非线性和非高斯性共存的序批次反应处理过程故障诊断（英文）
|
摘要
序批式反应器(SBR)的处理过程的数据具有非高斯分布和高度非线性的特点,传统特征提取方法在进行特征提取时仅仅考虑信息最大化而忽略数据的簇结构信息导致数据特征提取的不完整.由于多向核熵成分分析是一种新的监测方法,在监测过程中的应用表明能够克服传统监测方法的缺陷,减少误报警率.因此本文结合多向核熵成分分析的的优势,提出多向核熵独立成分分析方法用于SBR过程监测及故障诊断.首先,将三维SBR过程数据利用一种新的数据展开技术变为二维数据;其次,利用核熵成分分析将展开后的二维数据映射到高维空间用独立成分分析进行独立成分提取;最后提出一种基于多向核熵独立成分分析的故障诊断方法进行故障诊断.将该方法和传统方法应用于80升的SBR处理过程的监测结果表明,本文提出的方法优于传统的多向独立成分分析方法.
The data of sequencing batch reactor(SBR) has characteristics of non-Gaussian distribution and high nonlinearity, In order to solve the problem that SBR process monitoring algorithm can only maximize the use of data information and ignore the information in the structure of data cluster, a new multi-way kernel entropy component analysis(MKECA) method is proposed. It also address the shortcomings of the traditional monitoring method in omission failure rate. A novel contribution analysis scheme named bar plot is developed for MKEICA to diagnose faults. The proposed MKEICA method consist of three steps: 1) the three-dimensional data of SBR is unfolded into two-dimensional by a new data expanding method. 2) kernel entropy principal component analysis(KEPCA) is adopted to map the two-dimensional data into a high dimensional feature space and use independent component analysis(ICA) to extract independent components(ICs) in feature space. 3) in the stage of online monitoring,bar plot is used to identify the variables causing the fault. This method is successfully applied to an 80 L lab-scale SBR, and the experimental results demonstrate that, comparing with traditional MKICA, the proposed MKEICA method exhibits better performance in fault detection and diagnose.
The data of sequencing batch reactor(SBR) has characteristics of non-Gaussian distribution and high nonlinearity, In order to solve the problem that SBR process monitoring algorithm can only maximize the use of data information and ignore the information in the structure of data cluster, a new multi-way kernel entropy component analysis(MKECA) method is proposed. It also address the shortcomings of the traditional monitoring method in omission failure rate. A novel contribution analysis scheme named bar plot is developed for MKEICA to diagnose faults. The proposed MKEICA method consist of three steps: 1) the three-dimensional data of SBR is unfolded into two-dimensional by a new data expanding method. 2) kernel entropy principal component analysis(KEPCA) is adopted to map the two-dimensional data into a high dimensional feature space and use independent component analysis(ICA) to extract independent components(ICs) in feature space. 3) in the stage of online monitoring,bar plot is used to identify the variables causing the fault. This method is successfully applied to an 80 L lab-scale SBR, and the experimental results demonstrate that, comparing with traditional MKICA, the proposed MKEICA method exhibits better performance in fault detection and diagnose.
引文
[1] MARSILI-LIBELLI S, SPAGNI A, SUSINI R. Intelligent monitoring system for long-term control of sequencing batch reactors. Water Science and Technology, 2008, 57(3):431–436.
[2] KYOO Y C, INBEUM L, VANROLLEGHEM A. Multivariate nonlinear statistical process control of a sequencing batch reactor. Journal of Chemical Engineering of Japan, 2006, 39(1):43–51.
[3] LEE J M, QIN S J, LEE I B. Fault detection of nonlinear processes using kernel independent component analysis. The Canadian Journal of Chemical Engineering, 2007, 85(4):526–536.
[4] GE Z, SONG Z, GAO F. Review of recent research on data-based process monitoring. Industrial and Engineering Chemistry Research,2013, 52(10):3543–3562.
[5] VENKATASUBRAMANIAN V, RENGASWAMY R, KAVURI S N.A review of process fault detection and diagnosis, Part II:quanlitative models and search strategies. Computers and Chemical Engineering,2003, 27(3):327–346.
[6] KYOO Y C, INBEUM L, VANROLLEGHEM A. Multivariate nonlinear statistical process control of a sequencing batch reactor. Journal of Chemical Engineering of Japan, 2006, 39(1):43–51.
[7] YAO Y, GAO F. A survey on multistage/multiphase statistical modeling methods for batch processes. Annual Reviews in Control, 2009,33(2):172–183.
[8] KYOO Y C, INBEUM L, VANROLLEGHEM A. Multivariate nonlinear statistical process control of a sequencing batch reactor. Journal of Chemical Engineering of Japan, 2006, 39(1):43–51.
[9] GUO J Y, YUAN W Q. Palmprint recognition based on kernel principal component analysis and fisher linear discriminant. Journal of Optoelectronics Laser, 2008, 23(2):354–358.
[10] RASHID M M, YU J. Hidden markov model based adaptive independent component analysis approach for complex chemical process monitoring and fault detection. Industrial and Engineering Chemistry Research, 2012, 51(15):5506–5514.
[11] GUO J Y, YUAN W Q. Palmprint recognition based on kernel principal component analysis and fisher linear discriminant. Journal of Optoelectronics Laser, 2008, 23(2):354–358.
[12] NOMIKOS P, MACGREGOR J F. Monitoring batch processes using multiway principal component analysis. Aiche Journal, 1994, 40(8):1361–1375.
[13] KOURTI T, MACGREGOR J F. Process analysis, monitoring and diagnosis, using multivariate projection methods. Chemometrics and Intelligent Laboratory Systems, 1995, 28(1):3–21.
[14] LEE J M, YOO C K, SANG W C, et al. Nonlinear process monitoring using kernel principal component analysis. Chemical Engineering Science, 2004, 59(1):223–234.
[15] JIA M, XU H, LIU X, et al. The optimization of the kind and parameters of kernel function in KPCA for process monitoring. Computers and Chemical Engineering, 2012, 46(22):94–104.
[16] CHANG K Y, LEE J M, VANROLLEGHEM P A, et al. On-line monitoring of batch processes using multiway independent component analysis. Chemometrics and Intelligent Laboratory Systems, 2004,71(2):151–163.
[17] WANG J, ZHANG Y, CAO H, et al. Dimension reduction method of independent component analysis for process monitoring based on minimum mean square error. Journal of Process Control, 2012, 22(2):477–487.
[18] TIAN X, ZHANG X, DENG X, et al. Multiway kernel independent component analysis based on feature samples for batch process monitoring. Neurocomputing, 2009, 72(7/8/9):1584–1596.
[19] FAN J, WANG Y. Fault detection and diagnosis of non-linear nonGaussian dynamic processes using kernel dynamic independent component analysis. Information Sciences, 2014, 259(3):369–379.
[20] ZHANG Y, AN J, ZHANG H. Monitoring of time-varying processes using kernel independent component analysis. Chemical Engineering Science, 2013, 88(2):23–32.
[21] CAI L F, TIAN X M, ZHANG N. A kernel time structure independent component analysis method for nonlinear process monitoring. Chinese Journal of Chemical Engineering, 2014, 22(11/12):1243–1253.
[22] CAI L F, TIAN X M, ZHANG N. A kernel time structure independent component analysis method for nonlinear process monitoring. Chinese Journal of Chemical Engineering, 2014, 22(11/12):1243–1253.
[23] FAN J, QIN S J, WANG Y. Online monitoring of nonlinear multivariate industrial processes using filtering KICA–PCA. Chinese Control Engineering Practice, 2014, 22(1):205–216.
[24] ZHAO C, GAO F, WANG F. Nonlinear batch process monitoring using phase-based kernel-independent component analysis–principal component analysis(KICA–PCA). Industrial and Engineering Chemistry Research, 2009, 48(20):9163–9174.
[25] JENSSEN R. Kernel entropy component analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(5):847–860.
[26] GOMEZ-CHOVA L, JENSSEN R, CAMPS-VALLS G. Kernel entropy component analysis for remote sensing image clustering. IEEE Geoscience and Remote Sensing Letters, 2012, 9(2):312–316.
[27] CHANG P, QIAO J F, WANG P, et al. Monitoring non-Gaussian and non-linear batch process based on multi-way kernel entropy component analysis. Journal of Chemical Industry, 2018, 69(3):1200–1206.
[28] ZHANG H, QI Y, WANG L, et al. Fault detection and diagnosis of chemical process using enhanced KECA. Chemometrics and Intelligent Laboratory Systems, 2017, 161(2):61–69.
[29] CHANG P, WANG P, GAO X J. Microbial pharmaceutical process monitoring based on projection kernel entropy component. Information and Control, 2014, 43(4):490–494.
[30] CHANG P, WANG P, GAO X J. Research on microbial fermentation process monitoring based on higher order cumulant statistics. Control and Decision, 2017, 32(12):2273–2278.
[2] KYOO Y C, INBEUM L, VANROLLEGHEM A. Multivariate nonlinear statistical process control of a sequencing batch reactor. Journal of Chemical Engineering of Japan, 2006, 39(1):43–51.
[3] LEE J M, QIN S J, LEE I B. Fault detection of nonlinear processes using kernel independent component analysis. The Canadian Journal of Chemical Engineering, 2007, 85(4):526–536.
[4] GE Z, SONG Z, GAO F. Review of recent research on data-based process monitoring. Industrial and Engineering Chemistry Research,2013, 52(10):3543–3562.
[5] VENKATASUBRAMANIAN V, RENGASWAMY R, KAVURI S N.A review of process fault detection and diagnosis, Part II:quanlitative models and search strategies. Computers and Chemical Engineering,2003, 27(3):327–346.
[6] KYOO Y C, INBEUM L, VANROLLEGHEM A. Multivariate nonlinear statistical process control of a sequencing batch reactor. Journal of Chemical Engineering of Japan, 2006, 39(1):43–51.
[7] YAO Y, GAO F. A survey on multistage/multiphase statistical modeling methods for batch processes. Annual Reviews in Control, 2009,33(2):172–183.
[8] KYOO Y C, INBEUM L, VANROLLEGHEM A. Multivariate nonlinear statistical process control of a sequencing batch reactor. Journal of Chemical Engineering of Japan, 2006, 39(1):43–51.
[9] GUO J Y, YUAN W Q. Palmprint recognition based on kernel principal component analysis and fisher linear discriminant. Journal of Optoelectronics Laser, 2008, 23(2):354–358.
[10] RASHID M M, YU J. Hidden markov model based adaptive independent component analysis approach for complex chemical process monitoring and fault detection. Industrial and Engineering Chemistry Research, 2012, 51(15):5506–5514.
[11] GUO J Y, YUAN W Q. Palmprint recognition based on kernel principal component analysis and fisher linear discriminant. Journal of Optoelectronics Laser, 2008, 23(2):354–358.
[12] NOMIKOS P, MACGREGOR J F. Monitoring batch processes using multiway principal component analysis. Aiche Journal, 1994, 40(8):1361–1375.
[13] KOURTI T, MACGREGOR J F. Process analysis, monitoring and diagnosis, using multivariate projection methods. Chemometrics and Intelligent Laboratory Systems, 1995, 28(1):3–21.
[14] LEE J M, YOO C K, SANG W C, et al. Nonlinear process monitoring using kernel principal component analysis. Chemical Engineering Science, 2004, 59(1):223–234.
[15] JIA M, XU H, LIU X, et al. The optimization of the kind and parameters of kernel function in KPCA for process monitoring. Computers and Chemical Engineering, 2012, 46(22):94–104.
[16] CHANG K Y, LEE J M, VANROLLEGHEM P A, et al. On-line monitoring of batch processes using multiway independent component analysis. Chemometrics and Intelligent Laboratory Systems, 2004,71(2):151–163.
[17] WANG J, ZHANG Y, CAO H, et al. Dimension reduction method of independent component analysis for process monitoring based on minimum mean square error. Journal of Process Control, 2012, 22(2):477–487.
[18] TIAN X, ZHANG X, DENG X, et al. Multiway kernel independent component analysis based on feature samples for batch process monitoring. Neurocomputing, 2009, 72(7/8/9):1584–1596.
[19] FAN J, WANG Y. Fault detection and diagnosis of non-linear nonGaussian dynamic processes using kernel dynamic independent component analysis. Information Sciences, 2014, 259(3):369–379.
[20] ZHANG Y, AN J, ZHANG H. Monitoring of time-varying processes using kernel independent component analysis. Chemical Engineering Science, 2013, 88(2):23–32.
[21] CAI L F, TIAN X M, ZHANG N. A kernel time structure independent component analysis method for nonlinear process monitoring. Chinese Journal of Chemical Engineering, 2014, 22(11/12):1243–1253.
[22] CAI L F, TIAN X M, ZHANG N. A kernel time structure independent component analysis method for nonlinear process monitoring. Chinese Journal of Chemical Engineering, 2014, 22(11/12):1243–1253.
[23] FAN J, QIN S J, WANG Y. Online monitoring of nonlinear multivariate industrial processes using filtering KICA–PCA. Chinese Control Engineering Practice, 2014, 22(1):205–216.
[24] ZHAO C, GAO F, WANG F. Nonlinear batch process monitoring using phase-based kernel-independent component analysis–principal component analysis(KICA–PCA). Industrial and Engineering Chemistry Research, 2009, 48(20):9163–9174.
[25] JENSSEN R. Kernel entropy component analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(5):847–860.
[26] GOMEZ-CHOVA L, JENSSEN R, CAMPS-VALLS G. Kernel entropy component analysis for remote sensing image clustering. IEEE Geoscience and Remote Sensing Letters, 2012, 9(2):312–316.
[27] CHANG P, QIAO J F, WANG P, et al. Monitoring non-Gaussian and non-linear batch process based on multi-way kernel entropy component analysis. Journal of Chemical Industry, 2018, 69(3):1200–1206.
[28] ZHANG H, QI Y, WANG L, et al. Fault detection and diagnosis of chemical process using enhanced KECA. Chemometrics and Intelligent Laboratory Systems, 2017, 161(2):61–69.
[29] CHANG P, WANG P, GAO X J. Microbial pharmaceutical process monitoring based on projection kernel entropy component. Information and Control, 2014, 43(4):490–494.
[30] CHANG P, WANG P, GAO X J. Research on microbial fermentation process monitoring based on higher order cumulant statistics. Control and Decision, 2017, 32(12):2273–2278.