[1] Lu Chunhong, Gu Xiaofeng,. Quality prediction of batch process using the global-localdiscriminant analysis based Gaussian process regression model [J]. Journal of Southeast University (English Edition), 2015, 31 (1): 80-86. [doi:10.3969/j.issn.1003-7985.2015.01.014]

Copy

Quality prediction of batch process using the global-localdiscriminant analysis based Gaussian process regression model()

基于全局局部鉴别分析的高斯回归模型的间歇过程质量预测

Share：

Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]

Volumn:

31

Issue:

2015 1

Page:

80-86

Research Field:

Automation

Publishing date:

2015-03-30

Info

Title:

Quality prediction of batch process using the global-localdiscriminant analysis based Gaussian process regression model

基于全局局部鉴别分析的高斯回归模型的间歇过程质量预测

Author(s):

Lu Chunhong;  Gu Xiaofeng

Key Laboratory of Advanced Process Control for Light Industry of Ministry of Education, Jiangnan University, Wuxi 214122, China

卢春红;  顾晓峰

江南大学轻工过程先进控制教育部重点实验室, 无锡214122

Keywords:

quality prediction;  global-local discriminant analysis;  Gaussian process regression;  hidden Markov model;  soft sensor

质量预测;  全局局部鉴别分析;  高斯过程回归;  隐马尔科夫模型;  软测量

PACS:

TP273

DOI:

10.3969/j.issn.1003-7985.2015.01.014

Abstract:

The conventional single model strategy may be ill-suited due to the multiplicity of operation phases and system uncertainty. A novel global-local discriminant analysis(GLDA)based Gaussian process regression(GPR)approach is developed for the quality prediction of nonlinear and multiphase batch processes. After the collected data is preprocessed through batchwise unfolding, the hidden Markov model(HMM)is applied to identify different operation phases. A GLDA algorithm is also presented to extract the appropriate process variables highly correlated with the quality variables, decreasing the complexity of modeling. Besides, the multiple local GPR models are built in the reduced-dimensional space for all the identified operation phases. Furthermore, the HMM-based state estimation is used to classify each measurement sample of a test batch into a corresponding phase with the maximal likelihood estimation. Therefore, the local GPR model with respect to specific phase is selected for online prediction. The effectiveness of the proposed prediction approach is demonstrated through the multiphase penicillin fermentation process. The comparison results show that the proposed GLDA-GPR approach is superior to the regular GPR model and the GPR based on HMM(HMM-GPR)model.

由于过程操作阶段的复杂性及系统的不确定性使得传统的单模态模型策略为病态, 因此提出了一种全局局部鉴别分析(GLDA)的高斯过程回归(GPR)方法用于非线性多阶段暂态过程的质量预测.首先, 将采集数据按批次方向展开, 并采用隐马尔科夫模型(HMM)识别不同的操作阶段.其次, 利用GLDA算法提取与质量变量高度相关的过程变量, 降低建模的复杂度.在该降维后的子空间, 为所有识别出的操作阶段建立多个局部GPR模型.利用HMM状态估计将测试批次的每个测量样本以最大似然估计的方式划分到对应的阶段中.最后, 选出与具体阶段相对应的局部GPR模型进行在线预测.利用多阶段的青霉素发酵过程验证了所提预测方法的有效性.结果表明, 与常规的GPR模型及基于HMM的GPR模型相比, 提出的GLDA-GPR方法更具优势.

References:

[1] Kadlec P, Gabrys B, Strandt S. Data driven soft sensor in the process industry [J]. Computers and Chemical Engineering, 2009, 33(4): 795-814.
[2] Lin B, Recke J, Knudsen K H, et al. A systematic approach for soft sensor development [J]. Computers and Chemical Engineering, 2007, 31(5): 419-425.
[3] Sliškovic D, Grbic R, Nyarko E K. Data preprocessing in data based process modeling [C]//Proc of the IFAC International Conference on Intelligent Control Systems and Signal Processing. Istanbul, Turkey, 2009: 559-565.
[4] Chen J H, Hsu T-Y, Chen C-C, et al. Online predictive monitoring using dynamic imaging of furnaces with the combinational method of multiway principal component analysis and hidden Markov model [J]. Industrial & Engineering Chemistry Research, 2011, 50(5): 2946-2958.
[5] Viterbi A J. Error bounds for convolutional codes and an asymptotically optimum decoding algorithm [J]. IEEE Transactions on Information Theory, 1976, 13(2): 260-269.
[6] Grbic R, Sliškovic D, Kadlec P. Adaptive soft sensor for online prediction and process monitoring based on a mixture of Gaussian process models [J]. Computers and Chemical Engineering, 2013, 58:84-97.
[7] Rasmussen C E, Williams C K I. Gaussian processes in machine learning [M]. Cambridge, MA, USA: The MIT Press, 2006.
[8] Kwak N. Kernel discriminant analysis for regression problems [J]. Pattern Recognition, 2012, 45(5): 2019-2031.
[9] Kwak N, Lee J W. Feature extraction based on subspace methods for regression problems [J]. Neurocomputers, 2010, 73(10/11/12):1740-1751.
[10] Birol G, Undey C, Cinar A. A modular simulation package for fed-batch fermentation: penicillin production [J]. Computers and Chemical Engineering, 2002, 26(11): 1553-1565.
[11] Alford J S. Bioprocess control: advances and challenges [J]. Computers and Chemical Engineering, 2006, 30(10/11/12):1464-1475.

Memo

Memo:

Biographies: Lu Chunhong(1982—), female, graduate; Gu Xiaofeng(corresponding author), male, doctor, professor, xgu@jiangnan.edu.cn.
Foundation items: The Fundamental Research Funds for the Central Universities(No.JUDCF12027, JUSRP51323B), the Scientific Innovation Research of College Graduates in Jiangsu Province(No.CXLX12_0734).
Citation: Lu Chunhong, Gu Xiaofeng. Quality prediction of batch process using the global-local discriminant analysis based Gaussian process regression model[J].Journal of Southeast University(English Edition), 2015, 31(1):80-86.[doi:10.3969/j.issn.1003-7985.2015.01.014]

Common functions