lp范数约束的模拟电路3层多核故障诊断模型

doi:10.3969/j.issn.1000-1093.2018.07.013

摘要/Abstract

摘要： 为提升模拟电路故障隔离精度，结合基于故障特征间一维模糊度的特征选择算法，提出一种改进的l_p范数约束多核超限学习机诊断模型。该模型通过将带权分类误差融入超限学习机优化目标函数中，基于自适应Boosting策略构建了一种3层多核学习框架。在新框架下通过自适应调整训练样本的权重分布，使得每层框架能够聚焦于不同故障样本，进而提升诊断模型的辨识力。通过对2个电路实例的诊断，结果表明：所提模型在不同范数约束下具有近似一致的诊断性能；当故障属性单一时，在平衡漏警、虚警的同时，能够显著提升诊断正确率；当多种属性的故障并存时，能够将难以辨识的故障更加准确地隔离到少数模糊组中。

关键词: 模拟电路, l_p范数约束, 多核学习, 超限学习机, 集成学习, 模糊组, 故障诊断

Abstract: In order to improve the fault diagnostic accuracy of analog circuit, an improved l_p-norm multiple kernel extreme learning machine (ELM) diagnostic model is proposed based on the feature selection algorithm with one-dimensional ambiguity among fault features. In this model, the weighted classification error is incorporated into kernel ELM optimized objective function, and then a three-layer multiple kernel learning framework is constructed based on adaptive boosting (AdaBoost) algorithm, in which the training sample weights are adaptively adjusted so that the every layer in the model can focus on the different training samples. The proposed model provides an excellent strategy to improve the identifiability of classifier. Experimental results of two analog circuits show that the proposed model can achieve approximately consistent diagnostic performance under the constraints of different norms. For a fault with a single attri- bute, the diagnostic accuracy can be significantly improved, meanwhile the missing alarm and false alarm can be effectively balanced. For a fault with multiple attributes, the faults which are difficult to be identified can be accurately isolated into relevant ambiguity groups. Key

Key words: analogcircuit, l_p-normconstraint, multiplekernellearning, extremelearningmachine, ensemblelearning, ambiguitygroup, faultdiagnosis

中图分类号:

V243.2
TP181

张伟，刘星，许爱强，平殿发. l_p范数约束的模拟电路3层多核故障诊断模型[J]. 兵工学报, 2018, 39(7): 1352-1363.

ZHANG Wei， LIU Xing, XU Ai-qiang， PING Dian-fa. Three-layer Multiple Kernel Fault Diagnosis Model with l_p-norm Constraint for Analog Circuit[J]. Acta Armamentarii, 2018, 39(7): 1352-1363.

参考文献

［1］ Ao Y C, Shi Y B, Zhang W, et al. An approximate calculation of ratio of normal variables and its application in analog circuit fault diagnosis［J］. Journal of Electronic Testing, 2013, 29(4):555-565.
［2］ Han H, Wang H J, Tian S L, et al. A new analog circuit fault diagnosis method based on improved Mahalanobis distance［J］. Journal of Electronic Testing, 2013, 29(1): 95-102.
［3］ 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.
［4］田恒, 段富海, 江秀红, 等. 基于准信息熵的测试性D矩阵故障诊断新算法［J］. 兵工学报, 2016, 37(5):923-928.
TIAN Heng, DUAN Fu-hai, JIANG Xiu-hong, et al. A novel fault diagnosis algorithm of testability D matrix based on quasi information entropy［J］. Acta Armamentarii, 2016, 37(5):923-928.(in Chinese)
［5］ Hu H Z, Tian S L, Guo Q, et al. The application of HIWO-SVM in analog circuit fault diagnosis［J］. International Journal of Pattern Recognition and Artificial Intelligence, 2015, 29(8): 1550019.
［6］ 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.
［7］严峰, 陈晓, 王新民, 等. 改进的离散小波-优化极限学习机在倾转旋翼机故障诊断中的应用［J］. 兵工学报, 2014,35(11): 1914-1921.
YAN Feng, CHEN Xiao, WANG Xin-min, et al. Fault diagnosis of tiltrotor aircraft via improved discrete wavelet-OMELM［J］. Acta Armamentarii, 2014, 35(11): 1914-1921.(in Chinese)
［8］ Feng J, Jiao L C, Sun T, et al. Multiple kernel learning based on discriminative kernel clustering for hyperspectral band selection［J］. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(11):6516-6530.
［9］ Wang T H, Zhao D Y, Feng Y S. Two-stage multiple kernel learning with multiclass kernel polarization［J］. Knowledge-Based Systems, 2013, 48(2):10-16.

［10］ Ye Q, Pan H. Simultaneous fault diagnosis of main retarder using improved paired relevance vector machine based on multi-kernel learning［J］. Applied Mechanics and Materials, 2014, 614:339- 344.
［11］ Ye F M, Zhang Z B, Chakrabarty K, et al. Board-level functional fault diagnosis using multi-kernel support vector machines and incremental learning［J］. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2014, 33(2):279-290.
［12］ Liu X W, Wang L, Huang G B, et al. Multiple kernel extreme learning machine［J］. Neurocomputing, 2015, 149: 253-264.
［13］ Li X D, Mao W J, Jiang W. Multiple-kernel-learning-based extreme learning machine for classification design［J］. Neural Computing & Applications, 2016, 27(1):175-184.
［14］ Fossaceca J M, Mazzuchi T A, Sarkani S. MARK-ELM: application of a novel multiple kernel learning framework for improving the robustness of network intrusion detection［J］. Expert Systems with Applications, 2015, 42(8): 4062-4080.
［15］ Xia H, Hoi S C. MKBoost: a framework of multiple kernel boosting［J］. IEEE Transactions on Knowledge and Data Engineering, 2013, 25(7):1574-1586.
［16］ Pawel C. Evaluation measures for kernel optimization［J］. Pattern Recognition Letters, 2012, 33(9):1108-1116.
［17］ Peng H C, Long F H, Ding C. Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(8): 1226-1238.
［18］ Rakotomamonjy A, Bach F R, Canu S, et al. SimpleMKL ［J］. Journal of Machine Learning Research, 2008, 9(11): 2491-2521.
［19］ Liu X W, Zhou L P, Wang L, et al. An efficient radius-incorporated MKL algorithm for Alzheimer's disease prediction［J］. Pattern Recognition, 2015, 48(7):2141-2150.
［20］ Liu X W, Wang L, Yin J P, et al. Incorporation of radius-info can be simple with simple MKL［J］. Neurocomputing, 2012, 89(10): 30-38.

第39卷
第7期2018 年7月兵工学报ACTA
ARMAMENTARIIVol.39No.7Jul.2018

[1]	李良钰，苏铁熊，马富康，吴小军，徐春龙. 基于集合经验模态分解-支持向量机的高压共轨系统故障诊断方法[J]. 兵工学报, 2022, 43(5): 992-1001.
[2]	李志农, 胡志峰, 毛清华, 张旭辉, 陶俊勇. 非线性调频模态分解-同步提取变换方法及其在滚动轴承故障诊断中的应用[J]. 兵工学报, 2021, 42(6): 1324-1330.
[3]	朱敏，许爱强，许晴，李睿峰. 基于改进多层核超限学习机的模拟电路故障诊断[J]. 兵工学报, 2021, 42(2): 356-369.
[4]	李佳蔚，崔涛，刘宇航，师帅楠，孙强. 基于排气温度动态模型的在线观测器研究[J]. 兵工学报, 2019, 40(8): 1562-1571.
[5]	闫理跃, 王厚军, 刘震. 一种结合噪声辅助技术和现场数据的模拟电路实时可靠度预测方法[J]. 兵工学报, 2019, 40(2): 326-333.
[6]	郭伟超，赵怀山，李成，李言，汤奥斐. 基于小波包能量谱与主成分分析的轴承故障特征增强诊断方法[J]. 兵工学报, 2019, 40(11): 2370-2377.
[7]	翟禹尧，史贤俊，吕佳朋. 基于广义随机Petri网的导弹系统测试性建模与指标评估方法研究[J]. 兵工学报, 2019, 40(10): 2070-2079.
[8]	任海锋，潘宏侠. 基于多分形特征的枪械自动机裂纹故障诊断[J]. 兵工学报, 2018, 39(3): 457-462.
[9]	王英敏，崔涛，张付军，董天普. 基于局部线性模型树模型的柴油机进气系统漏气和堵塞故障诊断[J]. 兵工学报, 2017, 38(8): 1457-1468.
[10]	黄大荣, 陈长沙，孙国玺，赵玲，米波. 复杂装备轴承多重故障的线性判别分析与反向传播神经网络协作诊断方法[J]. 兵工学报, 2017, 38(8): 1649-1657.
[11]	李志农，朱明. 基于变分模态分解的机械故障诊断方法研究[J]. 兵工学报, 2017, 38(3): 593-599.
[12]	李海广，潘宏侠，任海锋. 基于冲击响应谱特征提取的自动机裂纹故障诊断[J]. 兵工学报, 2016, 37(9): 1744-1752.
[13]	田恒，段富海，江秀红，桑勇. 基于准信息熵的测试性D矩阵故障诊断新算法[J]. 兵工学报, 2016, 37(5): 923-928.
[14]	李志农，王海峰，肖尧先. 基于分数阶微积分的裂纹转子系统非线性动力学特性研究[J]. 兵工学报, 2015, 36(9): 1790-1798.
[15]	王福元，赵建社，唐霖. 多系统集成电解加工控制策略与故障诊断方法研究[J]. 兵工学报, 2015, 36(6): 1074-1081.