基于数据驱动的结构钢表面应力磁巴克豪森噪声表征方法

doi:10.7527/S1000-6893.2022.27237

Abstract

Abstract:

Magnetic Barkhausen Noise （MBN） technique can be used to quantitatively evaluate the surface stress of ferromagnetic materials. The current MBN stress assessment technology has the disadvantages of difficult feature selection， complex quantitative prediction model and low fitting accuracy of the calibration data set. A data-driven nonlinear mapping algorithm is proposed to fit the relationship between MBN noise and stress. The time-frequency feature based on wavelet packet transform coefficients is used to replace the statistical feature， which reduces the amount of sample data calculation. The wavelet packet transform coefficients of MBN noise in the wavelet packet transform time-frequency domain are used as eigenvectors. The dimensionality reduction algorithm based on singular value decomposition is used to reduce the dimension of the eigenvectors， and the eigenvectors after data dimension reduction are input into the Back Pagation （BP） neural network. Model training is performed to build predictive models. The results show that the data dimensionality reduction algorithm based on singular value decomposition can reduce the complexity of the model， and the BP neural network can be trained by using the eigenvectors of the wavelet packet transform coefficients after dimensionality reduction to achieve high-precision prediction of surface stress of ferromagnetic materials. The characterization method proposed can effectively solve the problem of stress distribution imaging of ferromagnetic components， and has great potential in application in stress corrosion prevention， fatigue strength improvement， and other damage early warning.

Key words: data-driven, magnetic Backhausen noise, structural steel, stress, singular value decomposition, wavelet packet decomposition

CLC Number:

V214.3⁺2

Ximing CUI, Zhipeng QIU, Jia WEI, Chi ZHANG, Kai SONG, Zhe LI, Shupeng WANG. Data-driven method for characterization of structural steel surface stress of magnetic Barkhausen noise[J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2023, 44(8): 427237-427237.

Figures/Tables 20

Fig.1

Fig.2

Fig.3

Fig.4

Fig. 5

Fig.6

Fig.7

Fig.8

Fig.9

Fig.10

Fig.11

Fig.12

Fig.13

Fig.14

Fig.15

Fig.16

Table 1

Test effect of BP neural network prediction model for lower surface stress of three-point bending test block

测试点个数	预测值/ $M P a$	实际值/ $M P a$	相对误差/%
1	53.84	63.29	14.93
2	62.58	74.77	16.30
3	75.23	86.91	10.71
4	98.47	108.34	9.11
5	108.06	118.80	9.04
6	117.77	128.66	8.47
7	139.13	137.82	0.95
8	141.41	146.14	3.24
9	148.78	153.54	3.10
10	154.37	159.91	3.47
11	155.40	165.19	5.93
12	165.06	169.31	2.51
13	166.14	172.23	3.54
14	172.61	173.90	0.74
15	171.44	174.32	1.65
16	172.49	173.49	0.58

Table 1

Fig.17

Fig.18

Fig.19

References 24

1	BANIK S D， KUMAR S， SINGH P K， et al. Distortion and residual stresses in thick plate weld joint of austenitic stainless steel： Experiments and analysis［J］. Journal of Materials Processing Technology， 2021， 289： 116944.
2	王秋成，柯映林，章巧芳. 7075铝合金板材残余应力深度梯度的评估［J］. 航空学报， 2003， 24（4）： 336-338.
	WANG Q C， KE Y L， ZHANG Q F. Evaluation of residual stress depth profiling in 7075 aluminum alloy plates［J］. Acta Aeronautica et Astronautica Sinica， 2003， 24（4）： 336-338 （in Chinese）.
3	JIA L， GUI Y T， BIN G， et al. Micro-macro characteristics between domain wall motion and magnetic Barkhausen noise under tensile stress［J］. Journal of Magnetism and Magnetic Materials： C， 2020， 493： 165719.
4	张志东. 磁性材料的磁结构、磁畴结构和拓扑磁结构［J］. 物理学报， 2015， 64（6）： 5-21.
	ZHANG Z D. Magnetic structures， magnetic domains and topological magnetic textures of magnetic materials［J］. Journal of Physics， 2015， 64（6）： 5-21 （in Chinese）.
5	DI J Y， HE C F， LEE Y C， et al. Evaluation of the stress gradient of the superficial layer in ferromagnetic components based on sub-band energy of magnetic Barkhausen noise［J］. Nondestructive Testing and Evaluation， 2022， 37（1）： 41-55.
6	苟磊，马玉娥，杜永，等. 7050凹槽铝板激光冲击强化残余应力分布与疲劳寿命［J］. 航空学报， 2019， 40（12）： 423096.
	GOU L， MA Y E， DU Y， et al. Residual stress profile and fatigue life of 7050 aluminum plate with groove under laser shot peening［J］. Acta Aeronautica et Astronautica Sinica， 2019， 40（12）： 423096 （in Chinese）.
7	BAHLEDA F， DREVENÝ I， PITOŇÁK M， et al. Employment of barkhausen noise technique for assessment of prestressing bars damage with respect of their over-stressing［J］. Metals， 2021， 11（5）： 770.
8	朱秋君. 巴克豪森噪声钢轨应力检测仪的开发和研究［D］. 南京：南京航空航天大学， 2012： 11-15.
	ZHU Q J. Development and research of the equipment of barkhausen noise rail stress detection［D］. Nanjing： Nanjing University of Aeronautics and Astronautics， 2012： 11-15 （in Chinese）.
9	FAGAN P， DUCHARNE B， DANIEL L， et al. Effect of stress on the magnetic Barkhausen noise energy cycles： A route for stress evaluation in ferromagnetic materials［J］. Materials Science and Engineering： B， 2022， 278： 115650.
10	杨吟飞，张峥，李亮，等. 7085铝合金残余应力及加工变形的数值仿真与试验［J］. 航空学报， 2014， 35（2）： 574-581.
	YANG Y F， ZHANG Z， LI L， et al. Numerical simulation and test of bulk residual stress and machining distortion in aluminum alloy 7085［J］. Acta Aeronautica et Astronautica Sinica， 2014， 35（2）： 574-581 （in Chinese）.
11	GUBBELS W. Magnetic Barkhausen noise analysis for inspection of ferromagnetic materials［J］. Materials Evaluation， 2020， 78（6）： 618-624.
12	PEREZ-MONTES F， ORTEGA-LABRA O， MANH T L， et al. Enhancing the precision of magnetocrystalline anisotropy energy estimation from Barkhausen noise using a deep neural network［J］. Materials Today Communications， 2020， 24： 101145.
13	朱秋君，王平，田贵云，等. 基于BP神经网络的巴克豪森铁轨温度应力检测［J］. 无损检测， 2011， 33（12）： 25-28.
	ZHU Q J， WANG P， TIAN G Y， et al. A rail temperature stress detection system by Barkhausen noise based on BP neural network［J］. Nondestructive Testing Technologying， 2011， 33（12）： 25-28 （in Chinese）.
14	蒋政培，凌张伟，王敏. 磁巴克豪森噪声技术在应力评估中的研究进展［J］. 无损检测， 2018， 40（8）： 67-74.
	JIANG Z P， LING Z W， WANG M. Progress of magnetic Barkhausen noise technique in stress evaluation［J］. Non-destructive testing， 2018， 40（8）： 67-74 （in Chinese）.
15	高涵，白照广，范东栋. 基于BP神经网络的GNSS-R海面风速反演［J］. 航空学报， 2019， 40（12）： 323261.
	GAO H， BAI Z G， FAN D D. GNSS-R sea surface wind speed inversion based on BP neural network［J］. Acta Aeronautica et Astronautica Sinica， 2019， 40（12）： 323261 （in Chinese）.
16	ZHANG N B， LI Y W， YANG X B， et al. Bearing fault diagnosis based on BP neural network and transfer learning［J］. Journal of Physics： Conference Series， 2021， 1881（2）： 3-6.
17	张翔，高晓蓉，郭建强，等. 基于能量重构的MBN材料硬度检测算法研究［J］. 传感器与微系统， 2020， 39（3）： 30-33， 41.
	ZHANG X， GAO X R， GUO J Q， et al. Research on algorithms for material hardness detection based on energy reconstruction MBN［J］. Transducer and Microsystem Technologies， 2020， 39（3）： 30-33， 41 （in Chinese）.
18	姬小丽，王平，田贵云，等. 基于小波分解和BP神经网络的磁巴克豪森噪声信号分层分析研究［J］. 无损检测， 2012， 34（11）： 5-9.
	JI X L， WANG P， TIAN G Y， et al. Stratified analysis of the magnetic barkhausen noise signal based on wavelet decomposition and back propagation neural network［J］. Nondestructive Testing Technologying， 2012， 34（11）： 5-9 （in Chinese）.
19	COIFMAN R R， MEYER Y， QUAKE S， et al. Signal processing and compression with wavelet packets［M］∥Wavelets and Their Applications. Dordrecht： Springer Netherlands， 1994： 363-379.
20	吴杰. 巴克豪森应力检测的提离消除及软硬件实现研究［D］. 南京：南京航空航天大学， 2015： 11-36.
	WU J. Research on eliminating the lift-off and realization of system of barkhausen stress testing［D］. Nanjing： Nanjing University of Aeronautics and Astronautics， 2015： 11-36 （in Chinese）.
21	张传栋，何存富，刘秀成，等. 基于BP神经网络的钢轴表面硬度磁巴克豪森噪声定量检测技术［J］. 实验力学， 2020， 35（1）： 1-8.
	ZHANG C D， HE C F， LIU X C， et al. Magnetic Barkhausen noise technology for surface hardness evaluation in steel shaft based on BP neural network［J］. Journal of Experimental Mechanics， 2020， 35（1）： 1-8 （in Chinese）.
22	雷瑛，李达，罗森怡. 磨削加工件表面残余应力测试及其线性回归预测分析［J］. 工具技术， 2021， 55（10）： 19-23.
	LEI Y， LI D， LUO S Y. Surface residual stress measurement and linear regression prediction analysis of grinding workpiece［J］. Tool Engineering， 2021， 55（10）： 19-23 （in Chinese）.
23	PANDIT P， DEY P， KRISHNAMURTHY K N. Comparative assessment of multiple linear regression and fuzzy linear regression models［J］. SN Computer Science， 2021， 2（2）： 76.
24	董雷. 基于BP神经网络的电磁融合无损检测方法研究［D］. 重庆：重庆大学， 2018： 51-84.
	DONG L. Research on nondestructive detection of electromagnetic fusion based on BP neural network［D］. Chongqing： Chongqing University， 2018： 51-84 （in Chinese）.

[1]	Chao YANG, Kaifu ZHANG. Stress prediction of fuselage tube section based on PSO⁃BiLSTM neural network [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2023, 44(7): 426991-426991.
[2]	Xiaoxu HE, Pei LEI, Deng PAN, Yang YANG, Xiankun LI, Zhenbo DENG. Posture and position computing method for aircraft component based on PSO and WSVD [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2023, 44(7): 427162-427162.
[3]	Ping CHEN, Xia YE, Huaqiang LIU, Yiliang HU, Xin YU. Axial stress measurement of bolts based on ultrasonic energy attenuation [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2023, 44(7): 227250-227250.
[4]	Bi WEN, Baijie QIAO, Zepeng LI, Zhendong LI, Yanfeng WANG, Xuefeng CHEN. Synchronous vibration identification of fan blisk based on acoustic mode decomposition [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2023, 44(6): 227066-227066.
[5]	Dong WU, Hong YANG, Wenfeng ZHAO, Yue LUO. High temperature strain measurement of hypersonic aircraft carbon-based composite material structures [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(S2): 160-169.
[6]	QI Liangang, HAN Yanze, WANG Yani, GUO Qiang, Kaliuzhny MYKOLA. Multi-component LFM interference suppression method based on chirp rate turning point and FrFT [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(8): 326840-326840.
[7]	LI Baoguo, ZHANG Cheng'an, XU Jianqiu. A radar-embedded communication waveform design method based on SVD [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(7): 325401-325401.
[8]	LIU Zhendong, ZHENG Xitao, FAN Wenjing, ZHANG Dongjian. Effect of process-induced residual stress on strength of UAV composite wing [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(6): 526117-526117.
[9]	LI Chong, CHAI Yanan, WANG Binwen, CHEN Xiangming, YU Zhenbo, ZHOU Hong. Test technology for complex stress field of large scale fuselage panel [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(6): 526409-526409.
[10]	LI Hui, LI Guangxian, GAO Ruilin, JIN Xin, LIU Lu, LI Chaojiang, Songlin DING. Research progress of post-processing of stainless steel additive manufacturing parts [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(4): 525847-525847.
[11]	SUO Bin, YAN Ying. A new credibility evaluation method for accelerated degradation test based on area metric [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(3): 325207-325207.
[12]	YANG Xiawei, PENG Chong, MA Tiejun, WEN Guodong, WANG Yanying, CHAI Xiaoxia, XU Yaxin, LI Wenya. Finite element analysis of fatigue crack growth of linear friction welded superalloy joints [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(2): 625004-625004.
[13]	HAN Chongtao, SONG Linghui, DUAN Guosheng, WU Baolin. Effects of mean stress on ratcheting behavior of extruded AZ31B magnesium alloy [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(12): 426060-426060.
[14]	JIANG Lijian, ZHAO Wenwen, CHEN Weifang, YAO Shaobo. Data-driven rarefied nonlinear constitutive relations based on rotation invariants [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(12): 126256-126256.
[15]	SHU Bowen, DU Yiming, GAO Zhenghong, XIA Lu, CHEN Shusheng. Numerical simulation of Reynolds stress model of typical aerospace separated flow [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(11): 526385-526385.

Data-driven method for characterization of structural steel surface stress of magnetic Barkhausen noise

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 20

References 24

Related Articles 15

Recommended Articles

Metrics

Comments