Composite defect location based on Graph-in-Graph Convolutional Network
-
摘要: 针对复合材料层合板结构缺陷的快速检测定位,提出了一种基于超声导波的复合材料缺陷检测图嵌图卷积神经网络模型(G-GCN)。G-GCN通过构建导波信号相互关系的时空特征高级表征图,由局部-全局变换构建局部图,以表征单个导波信号内的相互关系信息;再基于局部图构建全局图,表征多个导波信号之间的相互关系信息;然后利用全局图输入图卷积神经网络模型训练学习,输出相应的复合材料缺陷预测,实现极少量传感器条件下的快速精准缺陷检测与定位。最后搭建了超声导波复合材料检测试验平台,验证了G-GCN的先进性和可靠性。Abstract: This paper proposed a Graph-in-Graph Convolutional Network (G-GCN) model based on ultrasound-guided waves for the rapid detection and localisation of structural defects in composite laminates. G-GCN was constructed an advanced representation map of the spatio-temporal characteristics of guided wave signals. The local map was constructed by local global transformation to represent the relationship information in a single guided wave signal. Then, the global map was constructed based on the local map to represent the relationship information between multiple guided wave signals. The global map input map was used to convolve neural network model training and learning, and the corresponding composite defect prediction was output, It realized fast and accurate defect detection and location with very few sensors. Finally, an experimental platform for nondestructive testing of ultrasonic guided wave composite materials was built to verify the advancement and reliability of G-GCN.
-
-
[1] ROSE J L.Ultrasonic Guided Waves in Solid Media[M].Cambridge:Cambridge University Press, 2014.
[2] CASTAINGS M, HOSTEN B, KUNDU T.Inversion of ultrasonic, plane-wave transmission data in composite plates to infer viscoelastic material properties[J].NDT & E International, 2000, 33(6):377-392.
[3] CASTELLANO A, FOTI P, FRADDOSIO A, et al.Mechanical characterization of CFRP composites by ultrasonic immersion tests:experimental and numerical approaches[J].Composites Part B:Engineering, 2014, 66:299-310.
[4] AYMERICH F, MEILI S.Ultrasonic evaluation of matrix damage in impacted composite laminates[J].Composites Part B:Engineering, 2000, 31(1):1-6.
[5] 王奔.改性复合材料层间力学性能超声导波评价技术研究[D].镇江:江苏大学, 2020. [6] KESSLER S S, SPEARING S M, SOUTIS C.Damage detection in composite materials using Lamb wave methods[J].Smart Materials and Structures, 2002, 11(2):269-278.
[7] LEMISTRE M, BALAGEAS D.Structural health monitoring system based on diffracted Lamb wave analysis by multiresolution processing[J].Smart Materials and Structures, 2001, 10(3):504-511.
[8] MICHAELS J E.Detection, localization and characterization of damage in plates with an in situarray of spatially distributed ultrasonic sensors[J].Smart Materials and Structures, 2008, 17(3):035035.
[9] MICHAELS J E, MICHAELS T E.Guided wave signal processing and image fusion for in situ damage localization in plates[J].Wave Motion, 2007, 44(6):482-492.
[10] HALL J S, MICHAELS J E.Computational efficiency of ultrasonic guided wave imaging algorithms[J].IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control, 2011, 58(1):244-248.
[11] HALL J S, MCKEON P, SATYANARAYAN L, et al.Minimum variance guided wave imaging in a quasi-isotropic composite plate[J].Smart Materials and Structures, 2011, 20(2):025013.
[12] NOKHBATOLFOGHAHAI A, NAVAZI H M, GROVES R M.Using the hybrid DAS-SR method for damage localization in composite plates[J].Composite Structures, 2020, 247:112420.
[13] NANDYALA A R, DARPE A K, SINGH S P.Damage localization in cross-ply laminated composite plates under varying temperature conditions using Lamb waves[J].Measurement Science and Technology, 2020, 31(6):064003.
[14] MUSTAPHA S, YE L, DONG X J, et al.Evaluation of barely visible indentation damage (BVID) in CF/EP sandwich composites using guided wave signals[J].Mechanical Systems and Signal Processing, 2016, 76/77:497-517.
[15] WANG Z, HUANG S L, WANG S, et al.Multihelical lamb wave imaging for pipe-like structures based on a probabilistic reconstruction approach[J].IEEE Transactions on Instrumentation and Measurement, 2021, 70:1-10.
[16] BANG S S, LEE Y H, SHIN Y J.Defect detection in pipelines via guided wave-based time-frequency-domain reflectometry[J].IEEE Transactions on Instrumentation and Measurement, 2021, 70:1-11.
[17] 邹兰林, 叶知秋.小波分析结合神经网络的桩基缺陷检测[J].无损检测, 2022, 44(7):50-54. [18] 杨志学, 汪正山, 叶雅婷, 等.基于超声导波的长距离高压多芯电缆缺陷检测[J].无损检测, 2018, 40(12):57-62. [19] 徐浩, 王中枢, 马寅魏, 等.基于超声导波和机器学习的蜂窝夹层结构脱黏诊断[J].无损检测, 2022, 44(10):44-47. [20] WANG Y M, KANG Y H, WU X J.Application of STFT and HOS to analyse magnetostrictively generated pulse-echo signals of a steel pipe defect[J].NDT & E International, 2006, 39(4):289-292.
[21] LI T F, ZHAO Z B, SUN C, et al.Multireceptive field graph convolutional networks for machine fault diagnosis[J].IEEE Transactions on Industrial Electronics, 2021, 68(12):12739-12749.
[22] ZHANG S Y, LI C M, YE W J.Damage localization in plate-like structures using time-varying feature and one-dimensional convolutional neural network[J].Mechanical Systems and Signal Processing, 2021, 147:107107.
[23] YANG C Y, ZHOU K B, LIU J.SuperGraph:spatial-temporal graph-based feature extraction for rotating machinery diagnosis[J].IEEE Transactions on Industrial Electronics, 2022, 69(4):4167-4176.
[24] MOLL J, KATHOL J, FRITZEN C P, et al.Open guided waves:online platform for ultrasonic guided wave measurements[J].Structural Health Monitoring, 2019, 18(5/6):1903-1914.
[25] WU Z H, PAN S R, LONG G D, et al.Graph WaveNet for deep spatial-temporal graph modeling[C]//Proceedings of the twenty-eighth international joint conference on artificial intelligence.California:International Joint Conferences on Artificial Intelligence Organization, 2019.
[26] RAUTELA M, GOPALAKRISHNAN S.Ultrasonic guided wave based structural damage detection and localization using model assisted convolutional and recurrent neural networks[J].Expert Systems with Applications, 2021, 167:114189.
计量
- 文章访问数: 9
- HTML全文浏览量: 4
- PDF下载量: 2