|本期目录/Table of Contents|

[1]王静虹,李晨阳,支有冉,等.一种改进的CSCA+PCA化工过程异常检测技术[J].中国安全生产科学技术,2017,13(7):144-148.[doi:10.11731/j.issn.1673-193x.2017.07.023]
 WANG Jinghong,LI Chenyang,ZHI Youran,et al.An improved CSCA+PCA anomaly detection method of chemical process[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2017,13(7):144-148.[doi:10.11731/j.issn.1673-193x.2017.07.023]
点击复制

一种改进的CSCA+PCA化工过程异常检测技术
分享到:

《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]

卷:
13
期数:
2017年7期
页码:
144-148
栏目:
职业安全卫生管理与技术
出版日期:
2017-07-31

文章信息/Info

Title:
An improved CSCA+PCA anomaly detection method of chemical process
文章编号:
1673-193X(2017)-07-0144-05
作者:
王静虹12李晨阳12支有冉3王志荣12
(1.南京工业大学 安全科学与工程学院,江苏 南京 210009;2.江苏省危险化学品本质安全与控制技术重点实验室,江苏 南京 210009;3.南京工程学院 机械工程学院,江苏 南京 210009)
Author(s):
WANG Jinghong12 LI Chenyang12 ZHI Youran3 WANG Zhirong12
(1. College of Safety Science and Engineering, Nanjing Tech University, Nanjing Jiangsu 210009, China; 2. Jiangsu Key Laboratory of Hazardous Chemicals Safety and Control, Nanjing Jiangsu 210009, China; 3. College of Mechanical Engineering, Nanjing Institute of Technology, Nanjing Jiangsu 210009, China)
关键词:
克隆选择分类主成分分析化工过程异常检测
Keywords:
clonal selection classification principal component analysis chemical process anomaly detection
分类号:
X937
DOI:
10.11731/j.issn.1673-193x.2017.07.023
文献标志码:
A
摘要:
为了解决化工过程异常检测时因参数众多且数据庞杂而导致一些异常无法被有效检出的问题,在Brownlee的克隆选择分类算法(CSCA)基础上,通过引入主成分分析(PCA)技术,进行数据降维和数据重整,探讨了人工免疫算法在化工过程异常检测中的适用效果和技术方案,以TE过程数据作为样本进行异常检测和分类实验。结果表明,过程异常数据的规模、属性的数目对CSCA异常检测效果具有明显影响,而通过主成分分析进行数据降维之后,CSCA检测效果有所提高;进一步的数据重整之后,CSCA对过程异常分类辨识的准确率可提升到85%以上;基于CSCA+PCA的数据降维及重构之后的过程异常检测技术方案,可以获得较高的异常检测准确率,从而一定程度上为化工过程安全运行提供技术保障。
Abstract:
In the anomaly detection of chemical process, some anomalies are difficult to be effectively detected due to the multitudinous parameters and miscellaneous data. To solve this problem, based on the clonal selection classification algorithm (CSCA) developed by Brownlee, the data dimension reduction and data rectification were carried out by introducing into the principal component analysis (PCA) technology. The applicability and technical scheme of artificial immune algorithm in the anomaly detection of chemical process were discussed, and the anomaly detection and classification experiments were conducted by using the TE process data as sample. The results showed that the process anomaly data size and the number of attributes had obvious influence on the anomaly detection effect of CSCA, while the detection effect of CSCA was improved after the data dimension reduction through PCA. The accuracy of process anomaly classification and identification using CSCA was significantly promoted to above 85% through the further data rectification. Therefore, the relatively higher accuracy of anomaly detection can be achieved by the process anomaly detection technical scheme after the data dimension reduction and data rectification based on CSCA+PCA, which can provide some technical support for the safe operation of chemical process to a certain extent.

参考文献/References:

[1]González F A. A study of artificial immune systems applied to anomaly detection[M]. The University of Memphis, 2003.
[2]Morteza J, Hossein M, Kasra M, et al. A Method in Security of Wireless Sensor Network based on Optimized Artificial immune system in Multi-Agent Environments[J]. Research Journal of Recent Sciences, 2013,2(10):99-106.
[3]Venkatasubramanian V, Rengaswamy R, Kavuri S N, et al. A review of process fault detection and diagnosis: Part III: Process history based methods [J]. Computers and Chemical Engineering, 2003, 27(3): 327-346.
[4]Tian W D, Sun S L, Liu J Q. Fault diagnosis in chemical processes based on dynamic simulation[J]. Journal of System Simulation, 2007, 19(12):2831-2835.
[5]黄启明, 钱宇, 林伟璐,等. 化工过程故障诊断研究进展[J].化工自动化及仪表, 2000, 27(3):1-5. HUANG Qiming, QIAN Yu,LIN Weilu,et al. Advances of fault diagnosis for chemical process[J]. Control and Instruments in Chemical Industry, 2000, 27(3):1-5.
[6]魏巧玲, 赵劲松, 钟本和. 基于模拟疫苗的人工免疫系统在氯乙烯聚合间歇过程故障诊断中的应用[J]. 化工学报, 2015, 66(2):635-639. WEI Qiaolin, ZHAO Jinsong,ZHONG Benhe . Application of AIS based on SV for fault diagnosis of vinyl chloride polymerization batch process[J]. CIESC Journal, 2015, 66(2):635-639.
[7]戴一阳,赵劲松,陈丙珍. 化工过程混合故障诊断系统的应用[J]. 化工学报,2010,61(2):342-346. DAI Yiyang, ZHAO Jinsong ,CHEN BingZhen. Application of hybrid diagnostic system for chemical processes[J]. CIESC Journal, 2010,61(2):342-346.
[8]戴一阳, 陈宁, 赵劲松,等. 人工免疫系统在间歇化工过程故障诊断中的应用[J]. 化工学报, 2009, 60(1):172-176. DAI Yiyang,CHEN Ning,ZHAO Jinsong,et al. Application of AIS to batch chemical process fault diagnosis[J]. CIESC Journal , 2009, 60(1):172-176.
[9]陆宁云, 杨英华, 王福利. 基于迭代主成分分析的过程监测方法的研究与实现[J]. 控制与决策, 2002, 17(2):215-218. LU Ningyun, YANG Yinghua,WANG Fuli. Research and implementation of process monitoring based on iterative principal component analysis( PCA)[J]. Contr ol and Decision, 2002, 17(2):215-218.
[10]孟程程,曾九孙,李文军. 核主成分分析的高炉故障检测研究[J]. 中国计量学院学报,2012,23(4):332-337. MENG Chengcheng,ZENG Jiusun,LI Wenjun. Blast furnace fault detection based on KPCA[J]. Journal of China University of Metrology, 2012,23(4): 332-337. [
11]吴卓卓. 基于田纳西—伊斯曼过程故障检测方法研究[D]. 上海:华东交通大学, 2016.
[12]陈果. 基于一类支持向量机与主成分分析的转静碰摩故障检测技术[J]. 振动与冲击,2012,31(22):29-33,38. CHEN Guo. Rotor-stator rubbing fault testing technique based on one-class support vector machine and primary component analysis[J]. 2012,31(22):29-33,38.
[13]Brownlee J. Clonal Selection Theory & Clonalg: The Clonal Selection Classification Algorithm (CSCA)[J]. Cheminform, 2005, 36(14):341.
[14]黄黎黎. 人工免疫算法研究及其在癌症诊断中的应用[D]. 北京:北京邮电大学, 2010.
[15]齐向娟, 李士雨, 孙灵栋. ChemCAD在精馏塔动态模拟中的应用[J]. 计算机与应用化学, 2008, 25(6):752-756. QI Xiangjuan, LI Shiyu, SUN Lingdong. Applied of ChemCAD in distillation column dynamic simulation [J]. Computers and Applied Chemistry, 2008, 25(6):752-756.

相似文献/References:

[1]刘程程,杨力.PCA-SVR在煤层瓦斯含量预测中的应用[J].中国安全生产科学技术,2012,8(7):78.
 LIU Cheng cheng,YANG Li.Application of PCASVR on gas content predicting in coal seam[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2012,8(7):78.
[2]王晓丽,魏志兵,彭士涛,等.基于主成分分析法的液体管道泄漏后果综合评价模型[J].中国安全生产科学技术,2014,10(5):85.[doi:10.11731/j.issn.1673-193x.2014.05.014]
 WANG Xiaoli,WEI Zhibing,PENG Shitao,et al.Comprehensive assessment model of liquid pipeline leakage consequences based on principle component analysis[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2014,10(7):85.[doi:10.11731/j.issn.1673-193x.2014.05.014]
[3]陈建宏,郑荣凯,陈 浩.基于PCA和BP神经网络边坡稳定性分析[J].中国安全生产科学技术,2014,10(5):142.[doi:10.11731/j.issn.1673-193x.2014.05.023]
 CHEN Jianhong,ZHENG Rongkai,CHEN Hao.Analysis on slope stability based on combination of PCA and BP neural network[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2014,10(7):142.[doi:10.11731/j.issn.1673-193x.2014.05.023]
[4]宋新明,居 勇,曾 鸣,等.基于神经网络的供电企业安全文化评价研究*[J].中国安全生产科学技术,2009,5(4):55.
 SONG Xin ming,JU Yong,ZENG Ming,et al.Research on the evaluation of power supply enterprises safety culture based on neural network[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2009,5(7):55.
[5]余福茂,肖亮,袁飞.主成分分析在重大危险源风险评价中的应用研究*[J].中国安全生产科学技术,2008,4(05):42.
 YU Fu mao,XIAO Liang,YUAN Fei.Application and research of PCA on risk assessment of major hazard installation[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2008,4(7):42.
[6]陈建宏,陈浩,郑荣凯,等.基于物元分析与PCA的部队汽车分队安全评价模型[J].中国安全生产科学技术,2014,10(7):180.[doi:10.11731/j.issn.1673-193x.2014.07.032]
 CHEN Jian-hong,CHEN Hao,ZHENG Rong-kai,et al.Safety assessment model for military vehicle units based on combination of matter element analysis and PCA[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2014,10(7):180.[doi:10.11731/j.issn.1673-193x.2014.07.032]
[7]李雨成,刘天奇,陈善乐,等.煤质指标对煤尘爆炸火焰长度影响作用的主成分分析*[J].中国安全生产科学技术,2015,11(3):40.[doi:10.11731/j.issn.1673-193x.2015.03.007]
 LI Yu-cheng,LIU Tian-qi,CHEN Shan-le,et al.Principal component analysis of impact of coal quality index on flame length in coal dust explosion[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2015,11(7):40.[doi:10.11731/j.issn.1673-193x.2015.03.007]
[8]王大勇.带式输送机传动滚筒材料结构损伤检测方法的研究[J].中国安全生产科学技术,2015,11(6):158.[doi:10.11731/j.issn.1673-193x.2015.06.025]
 WANG Da-yong.Research on detection method of structural damage for transmission roller materials of belt conveyor[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2015,11(7):158.[doi:10.11731/j.issn.1673-193x.2015.06.025]
[9]温廷新,朱成伟,孔祥博.基于PCA-ELM模型的露采爆破振动对民房破坏的预测分析[J].中国安全生产科学技术,2015,11(8):119.[doi:10.11731/j.issn.1673-193x.2015.08.020]
 WEN Ting-xin,ZHU Cheng-wei,KONG Xiang-bo.Predicting analysis on damage to residential house by blasting vibration in open pit mining based on PCA-ELM model[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2015,11(7):119.[doi:10.11731/j.issn.1673-193x.2015.08.020]
[10]孙华丽,项美康,薛耀锋.超大城市公共安全风险评估、归因与防范[J].中国安全生产科学技术,2018,14(8):74.[doi:10.11731/j.issn.1673-193x.2018.08.012]
 SUN Huali,XIANG Meikang,XUE Yaofeng.Assessment, attribution and prevention of public safety risk in megacity[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2018,14(7):74.[doi:10.11731/j.issn.1673-193x.2018.08.012]

备注/Memo

备注/Memo:
国家自然科学基金项目(21406115,51606092);江苏省自然科学基金项目(BK20140950);中国博士后科学基金项目(2014M551580)
更新日期/Last Update: 2017-08-21