基于子块典型变量分析的化工过程故障检测

doi:10.3969/j.issn.2095-2198.2024.01.009

摘要
参考文献
相关文章
推荐阅读
Metrics

下载:

PDF (4313KB)
输出: BibTeX | EndNote (RIS)

摘要

大型化工生产过程包含许多单元，单元内变量之间具有非常强的相关性，针对这一特点，提出一种基于子块典型变量分析（sub-block canonical variate analysis,SB-CVA）的故障检测方法.依据块内变量高度相关、块间变量相关性较小原则将过程建模数据分块，在各个块内分别建立CVA模型，计算T²和SPE统计量作为故障检测指标.该方法主要优点是能及时检测故障并定位故障发生的单元.对TE过程进行仿真，并与PLS、MB-PLS和CVA方法进行对比，结果验证了该方法的有效性.

	服务
	把本文推荐给朋友
	加入引用管理器
	E-mail Alert
	RSS
	（）
	作者相关文章

关键词:

子块')" href="#">

子块典型变量分析故障检测 TE过程

Abstract:

The large-scale chemical production process contains many units,and the variables within the units have a very strong correlation.In view of this characteristic,a fault detection method based on sub-block canonical variate analysis(SB-CVA) was proposed.Firstly,the process modeling data were divided into several sub-blocks according to the principle of high correlation of intra-block variables and low correlation of inter-block variables.Then CVA models were established within each block,T²and SPE statistics were calculated as fault detection indicators.The proposed method could detect the fault of sub-blocks in time and confirm the fault unit effectively.Simulation was carried out through TE process and compared with PLS,MB-PLS and CVA to verify the effectiveness of the proposed method.

Key words: sub-block canonical variate analysis fault detection TE process

出版日期: 2024-02-29 发布日期: 2024-09-24 整期出版日期: 2024-02-29

ZTFLH:

TP277

基金资助:

国家自然科学基金资助项目(61490701,61673279)；辽宁省教育厅重点实验室项目(LZ2015059)

通讯作者: 李元

作者简介: 郭小萍（1972—），女，山西大同人，教授，博士，主要从事基于数据驱动的复杂过程故障诊断的研究.

引用本文:

郭小萍, 赵英平, 李元.

基于子块典型变量分析的化工过程故障检测 [J]. 沈阳化工大学学报, 2024, 38(1): 61-70.
GUO Xiaoping, ZHAO Yingping, LI Yuan.

Fault Detection in Chemical Process Based on Sub-Block Canonical Variate Analysis . Journal of Shenyang University of Chemical Technology, 2024, 38(1): 61-70.

链接本文:

https://xuebao.syuct.edu.cn/CN/10.3969/j.issn.2095-2198.2024.01.009 或 https://xuebao.syuct.edu.cn/CN/Y2024/V38/I1/61

［1］徐圆,刘辛新,朱群雄.化工过程可拓PCA故障诊断方法研究与应用［J］.计算机与应用化学,2013,30(11):1324-1328.

［2］郭小萍,李克勤,李元.基于近邻距离加权主元分析的故障定位［J］.沈阳化工大学学报,2018,32(3):264-272.

［3］周东华,史建涛,何潇.动态系统间歇故障诊断技术综述［J］.自动化学报,2014,40(2):161-171.

［4］ZHANG W,JIA M P,ZHU L,et al.Comprehensive Overview on Computational Intelligence Techniques for Machinery Condition Monitoring and Fault Diagnosis［J］.Chinese Journal of Mechanical Engineering,2017,30(4):782-795.

［5］李元,黄莹莹.基于差分动态主元分析的多模态过程故障检测［J］.沈阳化工大学学报,2019,33(4):339-348.

［6］WANG J,ZHONG B,ZHOU J L.Quality-Relevant Fault Monitoring Based on Locality-Preserving Partial Least-Squares Statistical Models［J］.Industrial & Engineering Chemistry Research,2017,56(24):7009-7020.

［7］LEE C,CHOI S W,LEE I B.Variable Reconstruction and Sensor Fault Identification Using Canonical Variate Analysis［J］.Journal of Process Control,2006,16(7):747-761.

［8］JIANG Q C,YANG X F.Multimode Process Monitoring Using Variational Bayesian Inference and Canonical Correlation Analysis［J］.IEEE Transactions on Automation Science and Engineering,2019,16(4):1814-1824.

［9］SIMOGLOU A,MARTIN E B,MORRIS A J.Statistical Performance Monitoring of Dynamic Multivariate Processes Using State Space Modelling［J］.Computers & Chemical Engineering,2002,26(6):909-920.

［10］WEN Q J,GE Z Q,SONG Z H.Multimode Dynamic Process Monitoring Based on Mixture Canonical Variate Analysis Model［J］.Industrial and Engineering Chemistry Research,2015,54(5):1605-1614.

［11］LI X C,YANG Y J,BENNETT I,et al.Condition Monitoring of Rotating Machines Under Time-Varying Conditions Based on Adaptive Canonical Variate Analysis［J］.Mechanical Systems and Signal Processing,2019,131:348-363.

［12］LAN T,TONG C D,SHI X H,et al.Dynamic Statistical Process Monitoring Based on Generalized Canonical Variate Analysis［J］.Journal of the Taiwan Institute of Chemical Engineers,2020,112:78-86.

［13］LIU Q,ZHU Q Q,QIN S J,et al.Dynamic Concurrent Kernel CCA for Strip-Thickness Relevant Fault Diagnosis of Continuous Annealing Processes［J］.Journal of Process Control,2018,67:12-22.

［14］JIANG B B,HUANG D X,ZHU X X,et al.Canonical Variate Analysis-Based Contributions for Fault Identification［J］.Journal of Process Control,2015,26:17-25.

［15］季正燕,陈辉,张佳佳,等.一种基于奇异值分解的解相干算法［J］.电子与信息学报,2017,39(8):1913-1918.

［16］PREETHI R A,ANANDHARAJ G.Quantized Ternary Pattern and Singular Value Decomposition for the Efficient Mining of Sequences in SRSI Images［J］.SN Applied Sciences,2020,2(10):1697.

［17］商亮亮,刘建昌,谭树彬,等.基于递推规范变量分析的时变过程故障检测［J］.东北大学学报(自然科学版),2016,37(12):1673-1676,1682.

［18］SAMUEL R T,CAO Y.Kernel Canonical Variate Analysis for Nonlinear Dynamic Process Monitoring［J］.IFAC-Papersonline,2015,48(8):605-610.

[1]	李元1, 刘雨田1, 冯立伟1, 2. 基于时空近邻标准化和PCA的故障检测方法 [J]. 沈阳化工大学学报, 2024, 38(1): 52-60.
[2]	郭金玉, 李涛, 李元. 基于多模型SVM的多模态过程故障检测 [J]. 沈阳化工大学学报, 2023, 37(6): 533-541.
[3]	张成1, 赵丽颖2, 杨东昇2, 李元2. 基于LPP特征空间重构的故障检测策略 Fault Detection Strategy Based on the Feature Space Reconstruction of LPP [J]. 沈阳化工大学学报, 2023, 37(5): 472-471.
[4]	郭小萍, 徐月, 李元. 基于EWMA-kNN的多工况过程微小故障检测 [J]. 沈阳化工大学学报, 2021, 35(4): 358-365.
[5]	郭金玉, 刘玉超, 李元. 加权局部近邻标准化PCA的工业过程故障检测 [J]. 沈阳化工大学学报, 2021, 35(3): 265-274.
[6]	李元, 杨东昇, 李大舟. 基于二维卷积神经网络高层数据特征学习的过程故障检测[J]. 沈阳化工大学学报, 2021, 35(3): 256-264.

No Suggested Reading articles found!

Viewed

Full text

Abstract

Cited

Shared

Discussed