[1]王 威,李 青,孙叶青,等.基于卷积神经网络的红外热成像罐车内壁裂纹识别[J].红外技术,2018,40(12):1198-1205.[doi:10.11846/j.issn.1001_8891.201812014]
 WANG Wei,LI Qing,SUN Yeqing,et al.Inner Crack Identification on Car Tanks Using Thermal Imaging Based on Convolutional Neural Network [J].Infrared Technology,2018,40(12):1198-1205.[doi:10.11846/j.issn.1001_8891.201812014]
点击复制

基于卷积神经网络的红外热成像罐车内壁裂纹识别
分享到:

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

卷:
40
期数:
2018年第12期
页码:
1198-1205
栏目:
出版日期:
2018-12-21

文章信息/Info

Title:
Inner Crack Identification on Car Tanks Using Thermal Imaging
Based on Convolutional Neural Network
文章编号:
1001-8891(2018)12-1198-08
作者:
王 威1李 青1孙叶青1钟海见2夏新华2
1. 中国计量大学 灾害监测技术与仪器国家地方联合工程实验室,浙江 杭州 310018;
2. 浙江省特种设备检验研究院,浙江 杭州 310020
Author(s):
WANG Wei1LI Qing1SUN Yeqing1ZHONG Haijian2XIA Xinhua2
1. National and Local Joint Engineering Laboratories for Disaster Monitoring Technologies and Instruments, China Jiliang University, Hangzhou 310018, China; 2. Zhejiang Institute of Special Equipment Inspection, Hangzhou 310020, China
关键词:
罐车裂纹检测热成像卷积神经网络
Keywords:
tankercrack detectionthermal imagingconvolutional neural network
分类号:
TN219
DOI:
10.11846/j.issn.1001_8891.201812014
文献标志码:
A
摘要:
针对传统无损检测技术在罐车内壁裂纹检测中效率低、抗干扰能力差等问题,提出一种基于卷积神经网络的热成像裂纹识别方法。研制了一种滚动式电加热棒作为热激励源,并采用新的激励方式对被检测表面进行热激励;根据热量传输过程中遇到裂纹时温度产生异常的原理,对被检测表面裂纹进行判断;采集热激励后的红外热图像作为训练样本,并搭建5层卷积神经网络对样本进行训练。实验表明,利用红外热成像与卷积神经网络可以对裂纹进行准确识别;检测效率高、鲁棒性强;并且在测试集上识别准确率达到96.50%。
Abstract:
To solve the problems of low efficiency and poor anti-jamming ability in the detection of cracks on the inner wall of truck tanks using traditional non-destructive testing techniques, this paper proposes a thermal imaging crack recognition method based on convolutional neural network (CNN). A rolling electric heating rod was developed as a thermal excitation source, and a new excitation method was used to thermally stimulate the surface to be inspected. According to the principle of abnormal temperature generated during the heat transfer process, the surface crack was detected. The thermally excited infrared thermal images are used as training samples, and a six-layer CNN was built to train on the samples. Experiments show that infrared thermal imaging and the CNN can accurately identify the cracks. The detection efficiency is high and the model is robust. Furthermore, the recognition accuracy on the test set reaches 96.50%.

参考文献/References:

[1] 裘虹星, 沈志刚. 在用罐车检验中裂纹原因分析[J]. 化工管理, 2015, 31: 153-154.
QIU Hongxing, SHEN Zhigang. Analysis of crack causes in tanker inspection[J]. Chemical Industry Management, 2015, 31: 153-154.
[2] 焦阳, 李光海, 沈功田. 压力容器无损检测——汽车与铁路罐车的无损检测技术[J]. 无损检测, 2005(10): 542-546.
JIAO Yang, LI Guanghai, SHEN Gongtian. Non-destructive testing of pressure vessels——non-destructive testing technology for automobile and railway tankers[J]. Non-destructive Testing, 2005 (10): 542-546.
[3] 戚文阳, 高尚磊, 张伯莹, 等. 在役储罐无损检测技术[J]. 中国石油和化工标准与质量, 2012, 33(11): 11.
QI Wenyang, GAO Shanglei, ZHANG Boying, et al. Nondestructive testing technology for in-service storage tanks[J]. Petrochemical and Chemical Industry Standards and Quality, 2012, 33(11): 11.
[4] 李兴才. 压力容器检验中的无损检测方法研究[J]. 工程技术研究, 2017(2): 116-117.
LI Xingcai. Research on nondestructive testing methods in pressure vessel inspection[J]. Engineering Research, 2017(2): 116-117.
[5] 张伟, 蔡青青, 张磊, 等. 漏磁检测技术在新疆某油田的应用[J]. 无损检测, 2011, 33(2): 48-51.
ZHANG Wei, CAI Qingqing, ZHANG Lei, et al. Application of magnetic flux leakage detection technology in an oilfield in Xinjiang[J]. Non-destructive Testing, 2011, 33(2): 48-51.
[6] 郑金航. 压力容器检测方法分析[J]. 化学工程与装备, 2018(4): 247-249.
ZHENG Jinhang. Analysis of pressure vessel detection methods[J]. Chemical Engineering and Equipment, 2018(4): 247-249.
[7] 邬冠华, 熊鸿建. 中国射线检测技术现状及研究进展[J]. 仪器仪表学报, 2016, 37(8): 1683-1695.
WU Guanhua, XIONG Hongjian. Current status and research progress of Chinese radiation detection rechnology[J]. Journal of Scientific Instrument, 2016, 37(8): 1683-1695.
[8] 张兴正, 宋隆均, 高昭福. 液化石油气罐车罐体内表面腐蚀的原因及防护[J]. 黑龙江科技信息, 2007(24): 19.
ZHANG Xingzheng, SONG Longjun, GAO Zhaofu. Causes and protection of surface corrosion of liquefied petroleum gas tank cars[J]. Heilongjiang Science and Technology Information, 2007(24): 19.
[9] 许罗鹏, 王清远. 基于红外成像技术的铝锂合金2198疲劳裂纹监测机制研究[J]. 科学技术与工程, 2017, 17(19): 1-7.
XU Luopeng, WANG Qingyuan. Research on monitoring mechanism of aluminum and lithium alloy 2198 fatigue crack based on Infrared Imaging Technology[J]. Science Technology and Engineering, 2017, 17(19): 1-7.
[10] 白秋菊.热成像检测中材料表面热发射率影响机理及其抑制方法[D]. 成都: 电子科技大学, 2016.
BAI Qiuju. Mechanism of thermal emissivity of material surface in thermal imaging detection and its suppression method[D]. Chengdu: University of Electronic Science and Technology of China, 2016.
[11] LI H, LIN Z, SHEN X, et al. A convolutional neural network cascade for face detection[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2015: 5325-5334.
[12] 王晨, 汤心溢, 高思莉. 基于深度卷积神经网络的红外场景理解算法[J]. 红外技术, 2017, 39(8): 728-733.
WANG Chen, TANG Xinyi, GAO Sili. Infrared scene understanding algorithm based on deep convolutional neural network[J]. Infrared Technology, 2017, 39(8): 728-733.
[13] Hidenorilde, Takio Kurita. Improvement of learning for CNN with ReLU activation by sparse regularization[C]//2017 International Joint Conference on Neural Networks (IJCNN), 2017: 2161-4407.
[14] Ersan YAZAN, FatihTalu M. Comparison of the stochastic gradient descent based optimization techniques[C]//2017 International Artificial Intelligence and Data Processing Symposium(IDAP), 2017: 1-5.

备注/Memo

备注/Memo:
收稿日期:2018-06-19;修订日期:2018-06-25.
作者简介:王威(1994-),男,安徽省亳州人,硕士研究生,研究方向:红外技术、图像识别。E-mail:15382353582@163.com。
通信作者:李青(1955-),男,浙江省杭州人,教授,研究方向:传感技术、灾害监测。E-mail:lq13306532957@163.com。
基金项目:国家质量监督检验检疫总局科技计划项目(2014QK198)。
更新日期/Last Update: 2018-12-19