高级检索

  • ISSN 1006-3080
  • CN 31-1691/TQ

基于T-TSNPR的动态过程质量监控

吕铮 杨健 侍洪波 谭帅

吕铮, 杨健, 侍洪波, 谭帅. 基于T-TSNPR的动态过程质量监控[J]. 华东理工大学学报(自然科学版), 2019, 45(6): 946-953. doi: 10.14135/j.cnki.1006-3080.20181114003
引用本文: 吕铮, 杨健, 侍洪波, 谭帅. 基于T-TSNPR的动态过程质量监控[J]. 华东理工大学学报(自然科学版), 2019, 45(6): 946-953. doi: 10.14135/j.cnki.1006-3080.20181114003
LYU Zheng, YANG Jian, SHI Hongbo, TAN Shuai. Dynamic Process Quality Monitoring Based on T-TSNPR[J]. Journal of East China University of Science and Technology, 2019, 45(6): 946-953. doi: 10.14135/j.cnki.1006-3080.20181114003
Citation: LYU Zheng, YANG Jian, SHI Hongbo, TAN Shuai. Dynamic Process Quality Monitoring Based on T-TSNPR[J]. Journal of East China University of Science and Technology, 2019, 45(6): 946-953. doi: 10.14135/j.cnki.1006-3080.20181114003

基于T-TSNPR的动态过程质量监控

doi: 10.14135/j.cnki.1006-3080.20181114003
基金项目: 国家自然科学基金(61703161,61673173);中央高校基本科研业务费(222201714031);中国博士后基金(2017M611472)
详细信息
    作者简介:

    吕铮:吕 铮(1992-),男,江苏泰兴人,硕士生,主要研究方向为数据驱动的故障检测。E-mail:ecust_lv@163.com

    通讯作者:

    侍洪波,E-mail:hbshi@ecust.edu.cn

  • 中图分类号: TP277

Dynamic Process Quality Monitoring Based on T-TSNPR

  • 摘要: 针对动态过程的质量监控,提出了一种全时间序列邻域保持回归(Total Time Series Neighborhood Preserving Regression,T-TSNPR)算法。首先,考虑到无关变量对构造特征空间的影响,对过程变量进行相关性分析,利用贡献度方法进行变量优化。在数据降维过程中考虑到数据间的时序相关性,T-TSNPR在一定长度的移动时间窗内进行邻域点挑选并构造目标函数,通过全投影回归提取出质量相关特征空间,并建立相应的T2统计量进行质量监控。最后,通过数值仿真和TE过程(Tennessee-Eastman process)仿真实验验证了T-TSNPR算法的有效性。

     

  • 图  1  T-TSNPR算法结构

    Figure  1.  Structure of T-TSNPR

    图  2  故障1过程监测结果

    Figure  2.  Monitoring charts of fault 1

    图  3  故障2过程监测结果

    Figure  3.  Monitoring charts of fault 2

    图  4  TE 过程故障1过程监测结果

    Figure  4.  Monitoring charts of fault 1 of TE process

    表  1  数值仿真故障检测率

    Table  1.   FDR of case study

    FaultFDR/%
    NPEDPLST-TSNPR
    01.000.600.60
    110010.60100
    21001.200.60
    下载: 导出CSV

    表  2  质量相关故障的检测率

    Table  2.   FDR of quality-related faults

    FaultFDR/%
    NPEDPLST-TSNPR
    298.5098.3896.62
    699.3799.3899.80
    897.2597.6398.00
    1037.0081.0080.88
    1298.2099.1398.90
    1394.8895.0096.87
    Average87.5395.0995.18
    下载: 导出CSV

    表  3  质量无关故障的检测率

    Table  3.   FDR of quality-unrelated faults

    FaultFDR/%
    NPEDPLST-TSNPR
    00.980.880.95
    33.251.701.63
    473.6231.253.13
    94.251.751.50
    1161.7536.884.25
    14100.0096.880.37
    153.54.386.88
    Average35.3428.222.67
    下载: 导出CSV
  • [1] GE Z, SONG Z, GAO F. Review of recent research on data-based process monitoring[J]. Industrial & Engineering Chemistry Research, 2013, 52(10): 3543-3562.
    [2] YANG J, ZHANG M, SHI H, et al. Dynamic learning on the manifold with constrained time information and its application for dynamic process monitoring[J]. Chemometrics & Intelligent Laboratory Systems, 2017, 167: 179-189.
    [3] SONG B, SHI H. Fault detection and classification using quality-supervised double-layer method[J]. IEEE Transactions on Industrial Electronics, 2018, 65(10): 8163-8172. doi: 10.1109/TIE.2018.2801804
    [4] TONG C, LAN T, SHI X. Fault detection and diagnosis of dynamic processes using weighted dynamic decentralized PCA approach[J]. Chemometrics & Intelligent Laboratory Systems, 2017, 161: 34-42.
    [5] ZHANG Y. Fault detection and diagnosis of nonlinear processes using improved kernel independent component analysis (KICA) and support vector machine (SVM)[J]. Industrial & Engineering Chemistry Research, 2008, 47(18): 6961-6971.
    [6] ZHOU L, ZHENG J, GE Z, et al. Multimode process monitoring based on switching autoregressive dynamic latent variable model[J]. IEEE Transactions on Industrial Electronics, 2018, 65(10): 8184-8194. doi: 10.1109/TIE.2018.2803727
    [7] YANG J, LYU Z, SHI H, et al. Performance monitoring method based on balanced partial least square and statistics pattern analysis[J]. ISA Transactions, 2018, 81: 121-131. doi: 10.1016/j.isatra.2018.07.038
    [8] ZHANG S, ZHAO C. Stationarity test and Bayesian monitoring strategy for fault detection in nonlinear multimode processes[J]. Chemometrics & Intelligent Laboratory Systems, 2017, 168: 45-61.
    [9] 丁英涛, 程辉, 王振雷, 等. IFA和FA联合方法在化工过程监控中的应用[J]. 华东理工大学学报(自然科学版), 2017, 43(5): 684-691.
    [10] 许圆圆, 杨健, 谭帅, 等. 基于局部特征的多模态过程监控方法[J]. 华东理工大学学报(自然科学版), 2017, 43(2): 260-265.
    [11] ZHOU D, LI G, QIN S J. Total projection to latent structures for process monitoring[J]. AIChE Journal, 2010, 56(1): 168-178.
    [12] DING S X, YIN S, PENG K, et al. A novel scheme for key performance indicator prediction and diagnosis with application to an industrial hot strip mill[J]. IEEE Transactions on Industrial Informatics, 2013, 9(4): 2239-2247. doi: 10.1109/TII.2012.2214394
    [13] ZHANG K, HAO H, CHEN Z, et al. A comparison and evaluation of key performance indicator-based multivariate statistics process monitoring approaches[J]. Journal of Process Control, 2015, 33(3): 112-126.
    [14] QIN S J, ZHENG Y. Quality-relevant and process-relevant fault monitoring with concurrent projection to latent structures[J]. AIChE Journal, 2013, 59(2): 496-504. doi: 10.1002/aic.v59.2
    [15] SHARDT Y A W, HAO H, DING S X. A new soft-sensor-based process monitoring scheme incorporating infrequent KPI measurements[J]. IEEE Transactions on Industrial Electronics, 2015, 62(6): 3843-3851. doi: 10.1109/TIE.2014.2364561
    [16] JIA Q, ZHANG Y. Quality-related fault detection approach based on dynamic kernel partial least squares[J]. Chemical Engineering Research & Design, 2016, 106: 242-252.
    [17] MACGREGOR J F, JAECKLE C, KIPARISSIDES C, et al. Process monitoring and diagnosis by multi-block PLS methods[J]. AIChE Journal, 1994, 40(5): 826-838. doi: 10.1002/(ISSN)1547-5905
    [18] LI G, QIN S J, ZHOU D. Geometric properties of partial least squares for process monitoring[J]. Automatica, 2010, 46(1): 204-210. doi: 10.1016/j.automatica.2009.10.030
    [19] YIN S, ZHU X, KAYNAK O. Improved pls focused on key-performance-indicator-related fault diagnosis[J]. IEEE Transactions on Industrial Electronics, 2015, 62(3): 1651-1658. doi: 10.1109/TIE.2014.2345331
    [20] PENG K, ZHANG K, DONG J, et al. Quality-relevant fault detection and diagnosis for hot strip mill process with multi-specification and multi-batch measurements[J]. Journal of the Franklin Institute, 2015, 352(3): 987-1006. doi: 10.1016/j.jfranklin.2014.12.002
    [21] WANG G, LUO H, PENG K. Quality-related fault detection using linear and nonlinear principal component regression[J]. Journal of the Franklin Institute, 2016, 353(10): 2159-2177. doi: 10.1016/j.jfranklin.2016.03.021
    [22] ZHANG S, ZHAO C. Slow feature analysis based batch process monitoring with comprehensive interpretation of operation condition deviation and dynamic anomaly[J]. IEEE Transactions on Industrial Electronics, 2018, 66(5): 3773-3783.
    [23] 杨健, 宋冰, 谭帅, 等. 时序约束NPE算法在化工过程故障检测中的应用[J]. 化工学报, 2016, 67(12): 5131-5139.
    [24] KU W, STORER R H, GEORGAKIS C. Disturbance detection and isolation by dynamic principal component analysis[J]. Chemometrics & Intelligent Laboratory Systems, 1995, 30(1): 179-196.
    [25] MIAO A, GE Z, SONG Z, et al. Time neighborhood preserving embedding model and its application for fault detection[J]. Industrial & Engineering Chemistry Research, 2013, 52(38): 13717-13729.
    [26] ODIOWEI P P, CAO Y. State-space independent component analysis for nonlinear dynamic process monitoring[J]. Chemometrics & Intelligent Laboratory Systems, 2010, 103(1): 59-65.
    [27] CHEN Q, WYNNE R J, GOULDING P, et al. The application of principal component analysis and kernel density estimation to enhance process monitoring[J]. Control Engineering Practice, 2000, 8(5): 531-543. doi: 10.1016/S0967-0661(99)00191-4
    [28] SAUL L K, ROWEIS S T. Think globally, fit locally: Unsupervised learning of low dimensional manifolds[J]. The Journal of Machine Learning Research, 2003, 4(2): 119-155.
    [29] JIAO J, YU H, WANG G. A quality-related fault detection approach based on dynamic least squares for process monitoring[J]. IEEE Transactions on Industrial Electronics, 2016, 63(4): 2625-2632.
  • 加载中
图(4) / 表(3)
计量
  • 文章访问数:  6690
  • HTML全文浏览量:  1954
  • PDF下载量:  21
  • 被引次数: 0
出版历程
  • 收稿日期:  2018-11-14
  • 网络出版日期:  2019-07-23
  • 刊出日期:  2019-12-01

目录

    /

    返回文章
    返回