Calibration of soft sensor by using Just-in-time modeling and AdaBoost learning method

doi:10.1016/j.cjche.2016.05.015

›› 2016, Vol. 24 ›› Issue (8): 1038-1046.DOI: 10.1016/j.cjche.2016.05.015

• Process Systems Engineering and Process Safety • 上一篇下一篇

Calibration of soft sensor by using Just-in-time modeling and AdaBoost learning method

Huan Min, Xionglin Luo

Department of Automation, China University of Petroleum, Beijing 102249, China

收稿日期:2016-01-05 修回日期:2016-04-18 出版日期:2016-08-28 发布日期:2016-09-21
通讯作者: Xionglin Luo
基金资助:
Supported by the National Basic Research Program of China (2012CB720500).

Calibration of soft sensor by using Just-in-time modeling and AdaBoost learning method

Huan Min, Xionglin Luo

Department of Automation, China University of Petroleum, Beijing 102249, China

Received:2016-01-05 Revised:2016-04-18 Online:2016-08-28 Published:2016-09-21
Supported by:
Supported by the National Basic Research Program of China (2012CB720500).

摘要/Abstract

摘要： Soft sensor is an efficacious solution to predict the hard-to-measure target variable by using the process variables. In practical application scenarios, however, the feedback cycle of target variable is usually larger than that of the process variables, which causes the deficiency of prediction errors. Consequently soft sensor cannot be calibrated timely and deteriorates. We proposed a soft sensor calibration method by using Just-in-time modeling and AdaBoost learning method. A moving window consisting of a primary part and a secondary part is constructed. The primary part is made of history data from certain number of constant feedback cycles of target variable and the secondary part includes some coarse target values estimated initially by Just-in-time modeling during the latest feedback cycle of target variable. The data set of the whole moving window is processed by AdaBoost learning method to build an auxiliary estimation model and then target variable values of the latest corresponding feedback cycle are reestimated. Finally the soft sensor model is calibrated by using the reestimated target variable values when the target feedback is unavailable; otherwise using the feedback value. The feasibility and effectiveness of the proposed calibration method is tested and verified through a series of comparative experiments on a pH neutralization facility in our laboratory.

关键词: Process control, Measurement, Soft sensor, Calibration, Deterioration, Moving window, Just-in-time, AdaBoost

Abstract: Soft sensor is an efficacious solution to predict the hard-to-measure target variable by using the process variables. In practical application scenarios, however, the feedback cycle of target variable is usually larger than that of the process variables, which causes the deficiency of prediction errors. Consequently soft sensor cannot be calibrated timely and deteriorates. We proposed a soft sensor calibration method by using Just-in-time modeling and AdaBoost learning method. A moving window consisting of a primary part and a secondary part is constructed. The primary part is made of history data from certain number of constant feedback cycles of target variable and the secondary part includes some coarse target values estimated initially by Just-in-time modeling during the latest feedback cycle of target variable. The data set of the whole moving window is processed by AdaBoost learning method to build an auxiliary estimation model and then target variable values of the latest corresponding feedback cycle are reestimated. Finally the soft sensor model is calibrated by using the reestimated target variable values when the target feedback is unavailable; otherwise using the feedback value. The feasibility and effectiveness of the proposed calibration method is tested and verified through a series of comparative experiments on a pH neutralization facility in our laboratory.

Key words: Process control, Measurement, Soft sensor, Calibration, Deterioration, Moving window, Just-in-time, AdaBoost

Huan Min, Xionglin Luo. Calibration of soft sensor by using Just-in-time modeling and AdaBoost learning method[J]. , 2016, 24(8): 1038-1046.

参考文献

[1] L. Fortuna, S. Graziani, A. Rizzo, M.G. Xibilia, Soft sensors for monitoring and control of industrial processes, Springer, London, 2007.
[2] P. Kadlec, B. Gabrys, S. Strandt, Data-driven soft sensors in the process industry, Comput. Chem. Eng. 33(4) (2009) 795-814.
[3] K. Hiromasa, A. Masamoto, F. Kimito, Applicability domains and accuracy of prediction of soft sensor models, AIChE J. 57(6) (2011) 1506-1513.
[4] X. Zuo, F. Tu, H.Y. Qing, X.L. Luo, Advanced control of acetylene hydrogenation reactor (Ⅱ). Soft sensor and its engineering practice, Control Instrum. Chem. Ind. (China) 30(2) (2003) 19-21.
[5] R. Feng, Y.J. Zhang, Y.Z. Zhang, H.H. Shao, Drifting modeling method using weighted support vector machines with application to soft sensor, Acta Automat. Sin. 30(2004) 436-441.
[6] J.J. Macias, P. Angelov, X.W. Zhou, A method for predicting quality of the crude oil distillation, Proceedings of the Int. Symp. Evolving Fuzzy Syst, Lake, United Kingdom 2006, pp. 214-220.
[7] X. Wang, U. Kruger, G.W. Irwin, Process monitoring approach using fast moving window PCA, Ind. Eng. Chem. Res. 44(2005) 5691-5702.
[8] P. Kadlec, B. Gabrys, Adaptive local learning soft sensor for inferential control support, Proceedings of the Int. Confer. Comput. Intel. Modelling Contr. Auto. Vienna, Austria 2008, pp. 243-248.
[9] H.P. Jin, X.G. Chen, J.W. Yang, L. Wu, Adaptive soft sensor modeling framework based on just-in-time learning and kernel partial least squares regression for nonlinear multiphase batch processes, Comput. Chem. Eng. 71(2014) 77-93.
[10] S. Khatibisepehr, H. Biao, F.W. Xu, A. Espejo, A Bayesian approach to design of adaptive multi-model inferential sensors with application in oil sand industry, J. Process Control 22(2012) 1913-1929.
[11] G. Cybenko, Just-in-time learning and estimation, in:S. Bittanti, G. Picci (Eds.), Identification, adaptation, learning:The science of learning models from data, Springer, Berlin 1996, pp. 423-434.
[12] C. Cheng, M.S. Chiu, A new data-based methodology for nonlinear process modeling, Chem. Eng. Sci. 59(13) (2004) 2801-2810.
[13] K. Fujiwara, M. Kano, S. Hasebe, A. Takinami, Soft-sensor development using correlation-based just-in-time modeling, AIChE J. 55(7) (2009) 1754-1765.
[14] S. Kim, M. Kano, S. Hasebe, A. Takinami, T. Seki, Long-term industrial applications of inferential control based on just-in-time soft-sensors:Economical impact and challenges, Ind. Eng. Chem. Res. 52(35) (2013) 12346-12356.
[15] Z. Ge, Z. Song, A comparative study of just-in-time-learning based methods for online soft sensor modeling, Chemom. Intell. Lab. 104(2010) 306-317.
[16] R.E. Schapire, Explaining adaboost, Empirical inference, Springer, Berlin Heidelberg 2013, pp. 37-52.
[17] R. Rojas, AdaBoost and the super bowl of classifiers a tutorial introduction to adaptive boosting, Freie University, Berlin, Tech. Rep, 2009.
[18] Y. Freund, R. Schapire, N. Abe, A short introduction to boosting, J. Jpn. Soc. Artif. Intell. 14(1999) 771-780.
[19] Y. Liu, N. Hu, H. Wang, et al., Soft chemical analyzer development using adaptive least-squares support vector regression with selective pruning and variable moving window size, Ind. Eng. Chem. Res. 48(12) (2009) 5731-5741.
[20] S.J. Qin, Recursive PLS algorithms for adaptive data modeling, Comput. Chem. Eng. 22(4) (1998) 503-514.
[21] X.L. Luo, Process of fluid flow, Chemical process dynamics, Chemical Industry Press, Beijing 2005, pp. 25-27.
[22] P. Cao, X. Luo, Modeling for soft sensor systems and parameters updating online, J. Process Control 24(6) (2014) 975-990.
[23] P.F. Cao, X.L. Luo, Soft sensor model derived from Wiener model structure:Modeling and identification, Chin. J. Chem. Eng. 22(5) (2014) 538-548.

Calibration of soft sensor by using Just-in-time modeling and AdaBoost learning method

Calibration of soft sensor by using Just-in-time modeling and AdaBoost learning method

PDF (PC)

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	Haixiang Liu, Jun Zhang, Chunlei Dong, Gang Zhu, Guanben Du, Shuduan Deng. Synthesis, performance and structure characterization of glyoxal-monomethylolurea-melamine (G-MMU-M) co-condensed resin[J]. 中国化学工程学报, 2023, 59(7): 92-104.
[2]	Lusheng Zhai, Bo Xu, Haiyan Xia, Ningde Jin. Simultaneous measurement of velocity profile and liquid film thickness in horizontal gas-liquid slug flow by using ultrasonic Doppler method[J]. 中国化学工程学报, 2023, 58(6): 323-340.
[3]	Xiongzhuo Zhu, Dali Gao, Chong Yang, Chunjie Yang. A blast furnace fault monitoring algorithm with low false alarm rate: Ensemble of greedy dynamic principal component analysis-Gaussian mixture model[J]. 中国化学工程学报, 2023, 57(5): 151-161.
[4]	Jia Ren, Zengqiang Chen, Mingwei Sun, Qinglin Sun, Zenghui Wang. Proportion integral-type active disturbance rejection generalized predictive control for distillation process based on grey wolf optimization parameter tuning[J]. 中国化学工程学报, 2022, 49(9): 234-244.
[5]	Tianping Wang, Xuxiang Jia, Yu Wang, Chunsong Ye. Influence of CO₂ inleakage on the slight-alkalization of generator internal cooling water[J]. 中国化学工程学报, 2022, 48(8): 91-97.
[6]	Xiang Wu, Yuzhou Hou, Kanjian Zhang, Ming Cheng. Dynamic optimization of 1,3-propanediol fermentation process: A switched dynamical system approach[J]. 中国化学工程学报, 2022, 44(4): 192-204.
[7]	Vesna Krsti?. Theoretical and experimental assessment of a novel method to establish the complete measurement range of the calorimeter and its limit of detection and quantification[J]. 中国化学工程学报, 2022, 44(4): 466-473.
[8]	Teng Wang, Miao Gui, Jinle Zhao, Qincheng Bi, Tao Zhang. Void fraction measurement and calculation model of vertical upward co-current air–water slug flow[J]. 中国化学工程学报, 2022, 51(11): 178-198.
[9]	Hongliang Qian, Hongzhou Tian, Guoqiang Yang, Gaodong Yang, Lei Li, Feng Zhang, Zheng Zhou, Weihua Huang, Yufu Chen, Zhibing Zhang. Microinterface intensification in hydrogenation and air oxidation processes[J]. 中国化学工程学报, 2022, 50(10): 292-300.
[10]	Jingying Xu, Yue Lyu, Jiankun Zhuo, Yishu Xu, Zijian Zhou, Qiang Yao. Formation and emission characteristics of VOCs from a coal-fired power plant[J]. 中国化学工程学报, 2021, 35(7): 256-264.
[11]	Gabriel Khew Mun Hong, Mohd Azlan Hussain, Ahmad Khairi Abdul Wahab. Fuzzy logic controller implementation on a microbial electrolysis cell for biohydrogen production and storage[J]. 中国化学工程学报, 2021, 40(12): 149-159.
[12]	Zhuo Chen, Qiqiang Xiong, Shaowei Li, Yundong Wang, Jianhong Xu. Experimental investigation of dynamic mass transfer during droplet formation using micro-LIF in a coaxial microchannel[J]. 中国化学工程学报, 2021, 39(11): 51-58.
[13]	Yang Yuan, Kejin Huang, Xing Qian, Haisheng Chen, Lijing Zang, Liang Zhang. Enhanced temperature difference control of distillation columns based on the averaged absolute variation magnitude[J]. 中国化学工程学报, 2021, 29(1): 266-278.
[14]	Yanhong Wang, Yingnan Lu, Sufen Li, Ming Dong. Numerical study on non-uniform heat transfer deterioration of supercritical RP-3 aviation kerosene in a horizontal tube[J]. 中国化学工程学报, 2020, 28(6): 1542-1557.
[15]	Feng Pan, Zhan Du, Shaofu Li, Jun Li, Meiju Zhang, Maoqiao Xiang, Qingshan Zhu. Preparation of nano-sized tungsten carbide via fluidized bed[J]. 中国化学工程学报, 2020, 28(3): 923-932.