基于数据融合-知识迁移方法的高温数字图像相关试验应力表征

doi:10.7527/S1000-6893.2025.31574

Abstract

Abstract:

The Digital Image Correlation （DIC） experimental system is widely used for mechanical performance evaluation of structures in high-temperature environments due to its ability to achieve non-contact precise measurements of full-field strain. However， experimental methods based on DIC measurement technology face challenges in directly characterizing the stress field of structures， particularly in high-temperature environments where material parameters are closely related to temperature， and the heavy reliance of the Finite Element Method （FEM） on these parameters leads to insufficient accuracy of stress outcomes. Therefore， it is of great significance to understand and evaluate the mechanical properties of structures by combining high-temperature DIC experiments and FEM to accurately characterize the full-field stress of structures. This paper proposes a data fusion-knowledge transfer method for stress characterization in high-temperature DIC experiments. A high-temperature DIC experimental system， a high-precision FEM model， and a transfer learning framework are developed for typical high-temperature titanium alloys in aerospace structures， achieving accurate characterization of stress fields based on small-sample experimental data. Firstly， a multi-layer perceptron neural network is employed to pre-train large-sample simulation data， capturing the mapping relationship between structural coordinates and stress in complex high-temperature environments. Secondly， based on small-sample high-temperature DIC test data， the pre-trained model is fine-tuned to characterize a structural stress field in high-temperature environments， and effectively transfer knowledge from the finite element model to the experimental data. Finally， the accuracy and applicability of the proposed method for predicting structural stress fields are verified using indicators such as the mean square error and the coefficient of determination， which provides a new approach for characterizing experimental stress fields in high-temperature environments.

Key words: high-temperature digital image correlation, data fusion, transfer learning, stress characterization, multilayer perception neural network

CLC Number:

V214.3

Chengjie GUO, Dian XU, Jinbao LI, Chaoyu CHENG, Shuochang GUO, Rui LI. Stress characterization of high-temperature digital image correlation experiments based on a data fusion-knowledge transfer method[J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(19): 531574.

Figures/Tables 9

Fig.1

Fig.2

Table 1

Fig.3

Table 2

Comparison of prediction accuracy of three types of methods under different displacements at 450 ℃

位移/mm	方法	$R 2$	MSE
0.125	有限元分析	0.884 2	0.122 0
	冻结+重新训练	0.993 1	0.013 3
	全模型微调	0.996 8	0.002 5
0.250	有限元分析	0.838 8	0.160 9
	冻结+重新训练	0.993 9	0.066 1
	全模型微调	0.994 5	0.005 5
1.250	有限元分析	0.890 6	0.107 8
	冻结+重新训练	0.983 3	0.016 4
	全模型微调	0.999 4	0.005 9

Table 2

Fig.4

Table 3

Fig.5

Table 4

Comparison of prediction accuracy of three types of methods under different displacements at 500-800 ℃

位移/mm	方法	$R 2$	MSE
0.125	有限元分析	0.847 7	0.119 3
	冻结+重新训练	0.983 1	0.015 3
	全模型微调	0.998 9	0.002 9
0.250	有限元分析	0.820 4	0.140 1
	冻结+重新训练	0.983 8	0.014 3
	全模型微调	0.993 0	0.007 4
1.250	有限元分析	0.879 2	0.132 8
	冻结+重新训练	0.987 2	0.012 8
	全模型微调	0.997 1	0.005 4

Table 4

References 21

[1]	许璐瑶，辛朝阳，王丽明. 航空内燃机用TB6钛合金高温压缩成形特性分析［J］. 锻压装备与制造技术， 2024， 59（4）： 144-146.
	XU L Y， XIN C Y， WANG L M. High temperature compression molding characteristics of TB6 titanium alloy for aviation internal combustion engine［J］. China Metalforming Equipment & Manufacturing Technology， 2024， 59（4）： 144-146 （in Chinese）.
[2]	LAKSHMANAN P， SAKTHIVEL E. Examining the superplastic behavior of （Al-Si-Mg）/SiC metal matrix nanocomposites［J］. Materials Today： Proceedings， 2022， 62： 962-966.
[3]	CAI Y C， HO H W， LI S X， et al. Structural metals after exposure to high temperatures： residual mechanical properties and predictions［J］. Steel Research International， 2025， 96（7）： 2400610.
[4]	GERDES L， BERGER S， SAELZER J， et al. Application-oriented digital image correlation for the high-speed deformation and fracture analysis of AISI 1045 and Ti6Al4V materials［J］. Applied Mechanics， 2022， 3（4）： 1190-1205.
[5]	ROWLEY L J， THAI T Q， DABB A， et al. High speed ultraviolet digital image correlation （UV-DIC） for dynamic strains at extreme temperatures［J］. Review of Scientific Instruments， 2022， 93（8）： 084903.
[6]	LIU C Z， GUAN H， TAI Q G， et al. Microstructure， texture and mechanical studies of an inconspicuous shear band formed during hot compression of Ti-6Al-4V alloy［J］. Materials Science and Engineering： A， 2017， 698： 18-26.
[7]	LIU B， LAN S Z， LI J Q， et al. Digital image correlation in extreme conditions［J］. Thin-Walled Structures， 2024， 205： 112589.
[8]	FEDERICO C. A review of data fusion techniques［J］. The Scientific World Journal， 2013， 2013： 704504.
[9]	MENG T， JING X Y， YAN Z， et al. A survey on machine learning for data fusion［J］. Information Fusion， 2020， 57： 115-129.
[10]	ZHANG J Q， ZHANG J W， TENG S， et al. Structural damage detection based on vibration signal fusion and deep learning［J］. Journal of Vibration Engineering & Technologies， 2022， 10（4）： 1205-1220.
[11]	温志辉，夏桂锁，刘芳，等. 飞机蒙皮接缝特征的数据融合算法［J］. 传感技术学报， 2024， 37（4）： 629-638.
	WEN Z H， XIA G S， LIU F， et al. Research on a data fusion technology for aircraft skin seam features［J］. Chinese Journal of Sensors and Actuators， 2024， 37（4）： 629-638 （in Chinese）.
[12]	杨华，陈树生，高正红，等. 基于贝叶斯框架的旋翼气动力数据融合［J］. 航空学报， 2024， 45（8）： 128960.
	YANG H， CHEN S S， GAO Z H， et al. Rotor aerodynamic data fusion based on Bayesian framework［J］. Acta Aeronautica et Astronautica Sinica， 2024， 45（8）： 128960 （in Chinese）.
[13]	刘涵，刘勤明，叶春明，等. 多源数据融合的航空发动机轴承智能故障诊断［J］. 计算机集成制造系统， 2024， doi： 10.13196/j.cims.2024.0457 .
	LIU H， LIU Q M， YE C M， et al. Intelligent fault diagnosis of aero-engine bearings through multi-source data fusion［J］. Computer Integrated Manufacturing Systems， 2024， doi：10.13196/j.cims.2024.0457 （in Chinese）.
[14]	KHALEGHI B， KHAMIS A， KARRAY F O， et al. Multisensor data fusion： a review of the state-of-the-art［J］. Information Fusion， 2013， 14（1）： 28-44.
[15]	ZHENG Y. Methodologies for cross-domain data fusion： an overview［J］. IEEE Transactions on Big Data， 2015， 1（1）： 16-34.
[16]	CHANDRA R， KAPOOR A. Bayesian neural multi-source transfer learning［J］. Neurocomputing， 2020， 378： 54-64.
[17]	崔榕峰，李鸿岩，王祥云，等. 基于迁移学习的飞行器高低阶精度数据融合方法［J］. 飞行力学， 2024， 42（4）： 7-12， 20.
	CUI R F， LI H Y， WANG X Y， et al. High and low order precision data fusion method for aircraft based on transfer learning［J］. Flight Dynamics， 2024， 42（4）： 7-12， 20 （in Chinese）.
[18]	ZHUANG Y， WANG S Y， SHANG Y， et al. Virtual-real fusion-based transfer learning with limited data for gearbox fault diagnosis［J］. IEEE Sensors Journal， 2024， 24（3）： 3420-3430.
[19]	ZHANG Y， YAN X X， XIAO P， et al. A fault diagnosis method for bearings and gears in rotating machinery based on data fusion and transfer learning［J］. Measurement Science and Technology， 2025， 36（1）： 016104.
[20]	WANG B， LI Z C， XU Z Y， et al. Digital twin modeling for structural strength monitoring via transfer learning-based multi-source data fusion［J］. Mechanical Systems and Signal Processing， 2023， 200： 110625.
[21]	LI J M， WANG Y， JIANG S W， et al. Correction of the constitutive model and analysis of chip formation in cryogenic machining of TA15 titanium alloy［J］. Journal of Manufacturing Processes， 2024， 113： 16-33.

温度/℃	弹性模量/GPa	泊松比
450	79	0.34
500	65	0.34
550	55	0.34
600	36	0.34
650	30	0.34
700	23	0.34
750	13	0.34
800	8	0.34

位移/mm	编号	应力/MPa
位移/mm	编号	试验	有限元分析	冻结+ 重新训练	全模型微调
0.125	01	422.282	589.770	565.973	415.170
	02	422.282	590.661	565.953	412.541
	03	422.281	588.766	565.843	416.678
	04	422.281	588.656	565.845	413.171
	05	401.257	386.881	397.655	401.264
	06	401.257	385.341	397.426	401.095
0.250	01	684.393	676.008	680.533	684.383
	02	684.393	676.008	681.958	684.362
	03	684.382	674.683	682.163	683.963
	04	684.383	674.683	680.301	683.930
	05	634.106	632.951	634.858	634.383
	06	634.187	632.951	634.866	634.264
1.250	01	715.121	704.393	711.269	716.121
	02	714.978	704.393	708.163	713.931
	03	715.012	704.385	714.217	716.002
	04	715.191	704.385	712.273	715.115
	05	683.613	689.194	687.152	679.952
	06	683.607	689.190	680.141	680.076

Stress characterization of high-temperature digital image correlation experiments based on a data fusion-knowledge transfer method

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 9

References 21

Related Articles 15

Recommended Articles

Metrics

Comments

[1]	Rongzu LI, Li LIU, Dun YANG. Optimal design of hydrogen-powered UAV based on multi-source domain fusion surrogate model [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(9): 630979-630979.
[2]	Yang JIAO, Yuting LU, Ba XU, Jian OUYANG. Transfer prediction of satellite traffic based on spatiotemporal correlation [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(4): 330938-330938.
[3]	Yingjie SHI, Binchao LIU, Songsong LU, Liang CHEN, Hai SHANG, Rui BAO. Neural network model for wing strain-load relationship based on fusion of real and virtual data [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(19): 530921-530921.
[4]	Yiwei HUANG, Yibin GENG, Tianhe GAO, Xuanwei HU, Yuan WANG, Hongyan MA, Kuo TIAN. Digital twin driven high precision reconstruction method for full-field deformation of structure [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(19): 530967-530967.
[5]	Pengfei WANG, Lifang ZENG, Xueming SHAO, Jun LI. Multi-source data fusion modeling method for aerodynamic load of aircraft wing based on pre-training and fine-tuning [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(19): 532297-532297.
[6]	Ligong LI, Chao ZHANG, Jingting SU. Distributed fusion technology for multi-source landing guidance information [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(13): 531461-531461.
[7]	Xianchao MENG, Jun TAO. An airfoil inverse design method based on target testing conditional generative adversarial network [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(10): 631182-631182.
[8]	Dengfeng HU, Yu XIANG, Jun ZHANG, Jiachen YANG, Wenyong WANG. Multi-source data fusion method based on radial basis function generative adversarial network [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(10): 631478-631478.
[9]	Zichao LIU, Jiang WANG, Peng WANG, Defu LIN, Zhichuan HE. Time-constrained multi-missile cooperative guidance law [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(S1): 730607-730607.
[10]	Hua YANG, Shusheng CHEN, Zhenghong GAO, Quanfeng JIANG, Wei ZHANG. Rotor aerodynamic data fusion based on Bayesian framework [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(8): 128960-128960.
[11]	Kuo TIAN, Zhiyong SUN, Zengcong LI. High-precision digital twin method for structural static test monitoring [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(7): 429134-429134.
[12]	Hailang SONG, Jiandong ZHANG, Guoqing SHI, Qiming YANG, Yaozhong ZHANG. Comprehensive evaluation techniques and methods for flight test of avionics fire control system [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(5): 529687-529687.
[13]	Jiang CUI, Fan ZHOU, Yongfan CHEN, Li YU, Zhuoran ZHANG. A technique for aerospace generator rectifier fault diagnosis based on GAMF-CNN [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(24): 330398-330398.
[14]	Fan ZHANG, Wei CONG, Runcao TIAN, Peng WANG. Heterogeneous data fusion and reliability analysis based on two-layer variable weights [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(22): 230297-230297.
[15]	Zhaojun GU, Huan ZHAO, Jialiang WANG, Liuyang NIE. Automatic landing method for quad-rotor helicopter based on Markov decision process [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(15): 329652-329652.