基于改进的典型相关分析的故障检测方法

doi:10.6040/j.issn.1672-3961.0.2017.171

山东大学学报(工学版) ›› 2017, Vol. 47 ›› Issue (5): 44-50.doi: 10.6040/j.issn.1672-3961.0.2017.171

基于改进的典型相关分析的故障检测方法

陈志文¹, 彭涛^1*, 阳春华¹, 何章鸣²,杨超¹, 杨笑悦¹

1. 中南大学信息科学与工程学院, 湖南长沙 410083;2. 国防科学技术大学理学院, 湖南长沙 410083

收稿日期:2017-04-18 出版日期:2017-10-20 发布日期:2017-04-18
通讯作者: 彭涛(1965— ),女,湖南常德人,教授,博士,主要研究方向故障诊断与容错控制. E-mail:pandtao@csu.edu.cn E-mail:zhiwen.chen@csu.edu.cn
作者简介:陈志文(1986— ),男,湖南永州人,讲师,博士,主要研究方向为故障诊断. E-mail:zhiwen.chen@csu.edu.cn
基金资助:
国家自然科学基金资助项目(61490702);国家自然科学基金创新研究群体科学基金资助项目(61621062);中南大学创新驱动计划资助项目

A fault detection method based on modified canonical correlation analysis

CHEN Zhiwen¹, PENG Tao^1*, YANG Chunhua ¹, HE Zhangming², YANG Chao¹, YANG Xiaoyue¹

1. School of Information Science and Engineering, University of Central South, Changsha 410083, Hunan, China;
2. College of Science, National University of Defense Technology, Changsha 410083, Hunan, China

Received:2017-04-18 Online:2017-10-20 Published:2017-04-18

摘要/Abstract

摘要： 为提高基于典型相关分析的故障检测方法使用效率,对原有的残差产生方式进行改进。通过分析残差信号统计特性,重新选取残差产生方式,使得改进的残差生成方式不依赖于主元个数的选取,从而避免因主元个数选取所带来的故障检测性能影响。通过Tennessee Eastman benchmark process仿真实例,对改进方法的可行性和有效性进行验证。选取4个典型故障的运行数据,分别用所提方法进行故障检测,改进的典型相关分析方法能够有效的检测故障的发生。另外,通过对两个统计量的故障检测率的对比可以看出,两个统计量对于发生在不同子空间的故障敏感度各异,对于不同故障的检测能力不同。

Abstract: In order to improve the effectiveness of the fault detection(FD)method based on standard canonical correlation analysis(CCA), the original residual generation was modified. By analyzing the statistical characteristics of the residual signal and changing the residual generation mode, the improved residual generation method did not depend on the selection of the number of principal components, so that the fault detection performance would be free of such a selection. The proposed method was further applied to the Tennessee Eastman benchmark process, in which four typical faults were simulated. The achieved results showed that the proposed method could successfully detect the faults. Due to the different fault sensitivity of the two test statistics, it could be found that the fault detectability of the two test statistics were different.

Key words: data-driven, canonical correlation analysis, Tennessee Eastman process, fault detection

中图分类号:

TP206+.3

陈志文, 彭涛, 阳春华, 何章鸣,杨超, 杨笑悦. 基于改进的典型相关分析的故障检测方法[J]. 山东大学学报(工学版), 2017, 47(5): 44-50.

CHEN Zhiwen, PENG Tao, YANG Chunhua , HE Zhangming, YANG Chao, YANG Xiaoyue. A fault detection method based on modified canonical correlation analysis[J]. JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE), 2017, 47(5): 44-50.

参考文献

[1] 周东华,叶银忠. 现代故障诊断与容错控制[M].北京:清华大学出版社,2000.
[2] GERTLER J. Fault detection and diagnosis in engineering systems[M]. New York: Marcel Dekker, 1998.
[3] DING S X. Model-based fault diagnosis techniques-design schemes, algorithms and tools[M]. 2^nd ed. London: Springer-Verlag, 2013,
[4] GE Zhiqiang, SONG Zhihuan, GAO Furong. Review of recent research on data-based process monitoring[J]. Industrial Engineering Chemical Research, 2013, 52(10):3543-3562.
[5] ZHANG Kai, HAO Haiyang, CHEN Zhiwen, et al. A comparison and evaluation of key performance indicator-based multivariate statistics process monitoring approaches[J]. Journal of Process Control, 2015, 33:112-126.
[6] YIN Shen, DING S X, HAGHANI A. 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, 22:1567-1581.
[7] QIN S J. Survey on data-driven industrial process monitoring and diagnosis[J]. Annual Reviews in Control, 2012, 36(2):220-234.
[8] YIN Shen, LIU Lei, HOU Jian. A multivariate statistical combination forecasting method for product quality evaluation[J]. Information Science, 2016, 355-356:229-236.
[9] YIN Shen, WANG Guang, GAO Huijun. Data-driven process monitoring based on modified orthogonal projections to latent structures[J]. IEEE Transactions on Control System Technology, 2016, 24(4):1480-1487.
[10] MAJID N A, TAYLOR M P, CHEN J J, et al. Aluminium process fault detection by multiway principal component analysis[J]. Control Engineering Practice, 2011, 19(4):367-379.
[11] THORNIHILL N F, HORCH A. Advances and new directions in plant-wide disturbance detection and diagnosis [J]. Control Engineering Practice, 2007, 15(10):1196-1206.
[12] ZHOU Donghua, LI Gang, QIN S J. Total projection to latent structure for process monitoring[J]. AIChE J, 2010,56(1):168-178.
[13] MACGREGOR J F, KOURTI T. Statistical process control of multivariate processes[J]. Control Engineering Practice, 1995, 3(3):403-414.
[14] KANO M, HASEBE S, HASHIMOTO I, et al. A new multivariate statistical process monitoring method using principal component analysis [J]. Computer Chemometrics Engineering, 2001, 25(7-8):1103-1113.
[15] ZHANG Yingwei, ZHOU Hong, QIN S J, et al. Decentralized fault diagnosis of large-scale processes using multiblock kernel partial least squares[J]. IEEE Transactions on Industrial Informatics, 2010, 6(1):3-10.
[16] DING S X. Data-driven design of fault diagnosis and fault-tolerant control systems[M]. London: Springer-Verlag, 2014.
[17] CHEN Zhiwen, ZHANG Kai, DING S X, et al. Improved canonical correlation analysis-based fault detection methods for industrial processes[J]. Journal of Process Control, 2016, 41:26-34.
[18] 彭开香, 马亮, 张凯. 复杂工业过程质量相关的故障检测与诊断技术综述[J]. 自动化学报, 2017, 43(2): 1-17. PENG Kaixiang, MA Liang, ZHANG Kai. Review of quality-related fault detection and diagnosis techniques for complex industrial processes [J]. Acta Automatica Sinica, 2017, 43(3): 349-365.
[19] CHEN Zhiwen, DING S X, ZHANG Kai, et al. Canonical correlation analysis-based fault detection methods with application to alumina evaporation process [J]. Control Engineering Practice, 2016, 46:51-58.
[20] ANDERSON T W. An introduction to multivariate statistical analysis[M]. Second edition. New York: John Wiley and Sons, LTD, 1984.
[21] DOWNS J, FOGEL E. A plant-wide industrial process control problem[J]. Computer Chemistry Engineering, 1993, 17(3):245-255.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于改进的典型相关分析的故障检测方法

A fault detection method based on modified canonical correlation analysis

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 14

多维度评价

本文评价

推荐阅读 10

[1]	安海云,周前,刘玉方,黄成,陈哲,吴秋伟. 基于拓扑门控的数据-机理混合驱动的主动配电网线损计算方法[J]. 山东大学学报 (工学版), 2025, 55(5): 51-61.
[2]	贾轩,许吉凯,任艺婧,刘德才,许强,张利. 基于样本扩容和数据驱动的台区理论线损计算方法[J]. 山东大学学报 (工学版), 2025, 55(3): 158-164.
[3]	闵海根,雷小平,李杰,童星,吴霞,方煜坤. 基于双层混合集成的自动驾驶汽车故障检测[J]. 山东大学学报 (工学版), 2022, 52(6): 30-40.
[4]	王智伟,徐海超,郭相阳,马炯,褚云龙,陈前昌,卢治. 基于卷积神经网络和层次分析的新能源电源调频能力智能预测方法[J]. 山东大学学报 (工学版), 2022, 52(5): 70-76.
[5]	刘鸿斌,宋留. 废水处理过程的典型相关分析建模方法研究[J]. 山东大学学报 (工学版), 2020, 50(1): 101-108.
[6]	朱晓强,钟麦英. 基于强跟踪H_-/H_∞优化的无人机系统故障检测[J]. 山东大学学报 (工学版), 2019, 49(1): 66-74.
[7]	李广丽,刘斌,朱涛,殷依,张红斌. 基于优选典型相关分量的跨媒体检索模型[J]. 山东大学学报 (工学版), 2018, 48(5): 38-46.
[8]	赵煊,钟麦英,郭丁飞. 基于等价空间的无人机飞行控制系统故障检测[J]. 山东大学学报(工学版), 2017, 47(5): 150-156.
[9]	陈杰,钟麦英,张利刚. 基于L2范数最小估计的无人机飞控系统故障检测[J]. 山东大学学报(工学版), 2017, 47(5): 89-95.
[10]	张米露,王天真,汤天浩,辛斌. 一种模式关联主元分析的海流机故障检测方法[J]. 山东大学学报(工学版), 2017, 47(5): 123-129.
[11]	李洪阳,何潇. 基于SCKF方法的非线性随机动态系统故障诊断方法[J]. 山东大学学报(工学版), 2017, 47(5): 130-135.
[12]	杨瑞. 基于稀疏表示的间歇故障检测方法及仿真[J]. 山东大学学报(工学版), 2017, 47(5): 51-56.
[13]	刘洋. 乘性故障对开闭环系统故障诊断性能的影响[J]. 山东大学学报(工学版), 2017, 47(5): 38-43.
[14]	季涛,孙同景,徐丙垠,孙波 . 直流系统接地故障综合检测方法[J]. 山东大学学报(工学版), 2006, 36(1): 55-59 .