Two dimensional state estimation in batch process with delayed measurements

doi:10.11949/j.issn.0438-1157.20151894

Abstract

Abstract:

This work investigates the state estimation in a batch process based on the particle filter method. Considering that the two dimensional dynamics and the key parameters are obtained online with low accuracy or offline with large time delay, a two dimensional state transition model and delayed measurement model are developed. In addition, a two dimensional state estimation algorithm is proposed by using Bayesian method and the forward-backward smoothing algorithm. The proposed algorithm improves the estimation accuracy by fusing information of previous batches and delayed measurements, and overcomes the influence of the uncertainty of offline sampling period and time delay. The applications in a numerical example and a beer fermentation show the effectiveness of the proposed method.

Key words: batch process, two dimensional state space model, time delay, particle filter, Bayesian method, forward-backward smoothing

摘要：

基于粒子滤波研究了间歇过程的状态估计问题。根据间歇过程双维动态特性,针对关键参数在线检测精度低、离线分析时滞大等问题，分别建立一种双维状态转移模型和时滞测量模型，并利用贝叶斯方法及前/后向平滑，提出一种含时滞测量值下的双维状态估计算法。该算法通过融合先前批次和时滞测量值的信息提高估计精度，并且克服了离线采样周期和时滞时间不确定的问题。在数字仿真和啤酒发酵过程中的仿真应用验证了该算法的有效性。

关键词: 间歇过程, 双维状态空间模型, 时滞, 粒子滤波, 贝叶斯方法, 前/后向平滑

CLC Number:

TQ920.6

QI Pengcheng, ZHAO Zhonggai, LIU Fei. Two dimensional state estimation in batch process with delayed measurements[J]. CIESC Journal, 2016, 67(9): 3784-3792.

祁鹏程, 赵忠盖, 刘飞. 含时滞测量值下间歇过程的双维状态估计[J]. 化工学报, 2016, 67(9): 3784-3792.

References 22

[1]	侯迪波. 间歇生产过程中的知识发现方法研究[D]. 杭州:浙江大学, 2004. HOU D B. Research on knowledge discovery method in batch process[D]. Hangzhou:Zhejiang University, 2004.
[2]	李慧娟. 青霉素发酵过程建模与优化[D]. 沈阳:东北大学, 2010. LI H J. Modeling and optimization of penicillin fermentation process[D]. Shenyang:Northeastern University, 2010.
[3]	姜蕾蕾. 啤酒发酵过程状态监测及控制策略的研究[D]. 哈尔滨:哈尔滨理工大学, 2014. JIANG L L. Study on state monitoring and control strategy of beer fermentation process[D]. Harbin:Harbin University of Science and Technology, 2014.
[4]	KOZUB D J, MACGREGOR J F. State estimation for semibatch polymerization reactors[J]. Chemical Engineering Science, 1992, 47(5):1047-1062.
[5]	OISIOVICI R M, CRUZ S L. State estimation of batch distillation columns using an extended Kalman filter[J]. Chemical Engineering Science, 2000, 55(20):4667-4680.
[6]	WANG J L, ZHAO L Q, YU T. On-line estimation in fed-batch fermentation process using state space model and unscented Kalman filter[J]. Chinese Journal of Chemical Engineering, 2010, 18(2):258-264.
[7]	CHEN T, JULIAN M, ELAINE M. Particle filters for state and parameter estimation in batch processes[J].Journal of Process Control, 2005, 15(6):665-673.
[8]	YAO Y, GAO F. Batch process monitoring in score space of two-dimensional dynamic principal component analysis (PCA)[J]. Industrial & Engineering Chemistry Research, 2007, 46(24):8033-8043.
[9]	ZHAO Z G, HUANG B, LIU F. Bayesian method for state estimation of batch process with missing data[J]. Computers and Chemical Engineering, 2013, 53(11):14-24.
[10]	ZHAO Z G, HUANG B, LIU F. State estimation in batch process based on two-dimensional state-space model[J]. Industrial & Engineering Chemistry Research, 2014, 53(50):19573-19582.
[11]	GUO Y F, ZHAO Y, HUANG B. Development of soft sensor by incorporating the delayed infrequent and irregular measurements[J]. Journal of Process Control, 2014, 24(11):1733-1739.
[12]	GOPALAKRISHNAN A, KAISARE N S, NARASIMHAN S. Incorporating delayed and infrequent measurements in extended Kalman filter based nonlinear state estimation[J]. Journal of Process Control, 2011, 21(1):119-129.
[13]	GUO Y F, HUANG B. State estimation incorporating infrequent, delayed and integral measurements[J]. Automatica, 2015, 58:32-38.
[14]	FERDINAND E U. State-space estimation with a Bayesian filter in a coupled PDE system for transient gas flows[J]. Original Research Article, 2015, 39(2):682-692.
[15]	ANDRIEU C, DOUCET A, SINGH S, et al. Particle methods for change detection, system identification, and control[J]. Proceedings of the IEEE, 2004, 92(3):423-443.
[16]	DOUCET A, GODSILL S, ANDRIEU C. On sequential Monte Carlo sampling methods for Bayesian filtering[J]. Statistics and Computing, 2000, 10(3):197-208.
[17]	STORVIK G. Particle filters for state-space models with the presence of unknown static parameters[J]. IEEE Trans. Signal Processing, 2002, 50(2):281-289.
[18]	RIGATOS G G. particle filtering for state estimation in nonlinear industrial systems[J]. Instrumentation and Measurement, 2009, 58(11):3885-3900.
[19]	NURMINEN H, RISTIMAKI A, ALI-LOYTTY S, et al. Particle filter and smoother for indoor localization[C]//4th International Conference on Indoor Positioning and Indoor Navigation. Montbéliard, France:IEEE, 2013:1-10.
[20]	ORGUNER U, GUSTAFSSON F. Storage efficient particle filters for the out of sequence measurement problem[C]//11th International Conference on Information Fusion. Piscataway, NJ, USA:IEEE, 2008:1-8.
[21]	KOTTAKKI K K, BHARTIYA S, BHUSHAN M. State estimation of nonlinear dynamical systems using nonlinear update based unscented Gaussian sum filter[J]. Journal of Process Control, 2014, 24(9):1425-1443.
[22]	ZHAO Z G, HUANG B, LIU F. Parameter estimation in batch process using EM algorithm with particle filter[J]. Computers and Chemical Engineering, 2013, 57(15):156-172.