Chemical Process Monitoring Based on DNPE-SVDD

doi:10.16182/j.issn1004731x.joss.201801023

Abstract

Abstract: Chemical processes test dataset are high dimensional, and have the combined feature of nonlinear and dynamic characteristics. However, traditional linear dimension reduction algorithm cannot extract the local structure information and dynamic characteristics. The monitoring model of chemical process based on dynamic neighborhood preserving embedding-support vector data description (DNPE-SVDD) algorithm is proposed. With the superiority of NPE in nonlinear dimensionality reduction and SVDD in the detection of outliers, dimension is reduced by DNPE algorithm and the monitoring model of the manifold space with reduced dimension is established by SVDD algorithm. The Tennessee Eastman (TE) process is simulated using the proposed model. Compared with DPCA and DNPE algorithms, the simulation results show that the DNPE-SVDD has a higher accuracy of fault detection.

Key words: neighborhood preserving embedding, support vector data description, dimensionality reduction, process monitoring

CLC Number:

TP277

Han Xiaochun, Bo Cuimei, Yi Hui. Chemical Process Monitoring Based on DNPE-SVDD[J]. Journal of System Simulation, 2018, 30(1): 184-190.

References

[1] 宋冰, 马玉鑫, 方永锋, 等. 基于LSNPE算法的化工过程故障检测[J]. 化工学报, 2014, 65(2): 620-627.Song Bing, Ma Yuxin, Fang Yongfeng, et al.Fault detection for chemical process based on LSNPE method[J]. Journal of Chemical Industry and Engineering (China), 2014, 65(2): 620-627.
[2] 王健, 冯健, 韩志艳. 基于流形学习的局部保持PCA 算法在故障检测中的应用[J]. 控制与决策, 2013, 28(5): 683-687.Wang Jian, Feng Jian, Han Zhiyan.Locally preserving PCA method based on manifold learning and its application in fault detection[J]. Control and Decision, 2013, 28(5): 683-687.
[3] 张沐光, 宋执环. 一种基于独立元贡献度的子空间故障检测方法[J]. 控制理论与应用, 2010, 27(3): 296-302.Zhang Muguang, Song Zhihuan.Subspace fault detection method based on independent component contribution[J]. Control Theory & Applications, 2010, 27(3): 296-302.
[4] Miao Aimin, Ge Zhiqiang, Song Zhihuan, et al.Time Neighborhood preserving embedding model and Its application for fault detection[J]. Industrial and Engineering Chemistry Research(S0888-5885), 2013, 52(38): 13717-13729.
[5] 陈新忠, 胡汇涓, 王雪松. 基于加权近邻保持嵌入的高光谱数据降维方法[J]. 中国矿业大学学报, 2013, 42(6): 1066-1072.Chen Xinzhong, Hu Huijuan, Wang Xuesong.Dimensionality reduction for hyperspectral data using weighted neighborhood preserving embedding[J]. Journal of China University of Mining & Technology, 2013, 42(6): 1066-1072.
[6] Kenneth S McClure, R Bhushan Gopaluni, Terrance Chmelyk, et al. Nonlinear process monitoring using supervised locally linear embedding projection[J]. Industrial and Engineering Chemistry Research (S0888-5885), 2013, 53(13): 5205-5216.
[7] Gui Jie, Sun Zhenan.Discriminant sparse neighborhood preserving embedding for face recognition[J]. Pattern Recognition (S0031-3203), 2012, 45(2): 2884-2893.
[8] 张少捷, 王振雷, 钱峰. 基于LTSA的FS-SVDD方法及其在化工过程监控中的应用[J]. 化工学报, 2010, 61(8): 1894-1900.Zhang Shaojie, Wang Zhenlei, Qian Feng.FS-SVDD based on LTSA and its application to chemical process monitoring[J]. Journal of Chemical Industry and Engineering, 2010, 61(8): 1894-1900.
[9] Olga Kouropteva, Oleg Okun, Matti Pietikainen.Incremental Locally Linear Embedding[J]. Pattern Recognition (S0031-3203), 2005, 38(10): 1764-1767.
[10] 祝志博, 王培良, 宋执环. 基于PCA-SVDD 的故障检测和自学习辨识[J]. 浙江大学学报, 2010, 44(4): 652-658.Zhu Zhibo, Wang Peiliang, Song Zhihuan.PCA-SVDD based fault detection and self-learning identification[J], Journal of ZheJiang University, 2010, 44(4): 652-658.
[11] Dong Jie, Zhang Kai, Huang Ya, et al.Adaptive total PLS based quality-relevant process monitoring with application to the Tennessee Eastman process[J]. Neurocomputing(S0925-2312), 2015, 154(22): 77-85.
[12] 张沐光, 宋执环. 一种基于DLPP的动态过程故障检测方法[J]. 华中科技大学学报, 2009, 37(1): 62-65.Zhang Muguang, Song Zhihuan.A fault detection method based on DLPP for dynamic processes[J]. Journal Huazhong University of Science and Technology (Natural Science Edition), 2009, 37(1): 62-65.
[13] Jiang Qingchao, Yan Xuefeng.Probabilistic Weighted NPE-SVDD for chemical process monitoring[J]. Control Engineering Practice (S0967-0661), 2014, 28(5): 74-89.
[14] Miao Aimin, Ge Zhiqiang, Song Zhihuan, et al.Nonlocal structure constrained neighborhood preserving embedding model and Its Application for Fault Detection[J]. Chemometrics and Intelligent Laboratory Systems(S0169-7439), 2015, 142: 184-196.
[15] Ji-Hoon Cho, Jong-Min Lee, Sang Wook Choi, et al.Fault identification for process monitoring using kernel principal component analysis[J]. Chemical Engineering Science (S0009-2509), 2005, 60(1): 279-288.
[16] Molina G D, Zumoffen D A R, Basuldo M S. Plant-wide control strategy applied to the Tennessee Eastman process at two operating points[J] Computers and Chemical Engineering(S0098-1354), 2011, 35(10): 2081-2097.