基于数值微分的树突状细胞故障检测方法

doi:10.3969/j.issn.0372-2112.2019.05.008

电子学报 ›› 2019, Vol. 47 ›› Issue (5): 1029-1035.DOI: 10.3969/j.issn.0372-2112.2019.05.008

基于数值微分的树突状细胞故障检测方法

肖振华, 梁意文, 谭成予, 周雯, 刘维炜

武汉大学计算机学院, 湖北武汉 430072

收稿日期:2018-08-22 修回日期:2019-01-31 出版日期:2019-05-25
- 通讯作者:
- 梁意文
- 作者简介:
- 肖振华 男,1981年生于湖北武汉.武汉大学计算机学院博士研究生.研究方向为人工免疫系统、物联网安全.E-mail:desmen@126.com
- 基金资助:
- 国家自然科学基金 (No.61170306，No.61877045）; 国家863高技术研究发展计划 (No.2012AA09A410）; 深圳市科技计划 (No.JCYJ20170412151159461）

Dendritic Cell Fault Detection Method Based on Numerical Differentiation

XIAO Zhen-hua, LIANG Yi-wen, TAN Cheng-yu, ZHOU Wen, LIU Wei-wei

School of Computer Science, Wuhan University, Wuhan, Hubei 430072, China

Received:2018-08-22 Revised:2019-01-31 Online:2019-05-25 Published:2019-05-25

摘要/Abstract

摘要： 针对现有树突状细胞算法（dendritic cell algorithm，DCA）在不同类型设备的故障检测中严重依赖人工经验定义输入信号，缺乏适应性和完备性，提出了一种基于数值微分的树突状细胞故障检测模型——NDDC-FD.首先，引入变化是系统危险发生的征兆和外在表现的思想，提出了一种基于变化危险感知的信号自适应提取方法，采用数值微分描述数据的变化，再从变化中提取输入信号.其次，原DC模型中异常抗原的评价方式对突变性故障能有效检测，却无法及时发现渐变性故障，提出了采用T细胞浓度作为故障评价指标.最后，在DAMADICS和TE两个基准平台上，将本文方法与原DCA算法和传统主元分析法（principal component analysis，PCA）进行比较测试.实验结果表明NDDC-FD方法不仅提高了原DCA算法的适应性，且和DCA、PCA相比具有较高检测率的同时，更能较早地检测到渐变性故障.因此，本文提出的故障检测方法NDDC-FD具有一般性，且性能良好.

关键词: 人工免疫系统, 树突状细胞, 数值微分, 故障检测

Abstract: Currently,the DCA (dendritic cell algorithm) relies heavily on artificial experience to define the input signals in fault detection of different types of equipment,which is lack of adaptability and completeness.To address this problem,we propose a dendritic cell fault detection model based on numerical differentiation——NDDC-FD.In first place,according to change is the symptom and outward expression of system which is in danger,an adaptive signal extraction method based on danger perception of system status change is proposed,which uses numerical differentiation to calculate the change to extract the input signals.Next,the anomaly antigen evaluation method of original DC model can effectively detect abrupt fault,but it can't detect incipient fault in time.Therefore,the fault evaluation indicator based on concentration of T cells is proposed.Finally,our method is tested on DAMADICS and TE benchmark,and compared with DCA and PCA (principal component analysis).The results show that NDDC-FD method not only improves the adaptability of DCA,but also has higher detection rate than DCA and PCA,and has lower detection delay time in incipient fault detection.Overall,our method is generality and has well performance in the fault detection of industrial equipment.

Key words: artificial immune systems, dendritic cells, numerical differentiation, fault detection

中图分类号:

TP277

肖振华, 梁意文, 谭成予, 周雯, 刘维炜. 基于数值微分的树突状细胞故障检测方法[J]. 电子学报, 2019, 47(5): 1029-1035.

XIAO Zhen-hua, LIANG Yi-wen, TAN Cheng-yu, ZHOU Wen, LIU Wei-wei. Dendritic Cell Fault Detection Method Based on Numerical Differentiation[J]. Acta Electronica Sinica, 2019, 47(5): 1029-1035.

参考文献

[1] 李晗,萧德云.基于数据驱动的故障诊断方法综述[J].控制与决策,2011,26(1):1-9. LI Han,XIAO e-yun.Survey on data driven fault diagnosis methods[J].Control and Decision,2011,26(1):1-9.(in Chinese)
[2] Dai X,Gao Z.From model,signal to knowledge:A data-driven perspective of fault detection and diagnosis[J].IEEE Transactions on Industrial Informatics,2013,9(4):2226-2238.
[3] Yin S,Li X,Gao H,et al.Data-based techniques focused on modern industry:An overview[J].IEEE Transactions on Industrial Electronics,2015,62(1):657-667.
[4] 汪楚娇,夏士雄,牛强.免疫粒子群算法及其在矿井提升机故障诊断中的应用[J].电子学报,2010,38(2A):94-98. WANG Chu-Jiao,XIA Shi-xiong,NIU Qiang.Artificial immune particle swarm optimization for fault diagnosis of mine hoist[J].Acta Electronica Sinica,2010,38(2A):94-98.(in Chinese)
[5] Kiang C C,Srinivasan R.An artificial immune system for adaptive fault detection,diagnosis and recovery[J].International Journal of Advances in Engineering Sciences & Applied Mathematics,2012,4(1-2):22-31.
[6] Bayar N,Darmoul S,Hajri-Gabouj S,et al.Fault detection,diagnosis and recovery using artificial immune systems:A review[J].Engineering Applications of Artificial Intelligence,2015,46(A):43-57.
[7] Silva G C,Caminhas W M,Palhares R M.Artificial immune systems applied to fault detection and isolation:A brief review of immune response-based approaches and a case study[J].Applied Soft Computing,2017,57(8):118-131.
[8] Matzinger P.Tolerance,danger,and the extended family[J].Annual review of immunology,1994,12(1):991-1045.
[9] Greensmith J,Aickelin U,Cayzer S.Introducing dendritic cells as a novel immune-inspired algorithm for anomaly detection[A].Proc of the 4th International Conference on Artificial Immune Systems[C].Heidelberg:Springer,2005.153-167.
[10] Greensmith J,Gale M B.The functional dendritic cell algorithm:A formal specification with haskell[A].Proc of the 2017 IEEE Congress on Evolutionary Computation[C].Donostia:IEEE,2017.1787-1794.
[11] Cui D,Zhang Q,Xiong J,et al.Fault diagnosis research of rotating machinery based on dendritic cell algorithm[A].Proc of the 2015 IEEE International Conference on Information and Automation[C].Lijiang:IEEE,2015.1020-1025.
[12] Iftikhar K,Khan M T,de Silva C W.Fault detection with sensor fusion using intelligent immune system[A].Proc of the 7th Annual Information Technology,Electronics and Mobile Communication Conference[C].Vancouver:IEEE,2016.1-6.
[13] Alizadeh E,Meskin N,Khorasani K.A dendritic cell immune system inspired scheme for sensor fault detection and isolation of wind turbines[J].IEEE Transactions on Industrial Informatics,2018,PP(99):1-1.
[14] Chelly Z,Elouedi Z.A survey of the dendritic cell algorithm[J].Knowledge and Information Systems,2016,48(3):505-535.
[15] 杨超,李涛.计算机免疫危险理论中危险信号的提取方法研究[J].计算机科学,2015,42(8):170-174. YANG Chao,LI Tao.Research of danger signal extraction based on changes in danger theory[J].Computer Science,2015,42(8):170-174.(in Chinese)
[16] 周福娜,文成林,陈志国,等.基于指定元分析的多级相对微小故障诊断方法[J].电子学报,2010,38(8):1874-1879. ZHOU Fu-na,WEN Cheng-lin,CHEN Zhi-guo,et al.DCA based multi-level small fault diagnosis method[J].Acta Electronica Sinica,2010,38(8):1874-1879.(in Chinese)
[17] 肖振华,梁意文,谭成予,等.基于免疫危险感知的水下接驳盒故障检测方法[J].工程科学与技术,2017,49(5):143-148. XIAO Zhen-hua,LIANG Yi-wen,TAN Cheng-yu,et al.Fault detection method of underwater junction box based on danger theory of immune system[J].Advanced Engineering Sciences,2017,49(5):143-148.(in Chinese)
[18] Zhou W,Liang Y,Dong H,et al.A numerical differentiation based dendritic cell model[A].Proc of the 2017 IEEE International Conference on TOOLS with Artificial Intelligence[C].Boston:IEEE,2017.1092-1098.
[19] Greensmith J,Aickelin U.The deterministic dendritic cell algorithm[A].Proc of the 7th International Conference on Artificial Immune Systems[C].Phuket:Springer,2008.291-302.
[20] 莫宏伟.基于混合方法的免疫T细胞动力学模型研究[J].电子学报,2008,36(1):156-160. MO Hong-wei.Research of dynamics of immune t cells based on hybrid methods[J].Acta Electronica Sinica,2008,36(1):156-160.(in Chinese)
[21] Bartys'M,Patton R,Syfert M,et al.Introduction to the DAMADICS actuator FDI benchmark study[J].Control Engineering Practice,2006,14(6):577-596.
[22] Yin S,Ding SX,Haghani A,et al.A comparison study of basic data-driven fault diagnosis and process monitoring methods on the benchmark tennessee eastman process[J].Journal of Process Control,2012,22(9):1567-1581.

基于数值微分的树突状细胞故障检测方法

Dendritic Cell Fault Detection Method Based on Numerical Differentiation

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	戴强, 戴紫彬, 李伟. 基于冗余有限域算术的AES S盒高效故障检测方案[J]. 电子学报, 2018, 46(11): 2650-2659.
[2]	徐甫. 基于可信根的计算机终端免疫模型[J]. 电子学报, 2016, 44(3): 653-657.
[3]	黎恒, 李智. 基于高阶微分的EMD均值计算方法[J]. 电子学报, 2015, 43(6): 1073-1077.
[4]	廖勇, 代学武, 周昕. 基于特征根优化的无线网络控制系统故障检测滤波器设计[J]. 电子学报, 2015, 43(6): 1236-1240.
[5]	刘朝华, 李小花, 章兢. 精英免疫克隆选择的协同进化粒子群算法[J]. 电子学报, 2013, 41(11): 2167-2173.
[6]	朱喜华, 李颖晖, 李宁, 曹华金. 基于改进离散粒子群算法的传感器布局优化设计[J]. 电子学报, 2013, 41(10): 2104-2108.
[7]	侯彦东;文成林;陈志国. 多传感器故障检测与隔离的残差产生器设计方法研究[J]. 电子学报, 2011, 39(2): 429-434.
[8]	邱爱兵;文成林;姜斌. 一种新的多速率采样系统快速率故障检测设计方法[J]. 电子学报, 2010, 38(10): 2240-2245.
[9]	尚荣华;焦李成;马文萍;公茂果. 用于约束多目标优化的免疫记忆克隆算法[J]. 电子学报, 2009, 37(6): 1289-1294.
[10]	戚玉涛;焦李成;刘芳. 基于并行人工免疫算法的大规模TSP问题求解[J]. 电子学报, 2008, 36(8): 1552-1558.
[11]	朱大奇;陈楚瑶;颜明重. 基于CA-CMAC的快速传感器故障诊断方法[J]. 电子学报, 2008, 36(8): 1646-1650.
[12]	倪建成;李志蜀;孙继荣;周利平. 树突状细胞分化模型在人工免疫系统中的应用研究[J]. 电子学报, 2008, 36(11): 2210-2215.
[13]	杨光;刘冠军;李金国;杨国峰. 基于故障检测和可靠性约束的传感器布局优化[J]. 电子学报, 2006, 34(2): 348-351.
[14]	侯霞, 范植华, 胡刚. 基于系统级诊断理论的卫星网络故障诊断[J]. 电子学报, 2005, 33(11): 2066-2069.
[15]	吴作顺;窦文华;朱小俊. 负选择模型中初始检测器集的一个生成算法[J]. 电子学报, 2003, 31(5): 687-689.