Leveraging physics-informed neural networks for wavefield analysis in laser ultrasonic testing

doi:10.1080/10589759.2024.2443768

IMR OpenIR

	Leveraging physics-informed neural networks for wavefield analysis in laser ultrasonic testing
	Li, Yang 1; Xu, Bin 1; Zou, Yun 1; Sha, Gaofeng 2; Cai, Guixi 3
通讯作者	Li, Yang(yangli@zzu.edu.cn)
	2024-12-23
发表期刊	NONDESTRUCTIVE TESTING AND EVALUATION
ISSN	1058-9759
页码	23
摘要	Laser Ultrasonic (LU) technology has emerged as a pivotal non-destructive testing method, offering a unique capability to visualise ultrasonic wavefields and identify defects without causing structural damage. However, challenges arise in certain testing scenarios where direct laser irradiation of the sample surface is hindered, resulting in incomplete LU wavefield datasets. This limitation poses a significant obstacle in accurately assessing material integrity and defect detection. This paper explores the application of Physics-Informed Neural Networks (PINNs) for LU wavefield reconstruction and prediction. PINNs are employed to reconstruct wavefields from incomplete data and predict wavefield behaviour at different time instances. Results demonstrate PINNs' effectiveness in accurately reconstructing wavefields, with correlation coefficients exceeding 0.94 between reconstructed and actual wavefields. Additionally, PINNs show promise in predicting LU wavefield data, albeit with slightly reduced accuracy beyond the training range. Moreover, PINNs effectively reduce noise in wavefield data, enhancing clarity and reliability. This study lays groundwork for further exploration of PINNs in LU defect detection.
关键词	Physics-informed neural networks wavefield reconstruction wavefield prediction laser ultrasonic non-destructive testing
资助者	National Natural Science Foundation of China ; Henan Provincial Key Scientific Research Project of Higher Education Institutions
DOI	10.1080/10589759.2024.2443768
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[51705470] ; Henan Provincial Key Scientific Research Project of Higher Education Institutions[222102220025]
WOS研究方向	Materials Science
WOS类目	Materials Science, Characterization & Testing
WOS记录号	WOS:001381216500001
出版者	TAYLOR & FRANCIS LTD
引用统计
文献类型	期刊论文
条目标识符	http://ir.imr.ac.cn/handle/321006/181142
专题	中国科学院金属研究所
通讯作者	Li, Yang
作者单位	1.Zhengzhou Univ, Sch Mech & Power Engn, Zhengzhou, Peoples R China 2.Clover Pk Tech Coll, Sch Adv Mfg, Lakewood, WA USA 3.Chinese Acad Sci, Inst Met Res, Shenyang, Peoples R China
推荐引用方式 GB/T 7714	Li, Yang,Xu, Bin,Zou, Yun,et al. Leveraging physics-informed neural networks for wavefield analysis in laser ultrasonic testing[J]. NONDESTRUCTIVE TESTING AND EVALUATION,2024:23.
APA	Li, Yang,Xu, Bin,Zou, Yun,Sha, Gaofeng,&Cai, Guixi.(2024).Leveraging physics-informed neural networks for wavefield analysis in laser ultrasonic testing.NONDESTRUCTIVE TESTING AND EVALUATION,23.
MLA	Li, Yang,et al."Leveraging physics-informed neural networks for wavefield analysis in laser ultrasonic testing".NONDESTRUCTIVE TESTING AND EVALUATION (2024):23.