Using deep learning to identify the depth of metal surface defects with narrowband SAW signals
Using deep learning to identify the depth of metal surface defects with narrowband SAW signals
复制标题
利用深度学习通过窄带 SAW 信号识别金属表面缺陷的深度
DOI：
10.1016/j.optlastec.2022.108758
复制
发表时间：
2023-01
期刊：
影响因子：
--
通讯作者：
Yanfeng Chen
中科院分区：
文献类型：
--
作者：
Lei Ding;Haopeng Wan;Qiangbing Lu;Zhiheng Chen;Kangning Jia;Junyan Ge;Xuejun Yan;Xiaodong Xu;Guanbing Ma;Xi Chen;Haiou Zhang;GuoKuan Li;Minghui Lu;Yanfeng Chen
为了确保材料的安全性和可靠性，迫切需要一种有效的无损检测技术，能够检测和量化表面和亚表面缺陷。本文对不同深度的缺陷进行了分类和回归。采用脉冲激光诱导的瞬态热光栅（TTG）方法表征表面缺陷的性质。基于热弹性理论，采用有限元法建立了含不同类型表面缺陷的理论模型。利用TTG方法激发的声表面波在不同穿透深度的含缺陷试件表面传播，并利用振动计测量，结合仿真和实验结果，通过小波变换分析得到了8200幅图像的时频尺度图。随机选择70%的图像来训练残差网络（Resnet）模型，剩余的数据（2460张图像），以及独立实验中的10张尺度图，作为之前未知的实验信号来测试Resnet模型的鲁棒性。实验结果表明，基于小波变换的尺度图的Resnet算法在验证集上的分类准确率为96.21%，对10个尺度图的预测准确率为90.00%。与VGG16、BP和SVM三种常用的机器学习算法相比，该方法具有最高的分类精度。最后，从先前训练的实验数据库中随机选择500个数据和独立实验中的10个数据用于回归预测。结果表明，数据很好地定位在沿着或靠近斜率为1的直线上。统计结果表明，80.6%（66.0%）的实验数据残差落在±10 μm（±5 μm）的尺寸范围内。本文的工作证明了将Resnet模型与小波变换和数值模拟相结合应用于激光超声识别表面缺陷深度的可行性和可靠性。
An effective nondestructive testing technique that enables the detection and quantification of surface and subsurface defects is highly demanded for assuring the safety and reliability of materials. In this paper, we classified and regressed defects with different depths. A transient thermal grating (TTG) method induced by a pulsed laser is used to characterize the properties of surface defects. Based on thermo-elasticity theory, a theoretical model with different types of surface defects is established with the finite element method (FEM). Surface acoustic waves (SAWs) excited by the TTG method propagate at the surface of a sample with defects at different penetration depths and are measured by a vibrometer.By combining the simulation and experimental results, the time–frequency scalograms of 8200 images were obtained by wavelet transform analysis. 70 % of the images are randomly selected to train the residual network (Resnet) model, and the remaining data (2460 images), as well as 10 scalograms in an independent experiment, are used as previously unknown experimental signals to test the robustness of the Resnet model. The results indicate that the Resnet with scalograms via wavelet transform achieves a 96.21 % classification accuracy on the validation set, with a prediction accuracy of 90.00 % for the 10 scalograms. Moreover, compared with three widely used machine learning algorithms, VGG16, back propagation (BP), and support vector machine (SVM), this method achieves the highest classification accuracy. Finally, 500 data selected randomly from the previously trained experimental database and 10 data in an independent experiment are used for regression prediction. The result shows that the data are well located along or close to a straight line with a slope of 1. The statistical results suggest that 80.6 % (66.0 %) of the residuals of the experimental data fell within the size range ±10 μm (±5 μm). This work proves the feasibility and reliability of the combination of the Resnet model with wavelet transform and numerical simulation to identify the depth of surface defects using laser ultrasonics.
登录
查看更多内容
DOI：
10.1063/1.4936767
发表时间：
2015-12
期刊：
The Review of scientific instruments
影响因子：
--
作者：
A. Vega-Flick;A. Vega-Flick;Jeffrey K. Eliason;A. Maznev;A. Khanolkar;M. A. Ghanem;N. Boechler;J. J. Alvarado-Gil-J.;K. A. Nelson
通讯作者：
A. Vega-Flick;A. Vega-Flick;Jeffrey K. Eliason;A. Maznev;A. Khanolkar;M. A. Ghanem;N. Boechler;J. J. Alvarado-Gil-J.;K. A. Nelson
影响因子：
4.2
作者：
Jing Xiao;Jian Chen;Xudong Yu;Danylo Lisevych;Z. Fan
通讯作者：
Jing Xiao;Jian Chen;Xudong Yu;Danylo Lisevych;Z. Fan
影响因子：
1.6
作者：
Yunshil Choi;Hyomi Jeong;Jung‐Ryul Lee
通讯作者：
Yunshil Choi;Hyomi Jeong;Jung‐Ryul Lee
影响因子：
19.4
作者：
Zhang, Xiang;Fincke, Jonathan R.;Anthony, Brian W.
通讯作者：
Anthony, Brian W.
DOI：
10.4018/978-1-7998-1192-3.ch008
发表时间：
2020
期刊：
Advances in Systems Analysis, Software Engineering, and High Performance Computing
影响因子：
--
作者：
Menaga D.;R. S.
通讯作者：
Menaga D.;R. S.