WPA-IGA-BP神经网络的模拟电路故障诊断

doi:10.12305/j.issn.1001-506X.2021.04.32

摘要/Abstract

摘要：

针对模拟电路渐变性故障中的特征提取困难和故障信号无法进行有效分类的问题, 提出利用免疫遗传算法(immune genetic algorithm, IGA)优化反向传播(back propagation, BP)神经网络中参数寻优过程, 从而实现模拟电路故障诊断。首先, 采用小波包分析(wavelet package analysis, WPA), 对模拟电路输出响应进行4层小波分解和重构, 完成特征向量的提取。然后, 采用IGA优化BP神经网络进行训练及测试, 实现对不同故障进行故障诊断。最后, 通过两个模拟电路仿真实验对该方法进行实验验证。实验结果表明, 与优化前的BP神经网络相比, 所提方法提高故障诊断的准确率约15%。

关键词: 反向传播神经网络, 免疫遗传算法, 模拟电路, 特征提取, 故障诊断

Abstract:

In the view of the difficulty in feature extraction and failure signal classification in analog circuit with gradual change, an immune genetic algorithm (IGA) is proposed to optimize the parameter optimization process in back propagation (BP) neural network, so as to realize analog circuit fault diagnosis. Firstly, the wavelet package analysis (WPA) is used to decompose and reconstruct the output response of analog circuit in four layers, and the feature vector is extracted. Then, the IGA optimized BP neural network is used for training and testing to realize fault diagnosis of different faults. Finally, the two simulation methods are verified by simulation. The experimental results show that, compared with the BP neural network before optimization, the proposed method improves the accuracy of fault diagnosis by about 15%.

Key words: back propagation (BP) neural network, immune genetic algorithm (IGA), analog circuit, feature extraction, fault diagnosis

中图分类号:

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.

Li WANG, Ziqi LIU. Fault diagnosis of analog circuit for WPA-IGA-BP neural network[J]. Systems Engineering and Electronics, 2021, 43(4): 1133-1143.

图/表 21

图1

图2

图3

图4

图5

表1

图6

图7

图8

图9

图10

表2

图11

表3

图12

图13

图14

图15

图16

图17

表4

参考文献 31

1	高明哲, 许爱强, 唐小峰, 等. 基于多核多分类相关向量机的模拟电路故障诊断方法[J]. 自动化学报, 2019, 45 (2): 434- 444.
	GAO M Z , XU A Q , TANG X F , et al. Fault diagnosis method of analog circuit based on multi-core multi-classification correlation vector machine[J]. Acta Automatica Sinica, 2019, 45 (2): 434- 444.
2	TANG X F , XU A Q . Practical analog circuit diagnosis based on fault features with minimum ambiguities[J]. Journal of Electronic Testing, 2016, 32 (1): 83- 95. doi: 10.1007/s10836-015-5561-1
3	TADEUSIEWICZ M , HALGAS S . A method for local parametric fault diagnosis of a broad class of analog integrated circuits[J]. IEEE Trans.on Instrumentation and Measurement, 2018, 67 (2): 328- 337. doi: 10.1109/TIM.2017.2775438
4	SAI S V A , LONG B , PECHT M . Diagnostics and prognostics method for analog electronic circuits[J]. IEEE Trans.on Industrial Electronics, 2013, 60 (11): 5277- 5291. doi: 10.1109/TIE.2012.2224074
5	TIAN S L , YANG C L , CHEN F , et al. Circle equation-based fault modeling method for linear analog circuits[J]. IEEE Trans.on Instrumentation and Measurement, 2014, 63 (9): 2145- 2159. doi: 10.1109/TIM.2014.2307993
6	YANG C L , YANG J , LIU Z , et al. Complex field fault modeling-based optimal frequency selection in linear analog circuit fault diagnosis[J]. IEEE Trans.on Instrumentation and Measurement, 2014, 63 (4): 813- 825. doi: 10.1109/TIM.2013.2289074
7	XIONG J , TIAN S L , YANG C L . Fault diagnosis for analog circuits by using EEMD, relative entropy, and ELM[J]. Computational Intelligence & Neuroscience, 2016, 7657054.
8	SAHA B, GOEBEL K. Uncertainty management for diagnostics and prognostics of batteries using Bayesian techniques[C]//Proc.of the IEEE Aerospace Conference, 2008.
9	CUI Y Q , SHI J Y , WANG Z L . Analog circuits fault diagnosis using multi-valued Fisher's fuzzy decision tree (MFFDT)[J]. International Journal of Circuit Theory & Applications, 2016, 44 (1): 240- 260.
10	CUI Y Q , SHI J Y , WANG Z L . Analog circuit fault diagnosis based on quantum clustering based multi-valued quantum fuzzification decision tree (QC-MQFDT)[J]. Measurement, 2016, 93, 421- 434. doi: 10.1016/j.measurement.2016.07.018
11	YE F , ZHANG Z , CHAKRABARTY K , et al. Board-level functional fault diagnosis using multikernel support vector machines and incremental learning[J]. IEEE Trans.on Computer-Aided Design of Integrated Circuits and Systems, 2014, 33 (2): 279- 290. doi: 10.1109/TCAD.2013.2287184
12	WANG Z, ZARADER J L, ARGENTIERI S. A novel aircraft engine fault diagnostic and prognostic system based on SVM[C]//Proc.of the IEEE International Conference on Condition Monitoring and Diagnosis, 2013.
13	JIANG Y Y , WANG Y R , LUO H . Fault diagnosis of analog circuit based on a second map SVDD[J]. Analog Integrated Circuits and Signal Processing, 2015, 85 (3): 395- 404. doi: 10.1007/s10470-015-0597-9
14	ZHANG A H , CHEN C , JIANG B S . Analog circuit fault diagnosis based UCISVM[J]. Neurocomputing, 2016, 173 (1): 1752- 1760.
15	DING G J , WANG L D , YANG P , et al. Analog circuit fault diagnosis based on morphological wavelet and least squares support vector machine[J]. International Journal of Digital Content Technology and Its Applications, 2012, 6 (20): 211- 220. doi: 10.4156/jdcta.vol6.issue20.23
16	杨晓朋, 陈伟, 王鹏展, 等. 基于DCCA-IWO-MKSVM的模拟电路故障诊断方法[J]. 计算机应用与软件, 2020, 37 (1): 271- 276.
	YANG X P , CHEN W , WANG P Z , et al. Fault diagnosis method of analog circuit based on DCCA-IWO-MKSVM[J]. Computer Application and Software, 2020, 37 (1): 271- 276.
17	ZHANG C L , HE Y G , YUAN L F , et al. A novel approach for diagnosis of analog circuit fault by using GMKL-SVM and PSO[J]. Journal of Electronic Testing, 2016, 32 (5): 531- 540. doi: 10.1007/s10836-016-5616-y
18	SHEIKHAN M , AMIR A . PSO-optimized modular neural network trained by OWO-HWO algorithm for fault location in analog circuits[J]. Neural Computing and Applications, 2013, 23 (2): 519- 530. doi: 10.1007/s00521-012-0947-9
19	邵继业, 谢昭灵, 杨瑞. 基于GA-PSO优化BP神经网络的压缩机气阀故障诊断[J]. 电子科技大学学报, 2018, 47 (5): 781- 787. doi: 10.3969/j.issn.1001-0548.2018.05.023
	SHAO J Y , XIE Z L , YANG R . Fault diagnosis of compressor valve based on ga-pso optimization BP neural network[J]. Journal of University of Electronic Science and Technology, 2018, 47 (5): 781- 787. doi: 10.3969/j.issn.1001-0548.2018.05.023
20	SHI J Y , DENG Y , WANG Z L . Analog circuit fault diagnosis based on density peaks clustering and dynamic weight probabilistic neural network[J]. Neurocomputing, 2020, 407, 354- 365. doi: 10.1016/j.neucom.2020.04.113
21	WANG Y , MA Y , CUI S , et al. A novel approach of feature extraction for analog circuit fault diagnosis based on WPD-LLE-CSA[J]. Journal of Electrical Engineering and Technology, 2018, 13 (6): 2485- 2492.
22	XIONG L , LI K S , YANG L . A parallel immune genetic algorithm for community detection in complex networks[J]. International Journal of High Performance Computing and Networking, 2018, 11 (3): 242- 250. doi: 10.1504/IJHPCN.2018.091895
23	GANGSAR P , TIWARI R . Multifault diagnosis of induction motor at intermediate operating conditions using wavelet packet transform and support vector machine[J]. Journal of Dynamic Systems Measurement and Control, 2018, 140 (8): 081014. doi: 10.1115/1.4039204
24	SINGH S P, UROOJ S. Wavelet packets based spectral estimation of textured images[C]//Proc.of the IEEE International Conference on Computational Intelligence and Communication Technology, 2015: 651-654.
25	GAN X S , GAO W M , DAI Z , et al. Research on WNN soft fault diagnosis for analog circuit based on adaptive UKF algorithm[J]. Applied Soft Computing, 2017, 50 (C): 252- 259.
26	MIAO M , JIANG J G . Analog circuit fault diagnosis method based on optimized BP neural network[J]. International Journal of Digital Content Technology and its Applications, 2013, 7 (6): 774- 781. doi: 10.4156/jdcta.vol7.issue6.87
27	杨云龙, 徐自强, 吴孟强, 等. 基于免疫遗传算法的动力电池SOC估计研究[J]. 计算机测量与控制, 2018, 26 (12): 220- 224.
	YANG Y L , XU Z Q , WU M Q , et al. Research on SOC estimation of power battery based on immune genetic algorithm[J]. Computer Measurement and Control, 2018, 26 (12): 220- 224.
28	XIE T , HE Y G . Fault diagnosis of analog circuit based on high-order cumulants and information fusion[J]. Journal of Electronic Testing, 2014, 30 (5): 505- 514. doi: 10.1007/s10836-014-5478-0
29	KUMAR A , SINGH A P . Fuzzy classifier for fault diagnosis in analog electronic circuits[J]. ISA Transaction, 2013, 52 (6): 816- 824. doi: 10.1016/j.isatra.2013.06.006
30	YU W X , HE Y G . Analog circuit fault diagnosis via sensitivity computation[J]. Journal of Electronic Testing, 2015, 31 (1): 119- 122. doi: 10.1007/s10836-015-5509-5
31	LIU Z B , LIU T M , HAN J W , et al. Signal model-based fault coding for diagnostics and prognostics of analog electronic circuits[J]. IEEE Trans.on Industrial Electronics, 2017, 64 (1): 605- 614. doi: 10.1109/TIE.2016.2599142

故障编号	故障类型	标称值	故障值
F0	正常	—	—
F1	R1↑	40 kΩ	45 kΩ~90 kΩ
F2	R1↓	40 kΩ	35 kΩ~10 kΩ
F3	R2↑	18 kΩ	20 kΩ~40 kΩ
F4	R3↑	1 kΩ	1.2 kΩ~3 kΩ
F5	R3↓	1 kΩ	0.9 kΩ~0.1 kΩ
F6	R4↑	3 kΩ	3.5 kΩ~6.5 kΩ
F7	C3↑	470 μF	500 μF~750 μF

故障编号	故障类型	标称值	故障值
F0	正常	—	—
F1	R1↑	6.2 kΩ	9 kΩ~12 kΩ
F2	R1↓	6.2 kΩ	3 kΩ~1 kΩ
F3	R3↑	6.2 kΩ	9 kΩ~12 kΩ
F4	C1↓	5 μF	2 μF~0.5 μF
F5	R4↑	1.6 kΩ	2.4 kΩ~4 kΩ
F6	C2↑	5 μF	10 μF~15 μF
F7	R7↑	10 kΩ	15 kΩ~20 kΩ
F8	R7↓	10 kΩ	5 kΩ~1 kΩ

诊断模型	故障模式	训练样本		测试样本
诊断模型	故障模式	样本数量	时间/s	样本数量	正确数	正确率/%	时间/s
BP神经网络	正常	66	31.958 24	33	30	91	0.127 729 3
	R1↑	66	31.958 24	33	21	64	0.127 729 3
	R1↓	66	31.958 24	33	23	70	0.127 729 3
	R3↑	66	31.958 24	33	28	85	0.127 729 3
	C1↓	66	31.958 24	33	29	88	0.127 729 3
	R4↑	66	31.958 24	33	33	100	0.127 729 3
	C2↑	66	31.958 24	33	31	94	0.127 729 3
	R7↑	66	31.958 24	33	20	61	0.127 729 3
	R7↓	66	31.958 24	33	19	58	0.127 729 3
GA-BP神经网络	正常	66	28.196 34	33	32	97	0.134 497
	R1↑	66	28.196 34	33	27	82	0.134 497
	R1↓	66	28.196 34	33	28	85	0.134 497
	R3↑	66	28.196 34	33	33	100	0.134 497
	C1↓	66	28.196 34	33	30	91	0.134 497
	R4↑	66	28.196 34	33	33	100	0.134 497
	C2↑	66	28.196 34	33	31	94	0.134 497
	R7↑	66	28.196 34	33	25	76	0.134 497
	R7↓	66	28.196 34	33	23	70	0.134 497
IGA-BP神经网络	正常	66	24.315 7	33	33	100	0.014 457 4
	R1↑	66	24.315 7	33	30	91	0.014 457 4
	R1↓	66	24.315 7	33	32	97	0.014 457 4
	R3↑	66	24.315 7	33	33	100	0.014 457 4
	C1↓	66	24.315 7	33	33	100	0.014 457 4
	R4↑	66	24.315 7	33	33	100	0.014 457 4
	C2↑	66	24.315 7	33	33	100	0.014 457 4
	R7↑	66	24.315 7	33	30	91	0.014 457 4
	R7↓	66	24.315 7	33	31	94	0.014 457 4

[1]	马泽煊, 李进, 路艳丽, 陈晨. 融合WaveNet和BiGRU的网络入侵检测方法[J]. 系统工程与电子技术, 2022, 44(8): 2652-2660.
[2]	李郝亮, 陈思伟, 王雪松. 海面角反射器的极化旋转域特性研究[J]. 系统工程与电子技术, 2022, 44(7): 2065-2073.
[3]	高升, 马广富, 郭延宁. 基于自适应未知输入观测器的多故障快速重构[J]. 系统工程与电子技术, 2022, 44(7): 2364-2373.
[4]	侯召国, 王华伟, 周良, 付强. 基于改进深度残差网络的旋转机械故障诊断[J]. 系统工程与电子技术, 2022, 44(6): 2051-2059.
[5]	石宸睿, 田露, 徐湛, 职如昕, 陈晋辉. 基于PSO-BP的应急通信感知装备效能评价方法[J]. 系统工程与电子技术, 2022, 44(11): 3455-3462.
[6]	朱峰, 蒋倩倩, 林川, 杨啸. 基于支持向量机的典型宽带电磁干扰源识别[J]. 系统工程与电子技术, 2021, 43(9): 2400-2406.
[7]	刘星, 王文双, 赵建印, 朱敏. 自适应在线增量ELM的故障诊断模型研究[J]. 系统工程与电子技术, 2021, 43(9): 2678-2687.
[8]	苏瑜, 荆文芳, 卢晓春, 张阳. 基于BP-PID控制的载波频率准确度提高算法[J]. 系统工程与电子技术, 2021, 43(7): 1894-1903.
[9]	李睿峰, 许爱强, 孙伟超, 王树友. 基于元学习的航空电子设备特征选择算法推荐方法[J]. 系统工程与电子技术, 2021, 43(7): 2011-2020.
[10]	陈洪转, 赵爱佳, 李腾蛟, 蔡匆聪, 程硕, 徐春丽. 基于故障树的复杂装备模糊贝叶斯网络推理故障诊断[J]. 系统工程与电子技术, 2021, 43(5): 1248-1261.
[11]	陈浩, 杨俊安, 刘辉. 基于深度残差适配网络的通信辐射源个体识别[J]. 系统工程与电子技术, 2021, 43(3): 603-609.
[12]	戴金玲, 许爱强. 基于动态软聚类的航空电子部件LMKELM诊断模型[J]. 系统工程与电子技术, 2021, 43(3): 637-646.
[13]	孟晨, 杨华晖, 王成, 马征. 数据驱动的武器系统电子元部件级故障诊断研究综述[J]. 系统工程与电子技术, 2021, 43(2): 574-583.
[14]	张国令, 吴崇明, 李睿, 来杰, 向前. 基于一维堆叠池化融合卷积自编码器的HRRP目标识别方法[J]. 系统工程与电子技术, 2021, 43(12): 3533-3541.
[15]	赵若辰, 王敬东, 林思玉, 顾东泽. 基于卷积神经网络的小型建筑物检测算法[J]. 系统工程与电子技术, 2021, 43(11): 3098-3106.