[1]孙吉伟,孙 浩,谢 敏,等.涡流脉冲热像技术中基于神经网络的检出/漏检预测研究[J].红外技术,2020,42(8):795-800.[doi:10.11846/j.issn.1001_8891.202008015]
 SUN Jiwei,SUN Hao,XIE Min,et al.Prediction of Hit/Miss under Different Detection Conditions through Eddy Current Pulsed Thermography [J].Infrared Technology,2020,42(8):795-800.[doi:10.11846/j.issn.1001_8891.202008015]
点击复制

涡流脉冲热像技术中基于神经网络的检出/漏检预测研究
分享到:

《红外技术》[ISSN:1001-8891/CN:CN 53-1053/TN]

卷:
42卷
期数:
2020年第8期
页码:
795-800
栏目:
出版日期:
2020-08-23

文章信息/Info

Title:
Prediction of Hit/Miss under Different Detection Conditions
through Eddy Current Pulsed Thermography
文章编号:
1001-8891(2020)08-0795-06
作者:
孙吉伟孙 浩谢 敏李泓江邓栋栋曹 涛
中国华阴兵器试验中心,陕西 华阴 714200
Author(s):
SUN JiweiSUN HaoXIE MinLI HongjiangDENG DongdongCAO Tao
China Huayin Ordnance Test Center, Huayin 714200, China
关键词:
涡流脉冲热像检出概率BP神经网络检出/漏检预测
Keywords:
 ECPT POD BPNN prediction of hit/miss
分类号:
TG115.28
DOI:
10.11846/j.issn.1001_8891.202008015
文献标志码:
A
摘要:
涡流脉冲热像技术是一种新型的无损检测技术,已在金属材料和复合材料的检测领域得到了广泛应用。检出/漏检则是评价被检测对象是否存在裂纹的重要标准,为解决目前检出/漏检研究需要大量实验数据的问题,本文提出了一种基于BP神经网络的检出/漏检预测方法。首先,制作了30组含有不同尺寸疲劳裂纹的金属试件,并完成了15组不同检测条件下的裂纹检测实验。其次,分别绘制了3组检出概率曲线,并完成了不同检测条件对检出概率的影响分析。最后,为实现检出/漏检的可靠性预测,构建了基于BP神经网络的检出/漏检预测模型,并以50组数据为样本进行测试,实现了不同检测条件下不同尺寸裂纹的检出/漏检0误差预测。
Abstract:
 Eddy current pulsed thermography is an emerging nondestructive testing technique that has been widely used for flaw detection in metallic materials. Typically, its performance is evaluated through hit/miss analysis. However, the traditional method of analyzing hit/miss requires considerable experimental data, which is time-consuming and expensive. In this study, a model-assisted method based on back-propagation neural networks (BPNNs) for hit/miss prediction was developed to minimize the need for additional experimental tests. Thirty sets of metal specimens with fatigue cracks of different lengths were fabricated; 15 experimental groups were subjected to different detection conditions. Subsequently, three sets of the probability of detection (POD) curves were plotted, and the effects of the different detection conditions on the POD were analyzed. Finally, a prediction model of the hit/miss based on the BPNN was constructed, and the hit/miss prediction was realized. The results showed that under different detection conditions, the proposed framework could complete the hit/miss prediction with an error of zero.

参考文献/References:

[1] Maldague X P V. Introduction to NDT by active infrared thermography[J]. Materials Evaluation, 2002, 60(9): 1-22.
[2] Kumar M C S, Bagavathiappan S, Sankar Y S, et al. Active infrared thermal imaging for quantitative analysis of defects and delaminations in composite materials[J]. Nondestructive Evaluation, 2009, 8(1): 28-36.
[3] Chung Y, Ranjit S, Kim W. Thermal Imaging for Detection of SM45C subsurface defects using active infrared thermography techniques[J]. The Korean Society for Nondestructive Testing, 2015, 35(3): 193-199.
[4] 孙吉伟, 冯辅周, 张丽霞, 等. 涡流脉冲热像检测中金属疲劳裂纹的生热分析[J]. 红外技术, 2019, 41(4): 91-95.
SUN Jiwei, FENG Fuzhou, ZHANG Lixia, et al. Thermal analysis of metal fatigue cracks in eddy current pulsed thermography[J]. Infrared Technology, 2019, 41(4): 91-95.
[5] LI Y, YANG Z W, ZHU J T, et al. Investigation on the damage evolution in the impacted composite material based on active infrared thermography[J]. Ndt & E International, 2016, 83: 114-122.
[6] TANG Q, DAI J, LIU J, et al. Quantitative detection of defects based on Markov-PCA-BP algorithm using pulsed infrared thermography technology[J]. Infrared Physics & Technology, 2016, 77: 144-148.
[7] Kabouri A, Khabbazi A, Youlal H. Applied multiresolution analysis to infrared images for defects detection in materials[J]. Ndt & E International, 2017, 92: 38-49.
[8] Zuzana Stankovi?ová, Vladimír Deký?, Franti?ek Nový, et al. Nondestructive testing of metal parts by using infrared camera[J]. Procedia Engineering, 2017, 177: 562-567.
[9] ZHU J Z, ZHANG C S, FENG F Z, et al. Study on probability of detection for fatigue cracks in sonic infrared imaging[J]. Infrared Physics & Technology, 2016, 77: 296-301.
[10] MIN Q X, ZHU J Z, FENG F Z, et al. Study on optimization method of test conditions for fatigue crack detection using lock-in vibro thermography[J]. Infrared Physics & Technology, 2017, 83: 17-23.
[11] LIU J, YANG L, FEI W, et al. Study on probability of detection (POD) determination using lock-in thermography for nondestructive inspection (NDI) of CFRP composite materials[J]. Infrared Physics & Technology, 2015, 71(2): 448-456.
[12] Weekes B, Almond D P, Cawley P, et al. Eddy-current induced thermography—probability of detection study of small fatigue cracks in steel, titanium and nickel-based super alloy[J]. Ndt & E International, 2012, 49: 47-56.
[13] 孙吉伟, 冯辅周, 闵庆旭, 等. 涡流脉冲热像检测中疲劳裂纹的检出概率[J]. 红外与激光工程, 2018, 47(5): 46-51.
SUN Jiwei, FENG Fuzhou, MIN Qingxu, et al. Probability of detection for fatigue crack in eddy current pulsed thermography[J]. Infrared and Laser Engineering, 2018, 47(5): 46-51.
[14] 龚金龙, 盖志刚, 解维浩, 等. CFRP层板缺陷红外热波雷达成像检测概率研究[J]. 红外与激光工程, 2017(10): 276-284.
GONG Jinlong, GAI Zhigang, XIE Weihao, et al. Study on probability of detection for CFRP laminate defect using infrared thermal wave radar imaging[J]. Infrared and Laser Engineering, 2017(10): 276-284.
[15] CHENG H L, Soon Cheol Park. Combination of modified BPNN algorithms and an efficient feature selection method for text categorization[J]. Information Processing & Management, 2009, 45(3): 329-340.

相似文献/References:

[1]徐超,冯辅周,闵庆旭,等.基于主成分分析的热图像序列盲源分离[J].红外技术,2017,39(11):1018.[doi:10.11846/j.issn.1001_8891.201711009]
 XU Chao,FENG Fuzhou,MIN Qingxu,et al.Blind Source Separation of Thermal Image Sequences Using Principal Component Analysis[J].Infrared Technology,2017,39(8):1018.[doi:10.11846/j.issn.1001_8891.201711009]
[2]孙吉伟,冯辅周,张丽霞,等.涡流脉冲热像检测中金属疲劳裂纹的生热分析[J].红外技术,2019,41(4):383.[doi:10.11846/j.issn.1001_8891.2019040014]
 SUN Jiwei,FENG Fuzhou,ZHANG Lixia,et al.Thermal Analysis of Metal Fatigue Cracks in Eddy Current Pulsed Thermography[J].Infrared Technology,2019,41(8):383.[doi:10.11846/j.issn.1001_8891.2019040014]

备注/Memo

备注/Memo:
收稿日期:2019-12-01;修订日期:2019-12-27.
作者简介:孙吉伟(1994-),男,硕士研究生,主要从事红外无损检测技术弹药安全性研究。E-mail:whusjw@163.com。
更新日期/Last Update: 2020-08-20