|本期目录/Table of Contents|

[1]刘毅.基于KPLS数据重构的非线性过程监测与故障辨识[J].中国安全生产科学技术,2015,11(12):93-98.[doi:10.11731/j.issn.1673-193x.2015.12.014]
 LIU Yi.Nonlinear process monitoring and fault detection based on data reconstruction using KPLS[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2015,11(12):93-98.[doi:10.11731/j.issn.1673-193x.2015.12.014]
点击复制

基于KPLS数据重构的非线性过程监测与故障辨识
分享到:

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

卷:
11
期数:
2015年12期
页码:
93-98
栏目:
职业安全卫生管理与技术
出版日期:
2015-12-30

文章信息/Info

Title:
Nonlinear process monitoring and fault detection based on data reconstruction using KPLS
文章编号:
1673-193X(2015)-12-0093-06
作者:
刘毅12
(1.中国安全生产科学研究院,北京 100012;(2.重大危险源监控与事故应急技术国家安全监管总局安全生产重点实验室,北京 100012)
Author(s):
LIU Yi112
(1. China Academy of Safety Science and Technology, Beijing 100012, China; 2. Key Laboratory of Major Hazard control and Accident Emergency Technology, State Administration of Work Safety, Beijing 100012, China)
关键词:
故障辨识核偏最小二乘多变量统计过程控制非线性统计过程控制
Keywords:
fault detection kernel partial least square MSPC nonlinear SPC
分类号:
X937
DOI:
10.11731/j.issn.1673-193x.2015.12.014
文献标志码:
A
摘要:
为适应快速变化的化工产品需求,过程工业逐步向柔性生产发展,使得间歇过程的应用日益广泛。这一类工艺过程具有动态和非线性的特征,过程故障带来的工艺波动和安全风险是较为突出的挑战。采用基于核函数的偏最小二乘方法,在高维特征空间提取特征变量,这些变量包含了生产过程的非线性结构特征,也反应了过程工况的模式特征。针对传统线性方法存在的故障漏报等问题,利用核函数技巧,在特征空间进行数据重构,进而计算统计监控指标SPE,并通过对SPE的在线监测实现更加有效地故障辨识。本方法针对标准非线性测试对象进行了过程监测,实现结果充分说明了方法的有效性。
Abstract:
In this paper, a new nonlinear process monitoring technique based on kernel partial least squares (KPLS) is developed. KPLS has emerged in recent years as a promising regression method for tackling nonlinear systems, such as batch processes. KPLS can effectively capture the nonlinear relationship in the process variables and is potentially suitable for monitoring nonlinear process disturbances. To resolve the fault missing problem of the traditional linear methods, a simple approach of calculating the squared prediction error (SPE) based on data reconstruction in the feature space is suggested. Based on SPE charts in the feature space, KPLS was applied to fault detection in Tennessee Eastman benchmark process. The proposed approach showed superior performance in process monitoring and quality variables prediction compared to the conventional PLS methods.

参考文献/References:

[1]张杰, 阳宪惠. 多变量统计过程控制[M], 北京: 化学工业出版社, 2000
[2]Macgregor J F, Kourti T. Statistical process control of multivariate process[J]. Control Engineering Practice, 1995, 3(3): 403-414
[3]张玉良, 张贝克, 马昕, 等. 一种新的基于图模型的间歇过程故障监测方法[J]. 中国安全生产科学技术, 2014, 10(6): 164-170 ZHANG Yu-liang, ZHANG Bei-ke, MA Xin, et al. A novel fault detection method for batch process based on digraph model [J]. Journal of Safety Science and Technology, 2014, 10(6): 164-170
[4]魏利军, 关磊, 吴宗之. 重大危险源安全监控系统运行模式分析与探讨[J]. 中国安全生产科学技术, 2006, 2(5): 37-40 WEI Li-jun, GUAN Lei, WU Zong-zhi. Probe into and analysis of running mode for major hazard installations safety monitoring system [J]. Journal of Safety Science and Technology, 2006, 2(5): 37-40
[5]Geladi P, Kowalski B R. Partial least-squares regression: a tutorial[J]. Anal. Chem. Acta, 1986, 185: 1-17
[6]Kourti T. Application of latent variable methods to process control and multivariate statistical process control in industry[J]. International Journal of Adaptive Control and Signal Processing, 2005, 19(4): 213-246
[7]Qin S J, Mcavoy T J. Nonlinear PLS Modeling Using Neural Network[J]. Computers & Chemical Engineering, 1992, 16(4): 379-391
[8]Malthouse E C, Tamhane A C, Mah R S H. Non-linear partial least squares[J]. Computer and Chemical Engineering, 1997, 21(8): 875-890
[9]Vapnik V N. 统计学习理论[M]. 北京: 电子工业出版社, 2004
[10]Scholkopf B, Smola A J. Learning with kernels - support vector machines, regularization, optimization and beyond[M]. Cambridge, MA: MIT Press 2002
[11]王桂增, 叶昊. 主元分析与偏最小二乘法[M]. 北京: 清华大学出版社, 2012
[12]Rosipal R. Kernel partial least squares for nonlinear regression and discrimination[J]. Neural Network World, 2003, 13: 291-300
[13]陈冬青, 彭勇, 王华忠. 基于核主元分析的过程控制系统欺骗攻击 [J]. 清华大学学报(自然科学版), 2013, 53(12): 1694-1698 CHEN Dong-qing, PENG Yong, WANG Hua-zhong. Deception attacks in process control systems using kernel principal component analyses[J]. J Tsinghua Univ (Sci & Technol), 2013, 53(12): 1694-1698
[14]常鹏, 王普, 高学金. 基于统计量模式分析的T-KPLS间歇过程故障监控[J]. 化工学报, 2015, 66(1): 265-271 CHANG Peng, WANG Pu, GAO Xue-jin. Fault monitoring batch process based on statistics pattern analysis of T-KPLS[J]. CIESC Journal, 2015, 66(1): 265-271
[15]Hoskuldsson A. PLS regression methods[J]. Journal of Chemometrics, 1998, 2: 211-218
[16]Rosipal R, Trejo L J. Kernel partial least squares regression in reproducing kernel Hilbert space[J]. Journal of Machine Learning Research, 2001(2): 97-123
[17]Kim K, Lee J-M, Lee I-B. A novel multivariate regression approach based on kernel partial least squares with orthogonal signal correction[J]. Chemometrics and Intelligent Laboratory Systems, 2005(79): 22-30
[18]王惠文. 偏最小二乘回归方法及其应用[M]. 北京: 国防工业出版社, 1999
[19]Wise B M, Gallagher N B. The process chemometrics approach to process monitoring and fault detection[J]. J. Process Control, 1996, 6(6): 329-348
[20]Singhal A, Seborg D E. Evaluation of a pattern matching method for the Tennessee Eastman challenge process[J]. Journal of Process Control, 2006, 16(6): 601-613

相似文献/References:

备注/Memo

备注/Memo:
国家科技支撑计划项目(2015BAK16B04)
更新日期/Last Update: 2016-01-25