial basis function neural network (RBFNN) pre-classification test model was established to realize the classification recognition of pit defects, crack defects, and porosity defects. The results show that the accuracy of the training and test sets, and it is feasible to use this model to complete the intelligent classification of defects.
- metal magnetic memory detection,
- stress concentration,
- defect classification,
- radial basis function neural network,
- prediction
Citation: Kai Guo, Chencan Sun, Wenjie Pan, Wenying Fan, Hongsheng Zhang. Research on characteristic quantity and intelligent classification prediction of metal magnetic memory detection signal[J]. AIMS Mathematics, 2024, 9(5): 13224-13244. doi: 10.3934/math.2024645

Related Papers:

Abstract

Metal magnetic memory (MMM) is an innovative, nondestructive testing method. It can detect both stress concentrations and macroscopic defects. The three-dimensional force-magnetic coupling model was established by the ANSYS simulation software, the evolution process of different defect depths was studied in detail, and the change of the signal characteristic was analyzed. The results showed that the variation trend and amplitude characteristic of MMM signals resulted in obvious differences among different defect types. Meanwhile, the impacts caused by the defect parameters and the type are complex, which cannot be decoupled or calculated by a certain formula. The accuracy of the simulation data was verified by experiments. To solve the classification prediction problem in MMM detection, the signal peak and valley H_p-v, the signal width W, the gradient K_y, and the peak energy H_y were selected as characteristic parameters to evaluate different defect types according to the change in the signal waveform. Finally, using these vectors as the input variables, the radial basis function neural network (RBFNN) pre-classification test model was established to realize the classification recognition of pit defects, crack defects, and porosity defects. The results show that the accuracy of the training and test sets, and it is feasible to use this model to complete the intelligent classification of defects.

References

[1]	Z. Xiao, C. Zhang, P. Li, Engineering oxygen vacancies on Tb-doped ceria supported Pt catalyst for hydrogen production through steam reforming of long-chain hydrocarbon fuels, Chinese J. Chem. Eng., 68 (2024). https://doi.org/10.1016/j.cjche.2023.12.008 doi: 10.1016/j.cjche.2023.12.008
[2]	Q. Ma, G. Tian, Y. Zeng, R. Li, H. Song, Z. Wang, et al., Pipeline in-line inspection method, instrumentation and data management, Sensors, 21 (2021), 3862. https://doi.org/10.3390/s21113862 doi: 10.3390/s21113862
[3]	K. Xu, X. Qiu, X. Tian, Theoretical investigation of metal magnetic memory testing technique for detection of magnetic flux leakage signals from buried defect, Nondestruct. Test. Eva., 33 (2018), 45–55. https://doi.org/10.1080/10589759.2017.1293050 doi: 10.1080/10589759.2017.1293050
[4]	S. K. A. D. Steklov, Assessment of welded joints stress-strain state inhomogeneity before and after post weld heat treatment based on the metal magnetic memory method, Weld. World, 60 (2016), 665–672. https://doi.org/10.1007/s40194-016-0335-7 doi: 10.1007/s40194-016-0335-7
[5]	Y. Yang, X. Ma, S. Su, W. Wang, Study on corrosion damage characterization and tensile strength evaluation for locally corroded bridge steel via metal magnetic memory method, Measurement, 207 (2023), 112406. https://doi.org/10.1016/j.measurement.2022.112406 doi: 10.1016/j.measurement.2022.112406
[6]	B. Liu, J. Sun, L. He, H. Geng, L. Yang, Quantitative study on internal detection signal of weak magnetic stress in oil and gas pipelines based on force-magnetic Noncoaxial effect, Measurement, 215 (2023), 112870. https://doi.org/10.1016/j.measurement.2023.112870 doi: 10.1016/j.measurement.2023.112870
[7]	F. Gao, J. Fan, L. Zhang, Magnetic crawler climbing detection robot basing on metal magnetic memory testing technology, Robot. Auton. Syst., 125 (2020), 103439. https://doi.org/10.1016/j.robot.2020.103439 doi: 10.1016/j.robot.2020.103439
[8]	S. Kolokolnikov, A. Dubov, A. Medvedev, D. Boriskin, Comprehensive inspection of refrigerated ammonia storage tank welded joints by the metal magnetic memory technique and conventional NDT methods, Weld. world, 64 (2020), 1659–1670. https://doi.org/10.1007/s40194-020-00938-8 doi: 10.1007/s40194-020-00938-8
[9]	X. Di, W. Li, S. Bai, Metal magnetic memory signal by neural network for welding cracks, T. China Weld. Inst., 3 (2008), 13–16. https://doi.org/10.1109/IEMBS.1993.978529 doi: 10.1109/IEMBS.1993.978529
[10]	H. Chen, C. Wang, H. Zhu, Metal magnetic memory test method based on magnetic gradient tensor, Chinese J. Sci. Instrum., 37 (2016), 602–609. https://doi.org/10.3969/j.issn.0254-3087.2016.03.017 doi: 10.3969/j.issn.0254-3087.2016.03.017
[11]	X. D. Shi, J. C. Fan, W. Zhou, Pattern recognition of pipeline magnetic memory inspection based on BP neural network, China Petrol. Mach., 48 (2020), 111–117. https://doi.org/10.16082/j.cnki.issn.1001-4578.2020.06.017 doi: 10.16082/j.cnki.issn.1001-4578.2020.06.017
[12]	P. Ramuhalli, L. Udpa, S. S. Udpa, Electromagnetic NDE signal inversion by function-approximation neural networks, IEEE T. Magn., 38 (2002), 3633–3642. https://doi.org/10.1109/TMAG.2002.804817 doi: 10.1109/TMAG.2002.804817
[13]	A. F. Joshi, L. Udpa, S. Udpa, Adaptive wavelets for characterizing magnetic flux leakage signals from pipeline inspection, IEEE T. Magn., 42 (2006), 3168–3170. https://doi.org/10.1109/INTMAG.2006.376376 doi: 10.1109/INTMAG.2006.376376
[14]	H. Zhang, X. Yu, Research on oil and gas pipeline defect recognition based on IPSO for RBF neural network, Sustain. Comput.-Infor., 20 (2018), 203–209. https://doi.org/10.1016/j.suscom.2017.08.002 doi: 10.1016/j.suscom.2017.08.002
[15]	S. Wang, H. L. Huang, G. Han, Quantitative evaluation of magnetic memory signal based on PCA & GA-BP neural network, J. Electronic Meas. Instrum., 32 (2018), 190–196. https://doi.org/10.13382/j.jemi.2018.10.026 doi: 10.13382/j.jemi.2018.10.026
[16]	H. Y. Xing, Y. H. Chen, X. F. Li, Magnetic memory identification model of mental weld defect levels based on dynamic immune fuzzy clustering, Chinese J. Sci. Instrum., 40 (2019), 225–232. https://doi.org/10.19650/j.cnki.cjsi.J1905312 doi: 10.19650/j.cnki.cjsi.J1905312
[17]	P. Shi, K. Jin, P. Zhang, S. Xie; Z. Chen; X. Zheng, Quantitative inversion of stress and crack in ferromagnetic materials based on metal magnetic memory method, IEEE T. Magn., 54 (2018), 1–11. https://doi.org/10.1109/TMAG.2018.2856894 doi: 10.1109/TMAG.2018.2856894
[18]	K. Yao, B. Deng, Z. D. Wang, Numerical studies to signal characteristics with the metal magnetic memory-effect in plastically deformed samples, NDT & E Int., 47 (2012), 7–17. https://doi.org/10.1016/j.ndteint.2011.12.004 doi: 10.1016/j.ndteint.2011.12.004
[19]	P. P. S, X. J. Z. Magnetic charge model for 3D MMM signals, Nondestruct. Test. Eva., 31 (2016), 45–60. https://doi.org/10.1080/10589759.2015.1064121 doi: 10.1080/10589759.2015.1064121
[20]	B. Liu, Y. Fu, B. Xu, Study on metal magnetic memory testing mechanism, Res. Nondestruct. Eva., 26 (2015), 1–12. https://doi.org/10.1080/09349847.2014.896965 doi: 10.1080/09349847.2014.896965
[21]	A. Wenger, E. Tö rö k, Theory of the Magnetomechanical pole effect, J. Magn. Magn. Mater., 13 (1979), 283–288. https://doi.org/10.1016/0304-8853(79)90210-5 doi: 10.1016/0304-8853(79)90210-5
[22]	M. Shi, Y. Liang, M. Zhang, Z. Huang, L. Feng, Z. Zhou, Pipeline damage detection based on metal magnetic memory, IEEE T. Magn., 57 (2021), 1–15. https://doi.org/10.1109/TMAG.2021.3084808 doi: 10.1109/TMAG.2021.3084808
[23]	Y. En, L. Luming, C. Xing, Magnetic field aberration induced by cycle stress, J. Magn. Magn. Mater., 312 (2007), 72–77. https://doi.org/10.1016/j.jmmm.2006.09.019 doi: 10.1016/j.jmmm.2006.09.019
[24]	A. Dubov, S. Kolokolnikov, Detection of cracks in 25Cr35NiNb ethylene pyrolysis furnace tubes by metal magnetic memory technique, Weld. World, 58 (2014), 225–236. https://doi.org/10.1007/s40194-013-0102-y doi: 10.1007/s40194-013-0102-y
[25]	L. Wu, K. Yao, P. Shi, B. Zhao, Y. S. Wang, Influence of inhomogeneous stress on biaxial 3D magnetic flux leakage signals, NDT & E Int., 109 (2020), 102178. https://doi.org/10.1016/j.ndteint.2019.102178 doi: 10.1016/j.ndteint.2019.102178
[26]	G. Han, H. Huang, A dual-dipole model for stress concentration evaluation based on magnetic scalar potential analysis, NDT & E Int., 118 (2021), 102394. https://doi.org/10.1016/j.ndteint.2020.102394 doi: 10.1016/j.ndteint.2020.102394
[27]	X. Jian, X. Jian, G. Deng, Experiment on relationship between the magnetic gradient of low-carbon steel and its stress, J. Magn. Magn. Mater., 321 (2009), 3600–3606. https://doi.org/10.1016/j.jmmm.2009.06.077 doi: 10.1016/j.jmmm.2009.06.077
[28]	K. Xu, K. Yang, J. Liu, Y. Wang, Study on metal magnetic memory signal of buried defect in fracture process, J. Magn. Magn. Mater., 498 (2020), 166139. https://doi.org/10.1016/j.jmmm.2019.166139 doi: 10.1016/j.jmmm.2019.166139
[29]	S. Bao, P. Jin, Z. Zhao, M. Fu, A review of the metal magnetic memory method, J. Nondestruct. Eva., 39 (2020), 11. https://doi.org 10.1007/s10921-020-0652-z
[30]	K. Xu, J. Liu, K. Yang, J. Liu, Effect of applied load and thermal treatment on the magnetic memory signal of defect-bearing Q345R steel samples, J. Magn. Magn. Mater., 539 (2021), 168366. https://doi.org/10.1016/j.jmmm.2021.168366 doi: 10.1016/j.jmmm.2021.168366
[31]	C. Pang, J. Zhou, R. Zhao, H. Ma, Y. Zhou, Research on internal force detection method of steel bar in elastic and yielding stage based on metal magnetic memory, Materials, 12 (2019), 1167. https://doi.org/10.3390/ma12071167 doi: 10.3390/ma12071167
[32]	M. Moonesan, M. Kashefi, Effect of sample initial magnetic field on the metal magnetic memory NDT result, J. Magn. Magn. Mater., 460 (2018), 285–291. https://doi.org/10.1016/j.jmmm.2018.04.006 doi: 10.1016/j.jmmm.2018.04.006

Reader Comments

Your name:*

Email:*
© 2024 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)