|
|
|
| CFRP ultrasonic detection defect identification method based on recursive quantitative analysis |
Haijun WANG1( ),Tao WANG2,Cijun YU2,*() |
1. College of Engineering, Zhejiang University, Hangzhou 310058, China
2. College of Mechanical Engineering, Zhejiang University, Hangzhou 310058, China |
|
|
|
Abstract An adaptive variational mode decomposition (AVMD) and recursive quantitative analysis technique (RQAT) for feature extraction was proposed combined with convolutional neural network (CNN) for recognition in order to address the issues of inaccuracy and unreliability in ultrasonic defect detection of carbon fiber reinforced plastics (CFRP). Six types of simulated defects were embedded in the experiments, and 500 A-scan waveform signals were collected for each defect type after ultrasonic phased array detection. The stingray intelligent optimization algorithm was used to optimize the K and Alpha values required for variational mode decomposition (VMD). Intrinsic mode function (IMF) components were obtained by using these optimized parameters, and high-frequency noise parts were filtered out. The remaining IMF components were processed with recursive quantitative analysis technique. Each signal yielded 72 feature values, which were assembled into feature vectors and input into the CNN for recognition. The recognition accuracy was 99.94% for the training set, 98.09% for the validation set, and 98.27% for the test set. Results show that the combination of AVMD, RQAT and CNN solves the defect recognition and classification problem in CFRP ultrasonic testing.
|
|
Received: 05 July 2023
Published: 23 July 2024
|
|
|
| Fund: 自然科学基金重点资助项目（91748204）；国家自然科学基金创新研究群体科学基金资助项目（51821093）；浙江省重点研发计划资助项目（2020C01039）. |
|
Corresponding Authors:
Cijun YU
E-mail: navywang@zju.edu.cn;yuppy@zju.edu.cn
|
基于递归量化分析的CFRP超声检测缺陷识别方法
为了解决碳纤维增强复合材料 (CFRP)超声检测缺陷识别不准确、不可靠的问题，提出自适应变分模态分解(AVMD)与递归量化分析技术(RQAT)特征提取和卷积神经网络(CNN)识别方法. 实验预埋6种模拟缺陷，使用超声相控阵检测后，每种缺陷取500个A扫描波形信号数据，利用蝠鲼智能优化算法优化出变分模态分解(VMD)所需的K、Alpha，使用优化参数的VMD得到本征模态函数(IMF)分量，筛选高频噪声部分，对剩余IMF分量使用递归量化分析技术. 每个信号得到72个特征值，将特征值组成特征向量，输入CNN进行识别，训练集识别正确率为99.94%，验证集识别正确率为98.09%，测试集识别正确率为98.27%. 结果表明，AVMD与RQAT、CNN的结合解决了CFRP超声检测中缺陷的识别分类问题.
关键词：
碳纤维复合材料（CFRP）,
无损检测,
变分模态分解,
递归量化分析,
特征提取,
卷积神经网络,
缺陷识别
|
|
| [1] |
MOHAMMADKHANI R, FRAGONARA L Z, PADIYAR J M, et al. Ultrasonic phased array imaging technology for the inspection of aerospace composite structures [C]// IEEE 6th International Workshop on Metrology for Aerospace. New York: IEEE, 2019: 203-208.
|
|
|
| [2] |
LEE J C, PARK D H, JUNG H S, et al Design for carbon fiber lamination of PMI foam cored CFRP sandwich composite applied to automotive rear spoiler[J]. Fibers and Polymers, 2020, 21 (1): 156- 161
doi: 10.1007/s12221-020-9489-4
|
|
|
| [3] |
CHENG X Y, MA G S, WU Z Y, et al Automatic defect depth estimation for ultrasonic testing in carbon fiber reinforced composites using deep learning[J]. NDT and E International, 2023, 135 (2): 102804
|
|
|
| [4] |
WRONKOWICZ A, DRAGAN K, LIS K. Assessment of uncertainty in damage evaluation by ultrasonic testing of composite structures [J]. Composite Structures , 2018, 203(11): 71-84.
|
|
|
| [5] |
QU Z, JIANG P, ZHANG W Development and application of infrared thermography non-destructive testing techniques[J]. Sensors, 2020, 20 (14): 3851
doi: 10.3390/s20143851
|
|
|
| [6] |
SHOUKROUN D, MASSIMI L, IACOVIELLO F, et al Enhanced composite plate impact damage detection and characterization using X-Ray refraction and scattering contrast combined with ultrasonic imaging[J]. Composites Part B: Engineering, 2020, 181 (7): 107579
|
|
|
| [7] |
MAREC A, THOMAS J H, GUERJOUMA R Damage characterization of polymer-based composite materials: multivariable analysis and wavelet transform for clustering acoustic emission data[J]. Mechanical Systems and Signal Processing, 2008, 22 (6): 1441- 1464
doi: 10.1016/j.ymssp.2007.11.029
|
|
|
| [8] |
胡业发, 孟由, 张锦光, 等 含夹杂缺陷碳纤维复合材料层压板的无损检测与评估研究[J]. 复合材料科学与工程, 2023, 31 (2): 94- 100
HU Yefa, MENG You, ZHANG Jinguang, et al Nondestructive testing and evaluation of carbon fiber reinforced polymer laminates with inclusions[J]. Composites Science and Engineering, 2023, 31 (2): 94- 100
|
|
|
| [9] |
LIANG H, CHENG G, ZHANG Z, et al Research on ultrasonic defect identification method of well control manifold pipeline based on IAFSA-SVM[J]. Measurement, 2022, 194 (15): 110854
|
|
|
| [10] |
LEE K, ESTIVILL-CASTRO V Feature extraction and gating techniques for ultrasonic shaft signal classification[J]. Applied Soft Computing, 2007, 7 (1): 156- 165
doi: 10.1016/j.asoc.2005.05.003
|
|
|
| [11] |
GE M, WANG J, XU Y, et al Rolling bearing fault diagnosis based on EWT sub-modal hypothesis test and ambiguity correlation classification[J]. Symmetry, 2018, 10 (12): 730
doi: 10.3390/sym10120730
|
|
|
| [12] |
李健, 郭薇, 杨晓霞, 等 超声相控阵检测CFRP缺陷识别方法[J]. 天津大学学报: 自然科学与工程技术版, 2015, 48 (8): 750- 756
LI Jian, GUO Wei, YANG Xiaoxia, et al Ultrasonic phased array detection CFRP defect identification method[J]. Journal of Tianjin University: Natural Science and Engineering Technology Edition, 2015, 48 (8): 750- 756
|
|
|
| [13] |
ZHANG Y, YUEN K V, MOUSAVI M, et al Timber damage identification using dynamic broad network and ultrasonic signals[J]. Engineering Structures, 2022, 263 (17): 114418
|
|
|
| [14] |
CHEN H, LIU H, WANG X, et al Research on feature extraction and classification of ultrasonic flaw[J]. International Journal of Circuits, Systems and Signal Processing, 2015, 9 (5): 362- 372
|
|
|
| [15] |
邓勇, 黄远伟, 赖治屹 钢板缺陷识别的Volterra-SVM模型研究[J]. 机械科学与技术, 2023, 42 (1): 132- 138
DENG Yong, HUANG Yuanwei, LAI Zhiyi Study on Volterra-SVM model for defect recognition of steel plate[J]. Mechanical Science and Technology for Aerospace Engineering, 2023, 42 (1): 132- 138
|
|
|
| [16] |
胡宏伟, 张婕, 彭刚, 等 基于LBP-KPCA特征提取的焊缝超声检测缺陷分类方法[J]. 焊接学报, 2019, 40 (6): 34- 39
HU Hongwei, ZHANG Jie, PENG Gang, et al A defect classification method for ultrasonic testing of welds based on LBP-KPCA feature extraction[J]. Transactions of the China Welding Institution, 2019, 40 (6): 34- 39
|
|
|
| [17] |
RAO K S, BEATRICEVEENA T V, ANGANI C S, et al. Novel time-domain parameters for detection and classification of flaws using pulsed eddy current technique [J]. Journal of Magnetics , 2020, 25(3): 434-439.
|
|
|
| [18] |
YANG P, YANG Q Empirical mode decomposition and rough set attribute reduction for ultrasonic flaw signal classification[J]. International Journal of Computational Intelligence Systems, 2014, 7 (3): 481
doi: 10.1080/18756891.2014.889877
|
|
|
| [19] |
MOUSAVI M, TASKHIRI M S, HOLLOWAY D, et al Feature extraction of wood-hole defects using empirical mode decomposition of ultrasonic signals[J]. NDT and E International, 2020, 114 (21): 102282
|
|
|
| [20] |
HASSANI S, MOUSAVI M, GANDOMI A H Damage detection of composite laminate structures using VMD of FRF contaminated by high percentage of noise[J]. Composite Structures, 2022, 286 (35): 115243
|
|
|
| [21] |
DRAGOMIRETSKIY K, ZZOSSO D Variational mode decomposition[J]. Signal Process, 2014, 62 (9): 531- 544
|
|
|
| [22] |
赵雨. 基于AVMD和RF的GIS局部放电模式识别方法研究[D]. 长沙: 湖南大学, 2021: 001419.
ZHAO Yu. Research on GIS partial discharge pattern recognition method based on AVMD and RF [D]. Changsha: Hunan University, 2021: 001419.
|
|
|
| [23] |
褚惟, 王贵勇, 刘韬, 等 麻雀算法参数优化VMD联合K-SVD滚动轴承故障诊断[J]. 噪声与振动控制, 2022, 42 (4): 100- 106
CHU Wei, WANG Guiyong, LIU Tao, et al Fault diagnosis of VMD combined with K-SVD rolling bearing for parameter optimization of sparrow algorithm[J]. Noise and Vibration Control, 2022, 42 (4): 100- 106
|
|
|
| [24] |
ECKMANN J P, KAMPHORST S O, RUELLE D Recurrence plots of dynamical systems[J]. Europhysics Letter, 1987, 4 (13): 973- 977
|
|
|
| [25] |
WEBBER C L, ZBILUT J P Dynamical assessment of physiological systems and states using recurrence plot strategies[J]. Journal of Applied Physiology, 1994, 76 (2): 965
doi: 10.1152/jappl.1994.76.2.965
|
|
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
| |
Shared |
|
|
|
|
| |
Discussed |
|
|
|
|
