Active training sample selection and updating strategy for near-infrared model with an industrial application

doi:10.1016/j.cjche.2019.02.018

Chinese Journal of Chemical Engineering ›› 2019, Vol. 27 ›› Issue (11): 2749-2758.DOI: 10.1016/j.cjche.2019.02.018

• Process Systems Engineering and Process Safety • Previous Articles Next Articles

Active training sample selection and updating strategy for near-infrared model with an industrial application

Kaixun He¹, Kai Wang², Yayun Yan¹

1 College of Electrical Engineering and Automation, Shandong University of Science and Technology, Qingdao 266590, China;
2 Key Laboratory of Advanced Control and Optimization for Chemical Processes, Ministry of Education, East China University of Science and Technology, Shanghai 200237, China

Received:2018-10-13 Revised:2019-02-18 Online:2020-01-19 Published:2019-11-28
Contact: Kaixun He
Supported by:
Supported by the National Natural Science Foundation of China (61803234, 61751307), the Natural Science Foundation of Shandong Province, China (ZR2017BF026), China Postdoctoral Science Foundation (2018M632691), Research Fund for the Taishan Scholar Project of Shandong Province of China

Active training sample selection and updating strategy for near-infrared model with an industrial application

Kaixun He¹, Kai Wang², Yayun Yan¹

1 College of Electrical Engineering and Automation, Shandong University of Science and Technology, Qingdao 266590, China;
2 Key Laboratory of Advanced Control and Optimization for Chemical Processes, Ministry of Education, East China University of Science and Technology, Shanghai 200237, China

通讯作者: Kaixun He
基金资助:
Supported by the National Natural Science Foundation of China (61803234, 61751307), the Natural Science Foundation of Shandong Province, China (ZR2017BF026), China Postdoctoral Science Foundation (2018M632691), Research Fund for the Taishan Scholar Project of Shandong Province of China

Abstract

Abstract: Training sample selection is widely accepted as an important step in developing a near-infrared (NIR) spectroscopic model. For industrial applications, the initial training dataset is usually selected empirically. This process is time-consuming, and updating the structure of the modeling dataset online is difficult. Considering the static structure of the modeling dataset, the performance of the established NIR model could be degraded in the online process. To cope with this issue, an active training sample selection and updating strategy is proposed in this work. The advantage of the proposed approach is that it can select suitable modeling samples automatically according to the process information. Moreover, it can adjust model coefficients in a timely manner and avoid arbitrary updating effectively. The effectiveness of the proposed method is validated by applying the method to an industrial gasoline blending process.

Key words: Near-infrared spectroscopy, Chemical processes, Process systems, Soft sensor, Gasoline blending

摘要： Training sample selection is widely accepted as an important step in developing a near-infrared (NIR) spectroscopic model. For industrial applications, the initial training dataset is usually selected empirically. This process is time-consuming, and updating the structure of the modeling dataset online is difficult. Considering the static structure of the modeling dataset, the performance of the established NIR model could be degraded in the online process. To cope with this issue, an active training sample selection and updating strategy is proposed in this work. The advantage of the proposed approach is that it can select suitable modeling samples automatically according to the process information. Moreover, it can adjust model coefficients in a timely manner and avoid arbitrary updating effectively. The effectiveness of the proposed method is validated by applying the method to an industrial gasoline blending process.

关键词: Near-infrared spectroscopy, Chemical processes, Process systems, Soft sensor, Gasoline blending

Kaixun He, Kai Wang, Yayun Yan. Active training sample selection and updating strategy for near-infrared model with an industrial application[J]. Chinese Journal of Chemical Engineering, 2019, 27(11): 2749-2758.

Kaixun He, Kai Wang, Yayun Yan. Active training sample selection and updating strategy for near-infrared model with an industrial application[J]. 中国化学工程学报, 2019, 27(11): 2749-2758.

References

[1] J. Li, I.A. Karimi, Scheduling gasoline blending operations from recipe determination to shipping using unit slots, Ind. Eng. Chem. Res. 50(15) (2011) 9156-9174.
[2] H. Cheng, Z. Liu, F. Qian, A novel octane number model for gasoline blending and its application, Comput. Appl. Chem. 27(10) (2010) 1317-1320.
[3] A. Singh, P.J. Vermeer, S.S. Woo, J.F. Forbes, Model-based real-time optimization of automotive gasoline blending operations, J. Process Control 10(1) (2000) 43-58.
[4] K. He, F. Qian, H. Cheng, W.L. Du, Improved integrated optimization method of gasoline blend planning and real-time blend recipes, Ind. Eng. Chem. Res. 55(16) (2016) 4632-4645.
[5] Y. Wu, Y. Jin, Y. Li, D. Sun, X. Liu, Y. Chen, NIR spectroscopy as a process analytical technology (PAT) tool for on-line and real-time monitoring of an extraction process, Vib. Spectrosc. 58(1) (2012) 109-118.
[6] J. Wan, Z. Han, K. Liu, RON predicted of gasoline by NIR based on ICA and SVM, International Computer Conference on Wavelet Active Media Technology and Information Processing, IEEE 2016, pp. 498-501.
[7] W. Ni, L. NRgaard, M. MRup, Non-linear calibration models for near infrared spectroscopy, Anal. Chim. Acta 813(2014) 1-14.
[8] J.S. Shenk, J.J. Workman, M.O. Westerhaus, Handbook of Near-Infrared Analysis, CRC Press, 2001.
[9] R.M. Balabin, R.Z. Safieva, E.I. Lomakina, Comparison of linear and nonlinear calibration models based on near infrared (NIR) spectroscopy data for gasoline properties prediction, Chemom. Intell. Lab. Syst. 88(2) (2007) 183-188.
[10] R. Nikzadlangerodi, E. Lughofer, C. Cernuda, T. Reischer, W. Kantner, M. Pawliczek, M. Brandstetter, Calibration model maintenance in melamine resin production:Integrating drift detection, smart sample selection and model adaptation, Anal. Chim. Acta 1013(2) (2018) 1-12.
[11] P. Kadlec, R. Grbi, B. Gabrys, Review of adaptation mechanisms for data-driven soft sensors, Comput. Chem. Eng. 35(1) (2011) 1-24.
[12] O. Devos, C. Ruckebusch, A. Durand, L. Duponchel, J.P. Huvenne, Support vector machines (SVM) in near infrared (NIR) spectroscopy:Focus on parameters optimization and model interpretation, Chemom. Intell. Lab. Syst. 96(1) (2009) 27-33.
[13] C. Mei, Y. Su, G. Liu, Y. Ding, Z. Liao, Dynamic soft sensor development based on Gaussian mixture regression for fermentation processes, Chin. J. Chem. Eng. 25(1) (2017) 116-122.
[14] F. Allegrini, J.A. Fernndez Pierna, W.D. Fragoso, A.C. Olivieri, V. Baeten, P. Dardenne, Regression models based on new local strategies for near infrared spectroscopic data, Anal. Chim. Acta 933(24) (2016) 50-58.
[15] Y. Wang, Y. Si, B. Huang, Z. Lou, Survey on the theoretical research and engineering applications of multivariate statistics process monitoring algorithms:2008-2017, Can. J. Chem. Eng. 96(10) (2018) 2073-2085.
[16] Q.P. Mei, T.F. Li, L.Z. Yao, D. Huang, Y.L. Yang, Study of an adaptable calibration model of near-infrared spectra based on KF-PLS, Chemom. Intell. Lab. Syst. 157(15) (2016) 152-161.
[17] H. Jin, X. Chen, J. Yang, L. Wang, L. Wu, Online local learning based adaptive soft sensor and its application to an industrial fed-batch chlortetracycline fermentation process, Chemom. Intell. Lab. Syst. 143(15) (2015) 58-78.
[18] A. Rinnan, M. Andersson, C. Ridder, S.B. Engelsen, Recursive weighted partial least squares (rPLS):an efficient variable selection method using PLS, J. Chemom. 28(5) (2014) 439-447.
[19] N. Qi, Z. Zhang, Y. Xiang, P.B. Harrington, Locally linear embedding method for dimensionality reduction of tissue sections of endometrial carcinoma by near infrared spectroscopy, Anal. Chim. Acta 724(8) (2012) 12-19.
[20] H. Min, X.L. Luo, Calibration of soft sensor by using just-in-time modeling and Adaboost learning method, Chin. J. Chem. Eng. 24(8) (2016) 1038-1046.
[21] H. Kaneko, K. Funatsu, Ensemble locally weighted partial least squares as a just in time modeling method, AIChE J 62(3) (2016) 717-725.
[22] M. Anzanello, F. Fogliatto, M.C.A. Marcelo, D. Pozebon, M.F. Ferro, Wavelength selection framework for classifying food and pharmaceutical samples into multiple classes, J. Chemom. 30(6) (2016) 346-353.
[23] R. Liu, G. Tawa, A. Wallqvist, Locally weighted learning methods for predicting dosedependent toxicity with application to the human maximum recommended daily dose, Chem. Res. Toxicol. 25(10) (2012) 2216-2226.
[24] 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.
[25] B.S. Dayal, J.F. Macgregor, Improved PLS algorithms, J. Chemom. 11(1) (1997) 73-85.
[26] Q. Ding, G.W. Small, M.A. Arnold, Genetic algorithm-based wavelength selection for the near-infrared determination of glucose in biological matrixes:Initialization strategies and effects of spectral resolution, Anal. Chem. 70(21) (1998) 4472-4479.
[27] C. Cernuda, E. Lughofer, G. Mayr, T. Rder, P. Hintenaus, W. Mrzinger, J. Kasberger, Incremental and decremental active learning for optimized self-adaptive calibration in viscose production, Chemom. Intell. Lab. Syst. 138(15) (2014) 14-29.

Active training sample selection and updating strategy for near-infrared model with an industrial application

Active training sample selection and updating strategy for near-infrared model with an industrial application

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics

Comments

[1]	Danlei Chen, Yiqing Luo, Xigang Yuan. Cascade refrigeration system synthesis based on hybrid simulated annealing and particle swarm optimization algorithm [J]. Chinese Journal of Chemical Engineering, 2023, 58(6): 244-255.
[2]	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]. Chinese Journal of Chemical Engineering, 2023, 57(5): 151-161.
[3]	Shanwei Xiong, Li Zhou, Yiyang Dai, Xu Ji. Attention-based long short-term memory fully convolutional network for chemical process fault diagnosis [J]. Chinese Journal of Chemical Engineering, 2023, 56(4): 1-14.
[4]	Fangyuan Ma, Cheng Ji, Jingde Wang, Wei Sun. Early identification of process deviation based on convolutional neural network [J]. Chinese Journal of Chemical Engineering, 2023, 56(4): 104-118.
[5]	Yiming Bai, Shuaiyu Xiang, Feifan Cheng, Jinsong Zhao. A dynamic-inner LSTM prediction method for key alarm variables forecasting in chemical process [J]. Chinese Journal of Chemical Engineering, 2023, 55(3): 266-276.
[6]	Qingming Ma, Jianhong Xu. Green microfluidics in microchemical engineering for carbon neutrality [J]. Chinese Journal of Chemical Engineering, 2023, 53(1): 332-345.
[7]	Minjie Shi, Hangtian Zhu, Cheng Yang, Jing Xu, Chao Yan. Chemical reduction-induced fabrication of graphene hybrid fibers for energy-dense wire-shaped supercapacitors [J]. Chinese Journal of Chemical Engineering, 2022, 47(7): 1-10.
[8]	Ruoshi Qin, Jinsong Zhao. Adaptive multiscale convolutional neural network model for chemical process fault diagnosis [J]. Chinese Journal of Chemical Engineering, 2022, 50(10): 398-411.
[9]	Danlei Chen, Yiqing Luo, Xigang Yuan. Refrigeration system synthesis based on de-redundant model by particle swarm optimization algorithm [J]. Chinese Journal of Chemical Engineering, 2022, 50(10): 412-422.
[10]	Yuyang Kang, Yiqing Luo, Xigang Yuan. Recent progress on equation-oriented optimization of complex chemical processes [J]. Chinese Journal of Chemical Engineering, 2022, 41(1): 162-169.
[11]	Zhiquan Wang, Liang Wang, Zhihong Yuan, Bingzhen Chen. Data-driven optimal operation of the industrial methanol to olefin process based on relevance vector machine [J]. Chinese Journal of Chemical Engineering, 2021, 34(6): 106-115.
[12]	Xiaoyu Wang, Haibo Zhao, Mingze Su. A comparative process simulation study of Ca—Cu looping involving post-combustion CO₂ capture [J]. Chinese Journal of Chemical Engineering, 2020, 28(9): 2382-2390.
[13]	Shutian Chen, Qingchao Jiang, Xuefeng Yan. Multimodal process monitoring based on transition-constrained Gaussian mixture model [J]. Chinese Journal of Chemical Engineering, 2020, 28(12): 3070-3078.
[14]	Tao Yang, Yiqing Luo, Yingjie Ma, Xigang Yuan. Optimal synthesis of compression refrigeration system using a novel MINLP approach [J]. Chin.J.Chem.Eng., 2018, 26(8): 1662-1669.
[15]	Li Xia, Yuanli Feng, Xiaoyan Sun, Shuguang Xiang. Design of heat exchanger network based on entransy theory [J]. Chin.J.Chem.Eng., 2018, 26(8): 1692-1699.