A novel physics-informed framework for reconstruction of structural defects

doi:10.1007/s10483-022-2912-6

Applied Mathematics and Mechanics (English Edition) ›› 2022, Vol. 43 ›› Issue (11): 1717-1730.doi: https://doi.org/10.1007/s10483-022-2912-6

A novel physics-informed framework for reconstruction of structural defects

Qi LI¹, Fushun LIU², Bin WANG¹, D. Z. LIU³, Zhenghua QIAN¹

1. State Key Laboratory of Mechanics and Control of Mechanical Structures, College of Aerospace Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China;
2. College of Engineering, Ocean University of China, Qingdao 266100, Shandong Province, China;
3. School of Engineering, University of East Anglia, Norwich NR4 7TJ, U. K.

收稿日期:2022-03-31 修回日期:2022-08-08 出版日期:2022-11-01 发布日期:2022-10-29
通讯作者: D. Z. LIU, E-mail: dianzi.liu@uea.ac.uk; Zhenghua QIAN, E-mail: qianzh@nuaa.edu.cn
基金资助:
The National Natural Science Foundation of China (Nos. 12061131013, 12211530064, and 12172171), the Fundamental Research Funds for the Central Universities of China (Nos. NE2020002 and NS2019007), the National Natural Science Foundation of China for Creative Research Groups (No. 51921003), the Postgraduate Research and Practice Innovation Program of Jiangsu Province of China (No. KYCX210184), the National Natural Science Foundation of Jiangsu Province of China (No. BK20211176), the State Key Laboratory of Mechanics and Control of Mechanical Structures at Nanjing University of Aeronautics and Astronautics of China (No. MCMS-E-0520K02), and the Interdisciplinary Innovation Fund for Doctoral Students of Nanjing University of Aeronautics and Astronautics of China (No. KXKCXJJ202208)

A novel physics-informed framework for reconstruction of structural defects

Qi LI¹, Fushun LIU², Bin WANG¹, D. Z. LIU³, Zhenghua QIAN¹

1. State Key Laboratory of Mechanics and Control of Mechanical Structures, College of Aerospace Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China;
2. College of Engineering, Ocean University of China, Qingdao 266100, Shandong Province, China;
3. School of Engineering, University of East Anglia, Norwich NR4 7TJ, U. K.

Received:2022-03-31 Revised:2022-08-08 Online:2022-11-01 Published:2022-10-29
Contact: D. Z. LIU, E-mail: dianzi.liu@uea.ac.uk; Zhenghua QIAN, E-mail: qianzh@nuaa.edu.cn
Supported by:
The National Natural Science Foundation of China (Nos. 12061131013, 12211530064, and 12172171), the Fundamental Research Funds for the Central Universities of China (Nos. NE2020002 and NS2019007), the National Natural Science Foundation of China for Creative Research Groups (No. 51921003), the Postgraduate Research and Practice Innovation Program of Jiangsu Province of China (No. KYCX210184), the National Natural Science Foundation of Jiangsu Province of China (No. BK20211176), the State Key Laboratory of Mechanics and Control of Mechanical Structures at Nanjing University of Aeronautics and Astronautics of China (No. MCMS-E-0520K02), and the Interdisciplinary Innovation Fund for Doctoral Students of Nanjing University of Aeronautics and Astronautics of China (No. KXKCXJJ202208)

摘要/Abstract

摘要： The ultrasonic guided wave technology plays a significant role in the field of non-destructive testing as it employs acoustic waves with the advantages of high propagation efficiency and low energy consumption during the inspect process. However, the theoretical solutions to guided wave scattering problems with assumptions such as the Born approximation have led to the poor quality of the reconstructed results. Besides, the scattering signals collected from industry sectors are often noised and nonstationary. To address these issues, a novel physics-informed framework (PIF) for the quantitative reconstruction of defects by means of the integration of the data-driven method with the guided wave scattering analysis is proposed in this paper. Based on the geometrical information of defects and initial results obtained by the PIF-based analysis of defect reconstructions, a deep-learning neural network model is built to reveal the physical relationship between the defects and the noisy detection signals. This learning model is then adopted to assess and characterize the defect profiles in structures, improve the accuracy of the analytical model, and eliminate the impact of the noise pollution in the process of inspection. To demonstrate the advantages of the developed PIF for the complex defect reconstructions with the capability of denoising, several numerical examples are carried out. The results show that the PIF has greater accuracy for the reconstruction of defects in the structures than the analytical method, and provides a valuable insight into the development of artificial intelligence (AI)-assisted inspection systems with high accuracy and efficiency in the fields of structural integrity and condition monitoring.

关键词: physics-informed, deep-learning, reconstruction of defects, denoising

Abstract: The ultrasonic guided wave technology plays a significant role in the field of non-destructive testing as it employs acoustic waves with the advantages of high propagation efficiency and low energy consumption during the inspect process. However, the theoretical solutions to guided wave scattering problems with assumptions such as the Born approximation have led to the poor quality of the reconstructed results. Besides, the scattering signals collected from industry sectors are often noised and nonstationary. To address these issues, a novel physics-informed framework (PIF) for the quantitative reconstruction of defects by means of the integration of the data-driven method with the guided wave scattering analysis is proposed in this paper. Based on the geometrical information of defects and initial results obtained by the PIF-based analysis of defect reconstructions, a deep-learning neural network model is built to reveal the physical relationship between the defects and the noisy detection signals. This learning model is then adopted to assess and characterize the defect profiles in structures, improve the accuracy of the analytical model, and eliminate the impact of the noise pollution in the process of inspection. To demonstrate the advantages of the developed PIF for the complex defect reconstructions with the capability of denoising, several numerical examples are carried out. The results show that the PIF has greater accuracy for the reconstruction of defects in the structures than the analytical method, and provides a valuable insight into the development of artificial intelligence (AI)-assisted inspection systems with high accuracy and efficiency in the fields of structural integrity and condition monitoring.

Key words: physics-informed, deep-learning, reconstruction of defects, denoising

中图分类号:

Qi LI, Fushun LIU, Bin WANG, D. Z. LIU, Zhenghua QIAN. A novel physics-informed framework for reconstruction of structural defects[J]. Applied Mathematics and Mechanics (English Edition), 2022, 43(11): 1717-1730.

参考文献

[1] ROSE, J. L. A baseline and vision of ultrasonic guided wave inspection potential. Journal of Pressure Vessel Technology, 124, 273-282(2002)
[2] BAI, H., SHAH, A. H., POPPLEWELL, N., and DATTA, S. K. Scattering of guided waves by circumferential cracks in composite cylinders. International Journal of Solids&Structures, 39, 4583-4603(2002)
[3] SU, Z., YE, L., and LU, Y. Guided lamb waves for identification of damage in composite structures:a review. Journal of Sound and Vibration, 295, 753-780(2006)
[4] DA, Y. H., Wang, B., LIU, D. Z., and QIAN, Z. H. An analytical approach to reconstruction of axisymmetric defects in pipelines using T (0, 1) guided waves. Applied Mathematics and Mechanics (English Edition), 41(10), 1479-1492(2020) https://doi.org/10.1007/s10483-020-2661-9
[5] QIU, L., YUAN, S., MEI, H., and FANG, F. An improved Gaussian mixture model for damage propagation monitoring of an aircraft wing spar under changing structural boundary conditions. Sensors, 16, 291(2016)
[6] EREMIN, A. V., BURKOV, M. V., BYAKOV, A. V., LYUBUTIN, P. S., PANIN, S. V., and KHIZHNYAK, S. A. Investigation of acoustic parameters for structural health monitoring of sandwich panel under cyclic load. Key Engineering Materials, 712, 319-323(2016)
[7] PUTHILLATH, P. and ROSE, J. L. Ultrasonic guided wave inspection of a titanium repair patch bonded to an aluminum aircraft skin. International Journal of Adhesion and Adhesives, 30, 566-573(2010)
[8] WANG, B. and HIROSE, S. Inverse problem for shape reconstruction of plate-thinning by guided SH-waves. Materials Transaction, 53, 1782-1789(2012)
[9] SIKDAR, S. and BANERJEE, S. Identification of disbond and high density core region in a honeycomb composite sandwich structure using ultrasonic guided waves. Composite Structures, 152, 568-578(2016)
[10] DA, Y., DONG, G., WANG, B., LIU, D., and QIAN Z. A novel approach to surface defect detection. International Journal of Engineering Science, 133, 181-195(2018)
[11] ARRIDGE, S., MAASS, P., ÖKTEM, O., and SCHONLIEB, C. B. Solving inverse problems using data-driven models. Acta Numerica, 28, 1-174(2019)
[12] AVCI, O., ABDELJABER, O., KIRANYAS, S., HUSSEIN, M., GABBOUJ, M., and INMAN, D. J. A review of vibration-based damage detection in civil structures:from traditional methods to machine learning and deep learning applications. Mechanical Systems and Signal Processing, 147, 107077(2021)
[13] MUNIR, N., KIM, H. J., PARK, J., SONG, S. J., and KANG, S. S. Convolutional neural network for ultrasonic weldment flaw classification in noisy conditions. Ultrasonics, 94, 74-81(2019)
[14] WANG, X. C., LIN, M., LI, J., TONG, J. K., HUANG, X. J., LIANG, L., FAN, Z., and LIU, Y. Ultrasonic guided wave imaging with deep learning:applications in corrosion mapping. Mechanical Systems and Signal Processing, 169, 108761(2022)
[15] CRUZ, F. C., SIMASFILHO, E. F., ALBUQUERQUE, M. C. S., SILVA, I. C., FARIAS, C. T. T., and GOUVEA, L. L. Efficient feature selection for neural network based detection of flaws in steel welded joints using ultrasound testing. Ultrasonics, 73, 1-8(2017)
[16] YE, Z. and YU, J. Deep morphological convolutional network for feature learning of vibration signals and its applications to gearbox fault diagnosis. Mechanical Systems and Signal Processing, 161, 107984(2021)
[17] VIRKKUNEN, I., KOSKINEN, T., JESSEN-JUHLER, O., and RINTA-AHO, J. Augmented ultrasonic data for machine learning. Journal of Nondestructive Evaluation, 40, 1-11(2021)
[18] LATÊTE, T., GAUTHIER, B., and BELANGER, P. Towards using convolutional neural network to locate, identify and size defects in phased array ultrasonic testing. Ultrasonics, 115, 106436(2021)
[19] MIORELLI, R., KULAKOVSKYI, A., CHAPUIS, B., D'ALMEIDA, O., and MESNIL, O. Supervised learning strategy for classification and regression tasks applied to aeronautical structural health monitoring problems. Ultrasonics, 113, 106372(2021)
[20] ZHAO, Y. P., XIE, Y. L., and YE, Z. F. A new dynamic radius SVDD for fault detection of aircraft engine. Engineering Applications of Artificial Intelligence, 100, 104177(2021)
[21] JIN, K. H., MCCANN, M. T., FROUSTEY, E., and UNSER, M. Deep convolutional neural network for inverse problems in imaging. IEEE Transactions on Image Processing, 26, 4509-4522(2017)
[22] SUN, Y., XIA, Z., and KAMILOV, U. S. Efficient and accurate inversion of multiple scattering with deep learning. Optics Express, 26, 14678-14688(2018)
[23] BOUBLIL, D., ELAD, M., SHTOK, J., and ZIBULEVSKY, M. Spatially-adaptive reconstruction in computed tomography using neural networks. IEEE Transactions on Medical Imaging, 34, 1474-1485(2015)
[24] MCCANN, M. T., JIN, K. H., and UNSER, M. Convolutional neural networks for inverse problems in imaging:a review. IEEE Signal Processing Magazine, 34, 85-95(2017)
[25] ACHENBACH, J. A. and ACHENBACH, J. D. Reciprocity in Elastodynamics, Cambridge University Press, Cambridge (2003)
[26] NAIR, V. and HINTON, G. E. Rectified linear units improve restricted Boltzmann machines. Proceedings of the 27th International Conference on Machine Learning (ICML-10), International Machine Learning Society, Haifa, 807-814(2010)
[27] YOO, H. J. Deep convolution neural networks in computer vision:a review. IEIE Transactions on Smart Processing and Computing, 4, 35-43(2015)
[28] YANG, C., WANG, B., and QIAN, Z. Three-dimensional modified BEM analysis of forward scattering problems in elastic solids. Engineering Analysis with Boundary Elements, 122, 145-154(2021)
[29] FLYNN, E. B., CHONG, S. Y., JARMER, G. J., and LEE, J. R. Structural imaging through local wavenumber estimation of guided waves. NDT&E International, 59, 1-10(2013)
[30] CAI, J., SHI, L., and QING, X. P. A time-distance domain transform method for Lamb wave dispersion compensation considering signal waveform correction. Smart Materials and Structures, 22, 105024(2013)
[31] BOUBLIL, D., ELAD, M., SHTOK, J., and ZIBULEVSKY, M. Spatially-adaptive reconstruction in computed tomography using neural networks. IEEE Transactions on Medical Imaging, 34, 1474-1485(2015)
[32] OQUAB, M., BOTTOU, L., LAPTEV, I., and SIVIC, J. Learning and transferring mid-level image representations using convolutional neural networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Columbus (2014)

A novel physics-informed framework for reconstruction of structural defects

A novel physics-informed framework for reconstruction of structural defects

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 6

编辑推荐

Metrics

本文评价

[1]	H. OWHADI. Gaussian process hydrodynamics[J]. Applied Mathematics and Mechanics (English Edition), 2023, 44(7): 1175-1198.
[2]	J. N. FUHG, A. KARMARKAR, T. KADEETHUM, H. YOON, N. BOUKLAS. Deep convolutional Ritz method: parametric PDE surrogates without labeled data[J]. Applied Mathematics and Mechanics (English Edition), 2023, 44(7): 1151-1174.
[3]	Xuhui MENG. Variational inference in neural functional prior using normalizing flows: application to differential equation and operator learning problems[J]. Applied Mathematics and Mechanics (English Edition), 2023, 44(7): 1111-1124.
[4]	Yichuan HE, Zhicheng WANG, Hui XIANG, Xiaomo JIANG, Dawei TANG. An artificial viscosity augmented physics-informed neural network for incompressible flow[J]. Applied Mathematics and Mechanics (English Edition), 2023, 44(7): 1101-1110.
[5]	Zhiping MAO, Xuhui MENG. Physics-informed neural networks with residual/gradient-based adaptive sampling methods for solving partial differential equations with sharp solutions[J]. Applied Mathematics and Mechanics (English Edition), 2023, 44(7): 1069-1084.
[6]	W. WU, M. DANEKER, M. A. JOLLEY, K. T. TURNER, L. LU. Effective data sampling strategies and boundary condition constraints of physics-informed neural networks for identifying material properties in solid mechanics[J]. Applied Mathematics and Mechanics (English Edition), 2023, 44(7): 1039-1068.