[1]张汉元,*,张汉营,等.基于改进核慢特征分析的间歇过程故障检测[J].山东建筑大学学报,2020,35(01):42-49.[doi:10.12077/sdjz.2020.01.007]
 ZHANG Hanyuan,*,ZHANG Hanying,et al.Batch process fault detection based on an improved kernel slow feature analysis[J].Journal of Shandong jianzhu university,2020,35(01):42-49.[doi:10.12077/sdjz.2020.01.007]
点击复制

基于改进核慢特征分析的间歇过程故障检测()
分享到:

《山东建筑大学学报》[ISSN:1673-7644/CN:37-1449/TU]

卷:
35
期数:
2020年01期
页码:
42-49
栏目:
研究论文
出版日期:
2020-02-15

文章信息/Info

Title:
Batch process fault detection based on an improved kernel slow feature analysis
文章编号:
1673-7644(2020)01-0042-08
作者:
张汉元1*张汉营1梁泽宇2
(1.山东建筑大学 信息与电气工程学院,山东 济南 250101;2.山东建筑大学 热能工程学院,山东 济南 250101)
Author(s):
ZHANG Hanyuan1* ZHANG Hanying1 LIANG Zeyu2
(1. School of Information and Electrical Engineering, Shandong Jianzhu University, Jinan 250101, China;2. School of Thermal Engineering, Shandong Jianzhu University, Jinan 250101, China)
关键词:
核慢特征分析间歇过程故障检测全局结构分析
Keywords:
kernel slow feature analysis batch process fault detection global preserving structure analysis
分类号:
TP277
DOI:
10.12077/sdjz.2020.01.007
文献标志码:
A
摘要:
将全局保持结构分析技术融入核慢特征分析中,实现基于改进核慢特征分析的间歇过程故障检测,可以有效提高对间歇过程的监控效率。文章采用两步多路数据展开策略将三维训练数据展开成两维矩阵,利用改进核慢特征分析提取间歇过程的局部动态数据,检测青霉素发酵过程中6种故障的仿真数据。结果表明:相比于传统的多路核主元分析、多路核独立元分析和核慢特征分析监控方法,基于改进核慢特征分析的监控方法具有最早的故障检测时刻,分别在第100、100、102、108、112和108个采样时刻检测到故障F1~F6;对间歇过程的6种故障具有最高的故障检测率,F1~F6的故障检测率分别为100%、100%、99%、96.67%、96.62%和97.97%;构造保留慢特征数目的准则是有效可行的。
Abstract:
To tackle the high nonlinearity and inherently time-varying dynamics of batch process, an improved KSFA (IKSFA) based fault detection approach is proposed by integrating global preserving structure analysis into KSFA model in order to improve the monitoring performance of batch process. In the proposed method, a two-step multiway data unfolding strategy is utilized to convert the three-way training dataset into a two-way matrix. The IKSFA approach is then used to explore the local dynamic data relationships as well as to mine the global structure information. A rule based on the cumulative slowness contribution is designed to determine the number of retained slow features. The case study on the six simulated faults of the fed-batch penicillin fermentation process demonstrates that compared with the traditional MKPCA, MKICA and KSFA methods, IKSFA based method gains the earliest fault detection time as well as the highest fault detection rate and that the rule of determining the number of retained slow features is proved to be effective.Faults were detected at 100, 100, 102, 108, 112 and 108 h respectively. The fault detection rates of F1-F6 are 100%, 100%, 99%, 96.67%, 96.62% and 97.97% respectively.

参考文献/References:

[1]Zhang S M, Chao C H, Gao F R.Incipient fault detection for multiphase batch processes with limited batches[J].IEEE Transactions on Control Systems Technology,2019,27(1):103-117. [2]刘世成,王海清,李平.基于多向核主元分析的青霉素生产过程在线监测[J].浙江大学学报(工学版),2007,41(2):202-207. [3]谢晓庆,王建林,赵利强,等.基于时段及过渡区域的KICA间歇过程监测方法[J].计算机与应用化学,2014,31(10):1250-1256. [4]翟坤,杜文霞,吕锋,等.一种改进的动态核主元分析故障检测方法[J].化工学报,2019,70(2):716-722. [5]齐咏生.一种基于改进MPCA的间歇过程监控与故障诊断方法[J].化工学报,2009, 60 (11):2838-2846. [6]Wang Y J, Jia M X, Mao Z Z.Weak fault monitoring method for batch process based on multi-model SDKPCA[J].Chemometrics & Intelligent Laboratory Systems,2012,118(5):1-12. [7]Shang C, Yang F, Huang B, et al. Recursive slow feature analysis for adaptive monitoring of industrial processes[J].IEEE Transactions on Industrial Electronics,2018,65(11):8895-8905. [8]彭慧来,赵帅,熊伟丽. 基于慢特征分析的高斯过程回归建模[J].控制工程,2019,26(1):120-124. [9]蒋昕祎,李绍军,金宇辉.基于慢特征重构与改进DPLS的软测量建模[J].华东理工大学学报(自然科学版),2018, 44(4):535-542. [10]Zhang S M, Zhao C H. Slow feature analysis based batch process monitoring with comprehensive interpretation of operation condition deviation and dynamic anomaly[J]. IEEE Transactions on Industrial Electronics,2018,66(5):3773-3783. [11]Gu X, Liu C, Wang S, et al. Uncorrelated slow feature discriminant analysis using globality preserving projections for feature extraction[J]. Neurocomputing,2015,168(30):488-499. [12]Huang Y P, Zhao J L, Liu Y H, et al. Nonlinear dimensionality reduction using a temporal coherence principle[J]. Information Sciences, 2011,181(16):3284-3307. [13]马萍,张宏立,范文慧.基于局部与全局结构保持算法的滚动轴承故障诊断[J].机械工程学报,2017,53(2):20-25. [14]Zhang H Y, Tian X M, Deng X G, et al. Batch process fault detection and identification based on discriminant global preserving kernel slow feature analysis[J].ISA Transactions,2018,79:108-126. [15]梁秀霞,陈娇娇,严婷,等.基于自适应动态时间规整(DTW)的GA-FCM多阶段间歇过程故障诊断[J].北京化工大学学报(自然科学版),2019,46(5):87-93.

备注/Memo

备注/Memo:
收稿日期:2020-01-12 基金项目:山东建筑大学博士科研基金项目(XNBS1821)作者简介:张汉元(1991-),男,讲师,博士,主要从事工业过程故障诊断理论与技术等方面的研究. E-mail: zhanghanyuan18@sdjzu.edu.cn[*通讯作者]
更新日期/Last Update: 2019-12-16