[1]郝建新,贾春宇.基于红外热图的机载电路板故障模式诊断研究[J].红外技术,2019,41(3):273-278.[doi:10.11846/j.issn.1001_8891.201903013]
 HAO Jianxin,JIA Chunyu.Research on Fault Mode Diagnosis of Airborne Circuit Board Based on Infrared Images[J].Infrared Technology,2019,41(3):273-278.[doi:10.11846/j.issn.1001_8891.201903013]
点击复制

基于红外热图的机载电路板故障模式诊断研究
分享到:

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

卷:
41卷
期数:
2019年第3期
页码:
273-278
栏目:
出版日期:
2019-03-20

文章信息/Info

Title:
Research on Fault Mode Diagnosis of Airborne Circuit Board Based on Infrared Images

文章编号:
1001-8891(2019)03-0273-05
作者:
郝建新1贾春宇2
1. 中国民航大学 基础实验中心;
2. 中国民航大学 电信与自动化学院
Author(s):
HAO Jianxin1JIA Chunyu2
1. Basic Experimental Center, Civil Aviation University of China;
2. College of Electronic Information and Automation, Civil Aviation University of China

关键词:
红外热图机载电路板支持向量机证据理论故障诊断
Keywords:
infrared technologycircuit boardSVMevidence theoryfault diagnosis
分类号:
TN219
DOI:
10.11846/j.issn.1001_8891.201903013
文献标志码:
A
摘要:
作为一种新型的非接触式检测方法,基于红外热成像技术的机载电路板故障模式诊断方法受到越来越多的关注。本文针对传统基于红外热图的电路板故障检测算法中存在的缺陷,提出一种结合红外图像分割、热阻网络、支持向量机SVM(Support Vector Machine)与D-S证据理论的故障检测算法。首先,通过红外图像分割完成目标芯片区域温度提取,应用热阻网络模型对目标区域温度信息进行优化;其次,提取温度信息特征向量分别输入对应的初级SVM诊断模块,输出各故障模式的加权基本概率分配值BPA(Basic Probability Assignment);最后,应用D-S证据理论对各证据体加权BPA进行数据融合,输出融合后的故障诊断结果。实验结果表明,本文算法加强了有效证据体对诊断结果的正面影响,削弱了无效证据体的负面影响,大幅度提高了机载电路板故障模式诊断准确度。
Abstract:
Infrared imaging technology is a new non-contact detection method, which has received attention in the field of on-board circuit board fault diagnosis. This paper combines image segmentation, thermal resistance network, SVM and D-S evidence theory to solve the problems in the traditional circuit board fault detection algorithms. Firstly, Image segmentation and thermal resistance networks are used to complete target region temperature extraction and optimization. Secondly, the temperature feature vector is input to the SVM to obtain a weighted BPA. Finally, D-S evidence theory is used to complete data fusion and obtain fault diagnosis results. The experimental results show that the proposed algorithm enhances the positive impact of effective evidence on the diagnosis results, and greatly improves the diagnostic accuracy of the circuit board failure mode.

参考文献/References:

[1] 李广宏, 雷建. 基于信息融合的PCB红外热像检测关键技术研究[J]. 红外技术, 2017, 39(9): 829-834.
LI Guanghong, LEI Jian. Research on Key Technology of PCB Thermal Image Detection Based on Information Fusion[J]. Infrared Technology, 2017, 39(9): 829-834.
[2] 田裕鹏. 红外检测与诊断技术[M]. 北京: 化学工业出版社, 2006.
TIAN Yupeng. Infrared detection and diagnosis technology[M]. Beijing: Chemical Industry Press, 2006.
[3] 王力, 张璐, 王坤, 等. 结合小波模极大值和改进Hausdorff距离的电路板红外图像配准[J]. 红外技术, 2014, 36(12): 992-996.
WANG Li, ZHANG Lu, WANG Kun, et al. Infrared image registration of circuit board combined with wavelet modulus maxima and improved Hausdorff distance[J]. Infrared Technology, 2014, 36(12): 992-996.
[4] 王坤, 张恺, 王力, 等. 结合博弈论的马尔可夫随机场红外图像分割[J]. 红外技术, 2014, 36(10): 801-806.
WANG Kun, ZHANG Kai, WANG Li, et al. Infrared image segmentation of Markov random field combined with game theory[J]. Infrared Technology, 2014, 36(10): 801-806.
[5] 王坤, 兰景, 王力, 等. 基于万有引律的PCB红外图像增强研究[J]. 控制工程, 2015(5): 809-814.
WANG Kun, LAN Jing, WANG Li, et al. Research on PCB Infrared Image Enhancement Based on the Law of Universal Gravity[J]. Control Engineering, 2015(5): 809-814.
[6] 吕一凡, 王月海, 白文乐. 基于红外图像处理的电路板故障诊断算法研究[C]//全国测控、计量、仪器仪表学术年会, 2010.
LV Yifan, WANG Yuehai, BAI Wenle. Research on circuit board fault diagnosis algorithm based on infrared image processing[C]//National Academic Conference on Measurement, Measurement and Instrumentation, 2010.
[7] 戴文远. 基于红外热图像的故障诊断方法综述[J]. 红外, 2013, 34(2): 16-21.
DAI Wenyuan. Overview of Fault Diagnosis Methods Based on Infrared Thermal Image[J]. Infrared, 2013, 34(2): 16-21.
[8] 吕昂, 陈怡, 方晋甬, 等. 基于红外热成像的电路板载器件故障检测[J]. 激光与红外, 2018(5): 579-584.
LV Ang, CHEN Yi, FANG Jinxi, et al. Fault detection of on-board devices based on infrared thermal imaging[J]. Laser and Infrared, 2018(5): 579-584.
[9] 崔伟. 电路板故障红外热像检测关键技术研究[D]. 南京: 南京航空航天大学, 2011.
CUI Wei. Research on key technologies of infrared thermal imaging detection for circuit board failure[D]. Nanjing: Nanjing University of Aeronautics and Astronautics, 2011.
[10] 王力, 曾佩佩, 郝建新. 电路板红外图像多目标提取算法[J]. 计算机系统应用, 2014, 23(2):142-145.
WANG Li, ZENG Peipei, HAO Jianxin. Multi-objective extraction algorithm for infrared image of circuit board[J]. Journal of Computer Systems, 2014, 23(2): 142-145.
[11]? EIA JEDEC/JESD, JESD15-3 Two-Resistor Compact Thermal Model Guideline[S]. South Arlington, VA, USA: JEDEC Solid State Technology Association, 2008.

备注/Memo

备注/Memo:
收稿日期:2018-09-20;修订日期:2019-03-04.
作者简介:郝建新(1986-),天津武清人,硕士研究生,讲师,主要从事模式识别、民航电子设备故障诊断研究。E-mail:zuizuiaiyanzi@163.com。
基金项目:国家自然科学基金委员会与中国民用航空局联合助项目(U1733119);中央高校基本科研业务费项目中国民航大学专项资助(3122017045)。

更新日期/Last Update: 2019-03-19