Application of Weighted Dynamic SVDD in Nonlinear Process Monitoring

doi:10.16182/j.issn1004731x.joss.201707015

Abstract

Abstract: Due to the complexity of the chemical process, the data are often characterized by dynamics and correlation between sequences. Traditional support vector data description (SVDD) methods are difficult to guarantee real-time monitoring online. A Weighted-Dynamic-SVDD (WDSVDD) method was proposed to monitor fault in real time online. The dynamic method was introduced, and the correlation between the data was considered. The weighted information was used to highlight the useful information. The model was established by using SVDD method, and the online real-time fault monitoring was realized. The method not only overcomes the adverse effect of non-Gaussian and nonlinearity, but also considers dynamic characteristics and correlation between sequences of the processing data. Applications in the numerical simulation and TE process instance verify the effectiveness of the proposed method.

Key words: faulty monitoring, dynamic, SVDD (support vector data description), chemical process

CLC Number:

TP277

Xie Yanhong, Sun Chengao, Li Yuan. Application of Weighted Dynamic SVDD in Nonlinear Process Monitoring[J]. Journal of System Simulation, 2017, 29(7): 1506-1513.

References

[1] 王姝, 常玉清, 王福利, 等. 时段划分的多向主元分析间歇过程监测及故障变量追溯[J]. 控制理论与应用, 2011, 28(2): 149-156.
(Wang S, Chang Y Q, Wang F L, et al.Time division multi-way principal component analysis of batch process monitoring and fault variable traces[J]. Control Theory and Application, 2011, 28(2): 149-156.)
[2] 常鹏, 王普, 高学金. 基于核熵投影技术的微生物制药生产过程监测[J]. 信息与控制, 2014, 43(4): 490-494.
(Chang P, Wang P, Gao X J.Based on the technology of nuclear entropy projection microbial pharmaceutical production process monitoring[J]. Information and Control, 2014, 43(4): 490-494.)
[3] Hoskuldsson A.PLS regression methods[J]. J. Chemometrics (S0886-9383), 1988, 2(3): 211-228.
[4] Nomikos P, Macgregor J F.Monitoring batch processes using multiway principal component analysis[J]. American Institute of Chemical Engineers Journal (S0096-7408), 1994, 40(8): 1361-1375.
[5] 周东华, 李钢, 李元. 数据驱动的工业过程故障检测与诊断技术 [M]. 北京: 科学出版社, 2011.
(Zhou D H, Li G, Li Y.A data-driven industrial process fault detection and diagnosis technology [M]. Beijing, China: Science Press, 2011.)
[6] Chen J, Liu J.On-line batch process monitoring using dynamic PCA and dynamic PLS models[J]. Chemical Engineering Science (S0009-2509), 2002, 57(1): 63-75.
[7] Choi S W, Lee I B.Nonlinear dynamic process monitoring based on dynamic kernel PCA[J]. Chemical Engineering Science (S0009-2509), 2004, 59(24): 5897-5908.
[8] Qin J S.Survey on data-driven industrial process monitoring and diagnosis[J]. Annual Reviews in Control (S1367-5788), 2012, 36(2): 220-234.
[9] Lee J M, Yoo C, Lee I B.Fault detection of batch processes using multiway kernel principal component analysis[J]. Comput Chem Eng (S0098-1354), 2004, 28(9): 1837-1847.
[10] 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.Based on statistical modeling of batch processes during online monitoring and quality prediction[J]. Acta Automatica Sinica, 2010, 36(3): 366-374.)
[11] Lennox B, Montague G A, Hiden H G, et al.Process monitoring of an industrial fed-batch fermentation[J]. Biotechnology and Bioengineering (S0006-3592), 2001, 74(2): 125-135.
[12] Ge Z Q, song Z H. Performance-driven ensemble learning ICA model for improved non-Gaussian process monitoring[J]. Chemometrics and Intelligent Laboratory Systems (S0169-7439), 2013, 123(15): 1-8.
[13] Ge Z Q, Gao F R, Song Z H.Batch Process monitoring based on support vector data description method[J]. Journal of Process Control (S0959-1524), 2011, 21(6): 949-959.
[14] Tax D M J, Duin R P W. Support vector domain description[J]. Pattern Recognition Letters (S0167-8655), 1999, 20(11/13): 1191-1199.
[15] Tax D M J, Duin R P W. Support vector domain description[J]. Machine Learning (S0885-6125), 2004, 54(1): 45-66.
[16] 谢彦红, 耿志成, 李元. SVDD在间歇过程监测中的应用研究[J]. 计算机与应用化学, 2013, 30(12): 1401-1405.
(Xei Y H, Geng Z C, Li Y.SVDD application in batch process monitoring research[J]. Computer and Applied Chemistry, 2013, 30(12): 1401-1405.)
[17] 谢彦红, 孙呈敖, 李元. 基于滑动窗口SVDD的间歇过程故障监测[J]. 信息与控制, 2015, 44(5): 531-537.
(Xie Y H, Sun C A, Li Y.Based on sliding window SVDD fault monitoring of batch process[J]. Information and Control, 2015, 44(5): 531-537.)
[18] 罗刚, 张湜, 牛彦杰. 基于TE过程的仿真系统的实现[J]. 南京工业大学学报(自然科学版), 2005, 27(3): 77-80.
(Luo G, Zhang D, Niu Y J.The realization of the simulation system based on TE process[J]. Journal of Nanjing University of Technology (Natural Science Edition), 2005, 27(3): 77-80.)