基于非负矩阵分解的多模态过程故障监测方法

doi:10.11949/j.issn.0438-1157.20151392

化工学报 ›› 2016, Vol. 67 ›› Issue (5): 1973-1981.DOI: 10.11949/j.issn.0438-1157.20151392

基于非负矩阵分解的多模态过程故障监测方法

朱红林, 王帆, 侍洪波, 谭帅

华东理工大学化工过程先进控制和优化技术教育部重点实验室, 上海 200237

收稿日期:2015-09-06 修回日期:2016-02-24 出版日期:2016-05-05 发布日期:2016-05-05
通讯作者: 侍洪波
基金资助:
国家自然科学基金项目(61374140);国家自然科学基金青年基金项目(61403072)。

Fault detection method based on non-negative matrix factorization for multimode processes

ZHU Honglin, WANG Fan, SHI Hongbo, TAN Shuai

Key Laboratory of Advanced Control and Optimization for Chemical Processes of Ministry of Education, East China University of Science and Technology, Shanghai 200237, China

Received:2015-09-06 Revised:2016-02-24 Online:2016-05-05 Published:2016-05-05
Supported by:
supported by the National Natural Science Foundation of China (61374140) and the Youth Foundation of the National Natural Science Foundation of China (61403072).

摘要/Abstract

摘要：

针对传统的多元统计故障监测方法往往需要假设测量数据服从单一高斯分布的不足,提出了一种基于非负矩阵分解(NMF)的多模态故障监测方法。首先使用标准的NMF算法对训练集数据进行聚类,将多模态数据划分到各个模态中;然后使用稀疏性正交非负矩阵分解(SONMF)算法对各模态分别建模,同时构造监控统计量进行故障监测。将提出的基于非负矩阵分解的多模态故障监测方法应用于数值例子和TE过程的仿真结果表明,该方法能够及时有效地检测出多模态过程中的故障。

关键词: 故障监测, 多模态过程, 非负矩阵分解

Abstract:

The traditional multivariate statistical fault detection methods are designed for single operating conditions and may produce erroneous conclusions if they are used for the multi-mode process monitoring. A novel multi-mode process monitoring approach based on non-negative matrix factorization (NMF) is proposed in this paper. First, the training set of data is clustered by the standard NMF algorithm and the multi-mode data are divided into each mode. Then, the sparseness orthogonal NMF (SONMF) algorithm is used to model every mode and the monitoring statistics are constructed to perform fault detection. The proposed method is applied to a numerical example and the TE process. The simulation results show that this method can effectively detect multi-mode process failure.

Key words: fault detection, multi-mode process, non-negative matrix factorization

中图分类号:

TP277

朱红林, 王帆, 侍洪波, 谭帅. 基于非负矩阵分解的多模态过程故障监测方法[J]. 化工学报, 2016, 67(5): 1973-1981.

ZHU Honglin, WANG Fan, SHI Hongbo, TAN Shuai. Fault detection method based on non-negative matrix factorization for multimode processes[J]. CIESC Journal, 2016, 67(5): 1973-1981.

参考文献 24

[1]	ZHOU D H, HU Y Y. Fault diagnosis techniques for dynamic system [J]. Acta Automation Sinica, 2009, 35 (6): 748-758.
[2]	WOLD S, ESBENSEN K, GELADI P. Principal component analysis [J]. Chemometrics & Intelligent Laboratory Systems, 1987, 2 (1/2/3): 37-52.
[3]	NOMIKOS P, MACGREGOR J F. Multi-way partial least squares in monitoring batch processes [J]. Chemometrics & Intelligent Laboratory Systems, 1995, 30 (1): 97-108.
[4]	GE Z Q, SONG Z H, GAO F R. Review of recent research on data-based process monitoring [J]. Industrial & Engineering Chemical Research, 2013, 52 (10): 3543-3562.
[5]	赵春晖, 王福利, 姚远, 等. 基于时段的间歇过程统计建模、在线监测及质量预报 [J]. 自动化学报, 2010, 36 (3): 366-374. ZHAO C H, WANG F L, YAO Y, et al. Phase-based statistical modeling, online monitoring and quality prediction for batch process [J]. Acta Automatica Sinica, 2010, 36 (3): 366-374.
[6]	GE Z Q, SONG Z H. Multimode process monitoring based on Bayesian method [J]. Journal of Chemometrics, 2009, 23 (12): 636-650.
[7]	SEBZALI Y M, WANG X Z. Knowledge discovery from process operational data using PCA and fuzzy clustering [J]. Engineering Applications of Artificial Intelligence, 2001, 14 (5): 607-616.
[8]	NG Y S, SRINIVASAN R. An adjoined multi-model approach for monitoring batch and transient operations [J]. Computers & Chemical Engineering, 2009, 33 (4): 887-902.
[9]	FEITAL T, KRUGER U, DUTRA J, et al. Modeling and performance monitoring of multivariate multimodal process [J]. AIChE Journal, 2013, 59 (5): 1557-1569.
[10]	YU J, QIN S J. Multimode process monitoring with Bayesian inference-based finite Gaussian mixture models [J]. AIChE Journal, 2008, 54 (7): 1811-1829.
[11]	YU J. Online quality prediction of nonlinear and non-Gaussian chemical processes with shifting dynamics using finite mixture model based Gaussian process regression approach [J]. Chemical Engineering Science, 2012, 82 (1): 22-30.
[12]	XIE X, SHI H B. Multimode process monitoring based on fuzzy C-means in locality preserving projection subspace [J]. Chinese Journal of Chemical Engineering, 2012, 20 (6): 1174-1179.
[13]	刘帮莉, 马玉鑫, 侍洪波. 基于局部密度估计的多模态过程故障检测 [J]. 化工学报, 2014, 65 (8): 3071-3081. LIU B L, MA Y X, SHI H B. Multimode process monitoring based on local density estimation [J]. CIESC Journal, 2014, 65 (8): 3071-3081.
[14]	SHANG F, JIAO L C, WANG F. Graph dual regularization non-negative matrix factorization for co-clustering [J]. Pattern Recognition, 2012, 45 (6): 2237-2250.
[15]	LONG X Z, LU H T, PENG Y, et al. Graph regularized discriminative non-negative matrix factorization for face recognition [J]. Multimedia Tools & Applications, 2014, 72 (3): 2679-2699.
[16]	ZENG K, YU J, LI C H, et al. Image clustering by hyper-graph regularized non-negative matrix factorization [J]. Neurocomputing, 2014, 138 (11): 209-217.
[17]	LI X B, YANG Y P, ZHANG W D. Fault detection method for non-Gaussian processes based on non-negative matrix factorization [J]. Asia-Pacific Journal of Chemical Engineering, 2013, 8 (8): 362-370.
[18]	LI X B, YaANG Y P, ZHANG W D. Statistical process monitoring via generalized non-negative matrix projection [J]. Chemometrics & Intelligent Laboratory Systems, 2013, 121 (7): 15-25.
[19]	PENG Y, CHEN X, Ye Q X, et al. Fault detection and classification in chemical processes using NMFSC and structural SVMs [J]. The Canadian Journal of Chemical Engineering, 2014, 92 (6): 1016-1023.
[20]	LEE D D, SEUNG H S. Learning the parts of objects by non-negative matrix factorization [J]. Nature, 1999, 401 (6755): 788-791.
[21]	LEE D D. Algorithms for non-negative matrix factorization//Adv. Neural Inform. Process. Syst. [C]. MIT Press, Cambridge, MA, USA, 2001, 32 (6):556-562.
[22]	GE Z Q, SONG Z H. Multimode process monitoring based on Bayesian method [J]. Journal of Chemometrics, 2009, 23 (12): 636-650.
[23]	DOWNS J J, VOGEL E F. A plant-wide industrial process control problem [J]. Computers & Chemical Engineering, 1993, 17 (3): 245-255.
[24]	YU J B. Local and global principal component analysis for process monitoring [J]. Journal of Process Control, 2012, 22 (7): 1358-1373.

基于非负矩阵分解的多模态过程故障监测方法

Fault detection method based on non-negative matrix factorization for multimode processes

PDF (PC)

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献 24

相关文章 15

编辑推荐

Metrics

本文评价

[1]	高学金, 姚玉卓, 韩华云, 齐咏生. 基于注意力动态卷积自编码器的发酵过程故障监测[J]. 化工学报, 2023, 74(6): 2503-2521.
[2]	高学金, 何紫鹤, 高慧慧, 齐咏生. 基于联合典型变量矩阵的多阶段发酵过程质量相关故障监测[J]. 化工学报, 2022, 73(3): 1300-1314.
[3]	李元, 杨东昇, 赵丽颖, 张成. 层次变分高斯混合模型与主多项式分析的故障检测策略[J]. 化工学报, 2021, 72(3): 1616-1626.
[4]	梅华, 黄彪, 钱锋. 石油馏分基础数据模型建模方法[J]. 化工学报, 2018, 69(3): 931-935.
[5]	辜小花, 张堃, 王甜, 候松, 宋鸿飞, 李太福, 邱奎. 基于CW-HCA联合指标的高含硫天然气净化过程故障监测[J]. 化工学报, 2018, 69(10): 4292-4301.
[6]	郭金玉, 袁堂明, 李元. 一种不等长的多模态间歇过程故障检测方法[J]. 化工学报, 2016, 67(7): 2916-2924.
[7]	齐咏生, 张海利, 高学金, 王普. 基于KECA的化工过程故障监测新方法[J]. 化工学报, 2016, 67(3): 1063-1069.
[8]	朱红林, 王帆, 侍洪波, 谭帅. 基于LPP-GNMF算法的化工过程故障监测方法[J]. 化工学报, 2016, 67(12): 5155-5162.
[9]	王帆, 杨雅伟, 谭帅, 侍洪波. 基于稀疏性非负矩阵分解的故障监测方法[J]. 化工学报, 2015, 66(5): 1798-1805.
[10]	衷路生, 何东, 龚锦红, 张永贤. 基于分布式ICA-PCA模型的工业过程故障监测[J]. 化工学报, 2015, 66(11): 4546-4554.
[11]	刘帮莉, 马玉鑫, 侍洪波. 基于局部密度估计的多模态过程故障检测[J]. 化工学报, 2014, 65(8): 3071-3081.
[12]	宋冰, 马玉鑫, 方永锋, 侍洪波. 基于LSNPE算法的化工过程故障检测[J]. 化工学报, 2014, 65(2): 620-627.
[13]	卢春红, 熊伟丽, 顾晓峰. 基于贝叶斯推理的PKPCAM的非线性多模态过程故障检测与诊断方法[J]. 化工学报, 2014, 65(12): 4866-4874.
[14]	张妮, 田学民, 蔡连芳. 基于RISOMAP的非线性过程故障检测方法[J]. 化工学报, 2013, 64(6): 2125-2130.
[15]	马贺贺, 胡益, 侍洪波. 基于马氏距离局部离群因子方法的复杂化工过程故障检测[J]. 化工学报, 2013, 64(5): 1674-1682.