基于红外图像的ISSA-BP神经网络机载电路板芯片故障诊断

王力; 谢晓怀; 张亦弛

基于红外图像的ISSA-BP神经网络机载电路板芯片故障诊断

中国民航大学电子信息与自动化学院机载电子系统深度维修实验室, 天津 300300

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资助基金 U1733119

中央高校基本业务费项目 3122017107

基于红外技术与数据驱动的机载电路板卡故障诊断与预测研究 2021YJS018

详细信息

作者简介:
王力（1973-），男，教授，研究生导师，主要从事航空电子系统维修技术与方法研究。E-mail: 43464376@qq.com

中图分类号: TN407
计量
- 文章访问数: 144
- HTML全文浏览量: 65
- PDF下载量: 32
- 被引次数: 0
出版历程
- 收稿日期: 2021-11-15
- 修回日期: 2022-01-18
- 刊出日期: 2023-03-20

Infrared Image-based ISSA-BP Neural Network for Airborne Circuit Board Chip Fault Diagnosis

Airborne Electronic Systems Deep Maintenance Laboratory, College of Vocational Technology, Civil Aviation University of China, Tianjin 300300, China

摘要

摘要: 针对传统红外图像的机载电路板芯片故障诊断法诊断率低且无法诊断动态故障的问题，本文提出了一种基于红外温度数据的改进麻雀搜索算法优化BP神经网络（Improved sparrow search algorithm-Back propagation neural networks, ISSA-BPNN）机载电路板芯片故障诊断方法。首先，提取红外热像仪采集的电路板芯片温度数据，建立电路板芯片升温过程中静态、动态、统计特征的特征模型；然后，利用Sine混沌映射初始化麻雀种群分布，利用Levy飞行策略改进发现者种群位置更新公式，将改进后的麻雀搜索算法优化BP神经网络的权值参数；最后，将温度特征模型输入到ISSA-BP神经网络进行训练和测试，从而完成电路板芯片故障诊断。实验采用航电系统电源电路板进行可靠性分析，实验结果表明，该方法在电路板不同工况下综合故障诊断率达到97.84%。
- 红外温度 /
- 改进麻雀搜索算法 /
- BP神经网络 /
- 电路板芯片 /
- 故障诊断
Abstract: This study proposes an improved sparrow search algorithm based on an infrared temperature-data-optimized back propagation neural network (ISSA-BPNN) for an airborne circuit board chip fault diagnosis method that cannot diagnose dynamic failures. First, an infrared thermal imaging camera collected circuit board chip temperature data to establish a feature model of static, dynamic, and statistical characteristics of the circuit board chip warming process. We used sine chaos mapping to initialize the sparrow population distribution, the levy flight improvement finder sparrow location update, and an improved sparrow search algorithm to optimize the weight parameters of the BP neural network. Finally, the temperature feature model was input to the ISSA-BP neural network for training and testing to complete the circuit board chip fault diagnosis. The experiments used an avionics system power supply circuit board for reliability analysis, and the results revealed that the method achieved a comprehensive fault diagnosis rate of 97.84% under different circuit board operating conditions.
- infrared temperature /
- improved sparrow search algorithm /
- BP neural network /
- circuit board chip /
- fault diagnosis

HTML全文

图 1 数据采集系统示意图

Figure 1. Schematic diagram of data acquisition system

下载: 全尺寸图片幻灯片

图 2 芯片发热过程热像图

Figure 2. Thermal images of the heating process of the chip

下载: 全尺寸图片幻灯片

图 3 BP神经网络示意图

Figure 3. Schematic diagram of BP neural network

下载: 全尺寸图片幻灯片

图 4 Sine混沌映射示意图

Figure 4. Sine chaotic map diagram

下载: 全尺寸图片幻灯片

图 5 Levy飞行二维平面示意图

Figure 5. Levy flight two-dimensional schematic

下载: 全尺寸图片幻灯片

图 6 ISSA-BP算法流程图

Figure 6. ISSA-BP algorithm flow chart

下载: 全尺寸图片幻灯片

图 7 机载电路板电源模块热像图

Figure 7. Thermal image of airborne circuit board power module

下载: 全尺寸图片幻灯片

图 8 低功率空载两种算法诊断结果图 9低功率1020 Ω两种算法诊断结果

Figure 8. Low power empty load two algorithms diagnostic results Fig.9 Low power 1020 Ω two algorithm diagnosis results

下载: 全尺寸图片幻灯片

图 9 低功率 1020 Ω两种算法诊断结果

Figure 9. Low power 1020 Ω two algorithm diagnosis results

下载: 全尺寸图片幻灯片

图 10 低功率330 kΩ两种算法诊断结果图 11高功率空载两种算法诊断结果

Figure 10. Low power 330 kΩ two algorithm diagnosis results Fig.11 High power empty load two algorithm diagnosis results

下载: 全尺寸图片幻灯片

图 11 高功率空载两种算法诊断结果

Figure 11. High power empty load two algorithm diagnosis results

下载: 全尺寸图片幻灯片

图 12 高功率1020 Ω两种算法诊断结果图 13高功率330 kΩ两种算法诊断结果

Figure 12. High power 1020 Ω two algorithm diagnosis results Fig.13 High power 330 kΩ two algorithm diagnosis results

下载: 全尺寸图片幻灯片

图 13 高功率 330 kΩ两种算法诊断结果

Figure 13. High power 330 kΩ two algorithm diagnosis results

下载: 全尺寸图片幻灯片

表 1 故障模式总数据集构成

Table 1. Failure mode total data set composition

Mode	Chip Number	Fault Mode	Samples
F1	None	Normal	90
F2~F3	U1	Open	180
F4~F7	U2	Open	360
F8~F9	U3	Open	180
F10~F12	U1	Virtual Soldering	270
F13~F15	U2	Virtual Soldering	270
F16~F18	U3	Virtual Soldering	270
F19~F21	U1	Short	270
F22~F24	U2	Short	270
F25~F27	U3	Short	270

下载: 导出CSV

表 2 低功率空载故障诊断率对比

Table 2. Low power empty load fault diagnosis rate comparison

Accuracy/%	F1	F2~F9	F10~F18	F19~F27
BP	100	84.38	88.89	86.11
SSA-BP	100	90.63	91.67	88.89
ISSA-BP	100	96.88	97.22	97.22

下载: 导出CSV

表 3 低功率1020 Ω故障诊断率对比

Table 3. Low power 1020 Ω fault diagnosis rate comparison

Accuracy/%	F1	F2~F9	F10~F18	F19~F27
BP	75	90.63	77.78	83.33
SSA-BP	100	94.44	83.33	91.67
ISSA-BP	100	100	97.22	100

下载: 导出CSV

表 4 低功率330 kΩ故障诊断率对比

Table 4. Low-power 330 kΩ fault diagnosis rate comparison

Accuracy/%	F1	F2~F9	F10~F18	F19~F27
BP	75	93.75	83.33	86.11
SSA-BP	100	96.88	88.89	88.89
ISSA-BP	100	100	94.44	100

下载: 导出CSV

表 5 高功率空载故障诊断率对比

Table 5. High-power empty load fault diagnosis rate comparison

Accuracy/%	F1	F2~F9	F10~F18	F19~F27
BP	100	68.75	58.33	61.11
SSA-BP	100	81.25	69.44	83.33
ISSA-BP	100	96.88	97.22	97.22

下载: 导出CSV

表 6 高功率1020 Ω故障诊断率对比

Table 6. High-power 1020 Ω fault diagnosis rate comparison

Accuracy/%	F1	F2~F9	F10~F18	F19~F27
BP	50	65.63	69.44	83.33
SSA-BP	75	83.33	80.56	88.89
ISSA-BP	100	96.88	97.22	97.22

下载: 导出CSV

表 7 高功率330 kΩ故障诊断率对比

Table 7. High-power 330 kΩ fault diagnosis rate comparison

Accuracy/%	F1	F2~F9	F10~F18	F19~F27
BP	75	87.5	80.56	91.67
SSA-BP	100	90.63	86.11	94.44
ISSA-BP	100	96.88	97.22	100

下载: 导出CSV

表 8 多工况下3种故障分别诊断率

Table 8. Diagnosis rate of three faults separately under multiple working conditions

Accuracy /%	Open (F2~F9)	Virtual soldering (F10~F18)	Short (F19~F27)
BP	81.77	76.39	81.94
SSA-BP	88.54	83.33	89.35
ISSA-BP	97.92	96.76	98.61

下载: 导出CSV

表 9 多工况下故障诊断率对比

Table 9. Comparison of fault diagnosis rate under multiple working conditions

Mode	Results	Combined accuracy
BP	514/648	79.32%
SSA-BP	566/648	87.35%
ISSA-BP	634/648	97.84%

下载: 导出CSV

参考文献(15)

[1]	SHI L, ZHOU Z, JIA H, et al. Fault diagnosis of functional circuit in avionics system based on BPNN[C]//Prognostics and System Health Management Conference, IEEE, 2019: 1-5.
[2]	DONG Z, CHEN L. Image registration in PCB fault detection based on infrared thermal imaging[C]//Chinese Control Conference (CCC). IEEE, 2019: 4819-4823.
[3]	Sarawade A A, Charniya N N. Detection of faulty integrated circuits in PCB with thermal image processing[C]//International Conference on Nascent Technologies in Engineering (ICNTE). IEEE, 2019: 1-6.
[4]	孙东旭, 贾世伟, 孟玉慈, 等. 综合模块化航电系统FC网络的机内测试设计[J]. 航空计算技术, 2016, 46(6): 108-112. https://www.cnki.com.cn/Article/CJFDTOTAL-HKJJ201606028.htm SUN Dongxu, JIA Shiwei, MENG Yuci, et al. Built-in-test design for integrated module avionics fibre channel networks[J]. Aeronautical Computing Technique, 2016, 46(6): 108-112. https://www.cnki.com.cn/Article/CJFDTOTAL-HKJJ201606028.htm
[5]	ZHENG T, WANG Z, TAN C, et al. Research on fault prediction and diagnosis method of PCB circuit[C]//International Conference on Artificial Intelligence and Computer Engineering (ICAICE). IEEE, 2020: 387-390.
[6]	徐奇伟, 黄宏, 张雪锋, 等. 基于改进区域全卷积网络的高压引线接头红外图像特征分析的在线故障诊断方法[J]. 电工技术学报, 2021, 36(7): 1380-1388. https://www.cnki.com.cn/Article/CJFDTOTAL-DGJS202107008.htm XU Qiwei, HUANG Hong, ZHANG Xuefeng, et al. Online fault diagnosis method for infrared image feature analysis of high-voltage lead connectors based on improved R-FCN[J]. Transactions of China Electrotechnical Society, 2021, 36(7): 1380-1388. https://www.cnki.com.cn/Article/CJFDTOTAL-DGJS202107008.htm
[7]	张博. 基于红外图像电路板故障检测技术研究[D]. 沈阳: 沈阳航空航天大学, 2018. ZHANG Bo. Research on Circuit Board Fault Detection Technology Based on Infrared Image[D]. Shenyang: Shenyang Aerospace University, 2018.
[8]	Salvi S S, Jain A. Detection of unusual thermal activities in a semiconductor chip using backside infrared thermal imaging[J]. Journal of Electronic Packaging, 2021, 143(2): 020901. doi: 10.1115/1.4049291
[9]	Al Obaidy F, Yazdani F, Mohammadi F A. Intelligent testing for Arduino UNO based on thermal image[J]. Computers & Electrical Engineering, 2017, 58: 88-100.
[10]	王力, 李硕, 武会杰, 等. 基于红外技术的机载电路板故障诊断研究[J]. 计算机仿真, 2017, 34(7): 89-93. https://www.cnki.com.cn/Article/CJFDTOTAL-JSJZ201707019.htm WANG Li, LI Shuo, WU Huijie, et al. Research of aviation circuit board fault diagnosis and prediction based on infrared technology[J]. Computer Simulation, 2017, 34(7): 89-93. https://www.cnki.com.cn/Article/CJFDTOTAL-JSJZ201707019.htm
[11]	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. http://hwjs.nvir.cn/article/id/hwjs201903013 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. http://hwjs.nvir.cn/article/id/hwjs201903013
[12]	王力, 刘子奇. WPA-IGA-BP神经网络的模拟电路故障诊断[J]. 系统工程与电子技术, 2021, 43(4): 1133-1143. https://www.cnki.com.cn/Article/CJFDTOTAL-XTYD202104034.htm WANG Li, LIU Ziqi. Fault diagnosis of analog circuit for WPA-IGA-BP neural network[J]. System Engineering and Electronics, 2021, 43(4): 1133-1143. https://www.cnki.com.cn/Article/CJFDTOTAL-XTYD202104034.htm
[13]	GUO Y, RAN C, JI X, et al. Fault diagnosis in analog circuits based on combined-optimization BP neural networks[J]. Journal of Northwestern Polytechnical University, 2013, 1: 44-48.
[14]	XUE J, SHEN B. A novel swarm intelligence optimization approach: sparrow search algorithm[J]. Systems Science & Control Engineering An Open Access Journal, 2020, 8(1): 22-34.
[15]	Reynolds Andy. Liberating Lévy walk research from the shackles of optimal foraging[J]. Physics of Life Reviews, 2015, 14: 59-83.