XIE Yanhong, SUN Chengao, LI Yuan. Fault Monitoring of Batch Process Based on Moving Window SVDD[J]. INFORMATION AND CONTROL, 2015, 44(5): 531-537. DOI: 10.13976/j.cnki.xk.2015.0531
Citation: XIE Yanhong, SUN Chengao, LI Yuan. Fault Monitoring of Batch Process Based on Moving Window SVDD[J]. INFORMATION AND CONTROL, 2015, 44(5): 531-537. DOI: 10.13976/j.cnki.xk.2015.0531

Fault Monitoring of Batch Process Based on Moving Window SVDD

More Information
  • Received Date: September 22, 2014
  • Revised Date: January 21, 2015
  • Published Date: October 19, 2015
  • Traditional support vector data description (SVDD) methods fail to guarantee real-time monitoring online in relation to dynamical characteristics of batch process data. This study proposes a moving-window-based SVDD method to monitor faults online in real-time. By selecting a moving window with an appropriate size, and gradually updating the current sub-data space, sub-models of SVDD are constructed, thereby executing fault monitoring online. The proposed method not only solves the adverse effects of non-Gaussian and nonlinearity, but also considers dynamic characteristics of batch process data and improves the timeliness and accuracy of batch processes monitoring. Finally, a numerical example and industrial cases are presented to verify effectiveness of the proposed method.
  • [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. Multiway principle component analysis monitoring and fault variable detection based on substage separation for batch processes[J]. Control Theory & Applications, 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. Microbial pharmaceutical process monitoring based on projection kernel entropy component[J]. Information and Control, 2014, 43(4):490-494.
    [3]
    Hoskuldsson A. PLS regression methods[J]. Journal of Chemometrics, 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, 1994, 40(8):1361-1375.
    [5]
    Chen J, Liu J. On-line batch process monitoring using dynamic PCA and dynamic PLS models[J]. Chemical Engineering Science, 2002, 57(1):63-75.
    [6]
    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. Data-driven based process fault detection and diagnosis technology[M]. Beijing:Science Press, 2011.
    [7]
    Qin J S. Survey on data-driven industrial process monitoring and diagnosis[J]. Annual Reviews in Control, 2012, 36(2):220-234.
    [8]
    Lee J M, Yoo C, Lee I B. Fault detection of batch processes using multiway kernel principal component analysis[J]. Computers & Chemical Engineering. 2004, 28(9):1837-1847.
    [9]
    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.
    [10]
    Lennox B, Montague G A, Hiden H G, et al. Process monitoring of an industrial fed-batch fermentation[J]. Biotechnology and Bioengineering, 2001, 74(2):125-135.
    [11]
    Ge Z Q, Song Z H. Performance-driven ensemble learning ICA model for improved non-Gaussian process monitoring[J]. Chemometrics and Intelligent Laboratory Systems, 2013, 123(15):1-8.
    [12]
    Ge Z Q, Gao F R, Song Z H. Batch Process monitoring based on support vector data description method[J]. Journal of Process Control, 2011, 21(6):949-959.
    [13]
    Ge Z Q, Song Z H. Bagging support vector data description model for batch process monitoring[J]. Journal of Process Control, 2013, 23(8):1090-1096.
    [14]
    Tax D M J, Duin R P W. Support vector domain description[J]. Pattern Recognition Letters, 1999, 20(11/12/13):1191-1199.
    [15]
    Tax D M J, Duin R P W. Support vector domain description[J]. Machine Learning, 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. Xie Y H, Geng Z C, Li Y. Research on the appliance of support vector data description method in batch process monitoring[J]. Computers and Applied Chemistry, 2013, 30(12):1401-1405.
    [17]
    Yao Y, Gao F R. Phase and transition based batch process modeling and online monitoring[J]. Journal of Process Control, 2009, 19(5):816-826.
    [18]
    熊伟丽, 肖应旺, 徐保国. 基于特征子空间的滑动窗PCA在批过程故障诊断中的应用[J]. 计算机与应用化学, 2006, 23(4):303-306. Xiong W L, Xiao Y W, Xu B G. Batch process fault diction based on characteristic subspace moving window PCA[J]. Computers and Applied Chemistry, 2006, 23(4):303-306.
    [19]
    刘世成, 王海清, 李平. 青霉素生产过程的在线统计检测与产品的质量控制[J]. 计算机与应用化学, 2006, 23(3):227-232. Liu S C, Wang H Q, Li P. On-line statistical monitoring and production quality control of penicillin cultivation process[J]. Computers and Applied Chemistry, 2006, 23(3):227-232.
    [20]
    刘毅, 王海清. Pensim仿真平台在青霉素发酵过程中的应用研究[J]. 系统仿真学报, 2006, 18(12):3524-3527. Liu Y, Wang H Q. Pensim simulator and its application in penicillin fermentation process[J]. Journal of System Simulation, 2006, 18(12):3524-3527.

Catalog

    Article views (934) PDF downloads (263) Cited by()
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return