基于OCKELM与增量学习的在线故障检测方法

戴金玲; 许爱强; 申江江; 王树友

doi:10.7527/S1000-6893.2021.25121

航空学报 >

2022 , Vol. 43 >Issue 3: 325121 - 325121

DOI: https://doi.org/10.7527/S1000-6893.2021.25121

电子电气工程与控制

基于OCKELM与增量学习的在线故障检测方法

戴金玲 ,
许爱强 ,
申江江 ,
王树友

展开

1. 海军航空大学航空作战勤务学院, 烟台 266001;
2. 91206部队, 青岛 266108

收稿日期: 2020-12-18

修回日期: 2021-01-26

网络出版日期: 2021-02-08

收起

Online fault detection method based on incremental learning and OCKELM

DAI Jinling ,
XU Aiqiang ,
SHEN Jiangjiang ,
WANG Shuyou

Expand

1. Naval Aviation University, Yantai 266001, China;
2. No. 91206 Troops of PLA, Qingdao 266108, China

Received date: 2020-12-18

Revised date: 2021-01-26

Online published: 2021-02-08

Fold

摘要

针对航空电子设备故障检测样本少、以及缺乏在线实时检测理论研究的问题，将一类核极限学习机（OCKELM）和数据增量学习（IL）相结合，实现对贯序来临的样本数据在线故障检测。基于正常状态下的样本数据，给出了OCKELM的核化形式，并推导了核函数和核权重向量的表达式；根据增量学习方法，在吸收新样本时更新核权重向量并估计样本输出值；最终基于2种阈值准则给出模型的检验阈值，对测试样本进行在线故障检测。将所提方法应用于UCI数据集和某航空电子设备的测试数据，实验结果表明:该方法的时间消耗在毫秒级别，实现了在线检测；且相比于现有的SVDD、PCA、OC-SVM方法，该方法在F1、AUC、G-mean和故障检测率等性能指标方面均表现优异。

关键词： 一类分类; 核极限学习机; 增量学习; 在线检测; 故障检测

本文引用格式

戴金玲 , 许爱强 , 申江江 , 王树友 . 基于OCKELM与增量学习的在线故障检测方法[J]. 航空学报, 2022 , 43(3) : 325121 -325121 . DOI: 10.7527/S1000-6893.2021.25121

Abstract

To solve the problems of less samples for avionics equipment fault detection and lack of online real-time detection theory, the One Class Kernel Extreme Learning Machine (OCKELM) is combined with the data driven method of Incremental Learning (IL) to realize online sequential fault detection. Based on the sample data in the normal state, the kernel form of OCKELM is given, and the expressions for the kernel function and kernel weight vector are deduced. According to the incremental learning method, the kernel weight vector is updated and the sample output value is estimated when new samples are absorbed. Finally, based on two kinds of threshold criteria, the inspection threshold of the model is given, and online fault detection of the test samples is carried out. The proposed method is applied to the test data of UCI data set and an avionics device. The experimental results show that the method can realize online detection. Compared with the existing SVDD, PCA and OC-SVM methods, the proposed method has better performance in terms of F1, AUC, G-mean, fault detection rate, and other performance indicators.

Key words： one class classification; kernel extreme learning; incremental learning; online detection; fault detection

参考文献

[1] 朱敏. 基于超限学习机的航空电子设备PHM关键技术研究[D]. 烟台:海军航空大学,2019:10-20. ZHU M. Research on key technologies of PHM for avionics based on extreme learning machine[D]. Yantai:Naval Aviation University, 2019:10-20(in Chinese).
[2] PENG K X, ZHANG K, LI G. Online contribution rate based fault diagnosis for nonlinear industrial processes[J]. ActaAutomatica Sinica, 2014, 40(3):423-430.
[3] 范仁周, 陈瑞林, 张锡明. 机载电子设备地面仿真检测系统[J]. 航空学报, 1990, 11(2):47-53. FAN R Z, CHEN R L, ZHANG X M. Aground simulation-inspection system for avionic devices[J]. Acta Aeronautica et Astronautica Sinica, 1990, 11(2):47-53(in Chinese).
[4] 刘江平, 王冬青, 马莉莉, 等. 航空装备故障检测决策建模仿真研究[J]. 计算机仿真, 2015, 32(4):79-82. LIU J P, WANG D Q, MA LL, et al. Simulation on aviation equipment fault detection decision model based on UML[J]. Computer Simulation, 2015, 32(4):79-82(in Chinese).
[5] 翟旭升, 杨仕美, 段朋振, 等. 航空发动机非线性分布式控制系统故障检测[J]. 电光与控制, 2020, 27(7):106-110. ZHAI X S, YANG S M, DUAN P Z, et al. Fault detection for aeroengine's nonlinear distributed controlsystem[J]. Electronics Optics & Control, 2020, 27(7):106-110(in Chinese).
[6] 缑林峰, 王镛根. 航空发动机控制系统故障检测仿真平台研究[J]. 计算机仿真, 2007, 24(12):74-76, 80. GOU L F, WANG Y G. A fault detection simulation platform foraero engine control system[J]. Computer Simulation, 2007, 24(12):74-76, 80(in Chinese).
[7] 陶立权, 刘程, 张正, 等. 基于观测器的传感器故障检测方法对比分析[J]. 航空发动机, 2020, 46(3):46-53. TAO L Q, LIU C, ZHANG Z, et al.Comparison and analysis of sensor fault detection methods based on observer[J]. Aeroengine, 2020, 46(3):46-53(in Chinese).
[8] 薄翠梅, 李俊, 张广明, 等. 自适应阈值故障检测方法在DAMADICS基准平台中的应用[J]. 计算机集成制造系统, 2010, 16(6):1279-1285. BO C M, LI J, ZHANG G M, et al. Application of fault detection based on adaptive threshold in the DAMDDICS benchmarkproblem[J]. Computer Integrated Manufacturing Systems, 2010, 16(6):1279-1285(in Chinese).
[9] YIN S, GAO H J, QIU J B, et al. Fault detection for nonlinear process with deterministic disturbances:A just-in-time learning based data driven method[J]. IEEE Transactions on Cybernetics, 2017, 47(11):3649-3657.
[10] SMART E, BROWN D, AXEL-BERG L. Comparing one and two class classification methods for multiple fault detection on an induction motor[C]//2013 IEEE Symposium on Industrial Electronics & Applications. Piscataway:IEEE Press, 2013:132-137.
[11] 殷锴, 钟诗胜, 那媛, 等. 基于BP神经网络的航空发动机故障检测技术研究[J]. 航空发动机, 2017, 43(1):53-57. YIN K, ZHONG SS, NA Y, et al. Research on aeroengine fault detection technology based on BP neural network[J]. Aeroengine, 2017, 43(1):53-57(in Chinese).
[12] 崔芮华, 李锋锋, 李英男, 等. 基于连续小波Tsallis奇异熵的航空交流电弧故障检测[J]. 电气传动, 2020, 50(12):93-98. CUI R H, LI FF, LI Y N, et al. AC arc-fault detection based on continuous wavelet tsallis singular entropy in airplane[J]. Electric Drive, 2020, 50(12):93-98(in Chinese).
[13] 丁建立, 邹云开, 王静, 等. 基于深度学习的ADS-B异常数据检测模型[J]. 航空学报, 2019, 40(12):323220. DING J L, ZOU Y K, WANG J, et al. ADS-B anomaly data detection model based on deeplearning[J]. Acta Aeronautica et Astronautica Sinica, 2019, 40(12):323220(in Chinese).
[14] 罗鹏, 王布宏, 李腾耀. 基于BiGRU-SVDD的ADS-B异常数据检测模型[J]. 航空学报, 2020, 41(10):323878. LUO P, WANG B H, LI T Y. ADS-B anomaly data detection model based onBiGRU-SVDD[J]. Acta Aeronautica et Astronautica Sinica, 2020, 41(10):323878(in Chinese).
[15] MOYA M, KOCH M, HOSTETLER L. One-class classifier networks for target recognition applications:SAND-93-0084C[R]. Washington, D.C.:NASA, 1993:797-801.
[16] TAX D M J. One-class classification[D]. Delft:Delft University of Technology, 2001.
[17] COHEN G,HILARIO M, SAX H, et al. An application of one-class support vector machine to nosocomial infection detection[J]. Studies in Health Technology and Informatics, 2004, 107(Pt 1):716-720.
[18] TAX D M J, MULLER K R. A consistency-based model selection for one-class classification[C]//Proceedings of the 17th International Conference on Pattern Recognition. Piscataway:IEEE Press, 2004:363-366.
[19] 戴海发, 卞鸿巍, 马恒, 等. 基于一类SVM的综合导航系统信息故障检测方法[J]. 中国惯性技术学报, 2017, 25(4):555-560. DAI H F, BIAN H W, MA H, et al. Information fault detection for integrated navigation systems using one-class support vectormachine[J]. Journal of Chinese Inertial Technology, 2017, 25(4):555-560(in Chinese).
[20] TAX D M J, DUIN R P W. Support vector data description[J]. MachineLearning, 2004, 54(1):45-66.
[21] MANSOURI M, NOUNOU M, NOUNOU H, et al. Kernel PCA-based GLRT for nonlinear fault detection of chemical processes[J]. Journal of Loss Prevention in the Process Industries, 2016, 40:334-347.
[22] IOSIFIDIS A, MYGDALIS V, TEFAS A, et al. One-class classification based on extreme learning and geometric class information[J]. Neural Processing Letters, 2017, 45(2):577-592.
[23] LENG Q, QI H G, MIAO J, et al. One-class classification with extreme learning machine[J]. Mathematical Problems in Engineering, 2015, 2015:1-11.
[24] GAUTAM C, TIWARI A, LENG Q. On the construction of extreme learning machine for online and offline one-class classification-An expanded toolbox[J]. Neurocomputing, 2017, 261:126-143.
[25] 朱敏, 刘奇, 刘星, 等. 基于LMKL和OC-ELM的航空电子部件故障检测方法[J]. 系统工程与电子技术, 2020, 42(6):1424-1432. ZHU M, LIU Q, LIU X, et al. Fault detection method for avionics based on LMKL and OC-ELM[J]. Systems Engineering and Electronics, 2020, 42(6):1424-1432(in Chinese).
[26] GUO L, HAO J H, LIU M. An incremental extreme learning machine for online sequential learning problems[J]. Neurocomputing, 2014, 128:50-58.
[27] SCARDAPANE S, COMMINIELLO D, SCARPINITI M, et al. Onlinesequential extreme learning machine with kernels[J]. IEEE Transactions on Neural Networks and Learning Systems, 2015, 26(9):2214-2220.
[28] 朱敏, 许爱强, 陈强强, 等. 一种基于改进KELM的在线状态预测方法[J]. 北京航空航天大学学报, 2019, 45(7):1370-1379. ZHU M, XU A Q, CHEN QQ, et al. An improved KELM based online condition prediction method[J]. Journal of Beijing University of Aeronautics and Astronautics, 2019, 45(7):1370-1379(in Chinese).
[29] 张英堂, 马超, 李志宁, 等. 基于快速留一交叉验证的核极限学习机在线建模[J]. 上海交通大学学报, 2014, 48(5):641-646. ZHANG Y T, MA C, LI Z N, et al. Online modeling of kernel extreme learning machine based on fast leave-one-out cross-validation[J]. Journal of Shanghai Jiao Tong University, 2014, 48(5):641-646(in Chinese).
[30] DAI J L, XU A Q, LIU X, et al. Onlinesequential model for multivariate time series prediction with adaptive forgetting factor[J]. IEEE Access, 2020, 8:175958-175971.
[31] TAX D M J. DDtools, the data description toolbox for Matlab[EB/OL].(2013-07-24)[2020-12-10]. http://prlab.tudeft.nl/david-tax/dd_tools.html.

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献