A subspace ensemble regression model based slow feature for soft sensing application

doi:10.1016/j.cjche.2020.07.047

中国化学工程学报 ›› 2020, Vol. 28 ›› Issue (12): 3061-3069.DOI: 10.1016/j.cjche.2020.07.047

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

A subspace ensemble regression model based slow feature for soft sensing application

Qiong Jia, Jun Cai, Xinyi Jiang, Shaojun Li

Key Laboratory of Advanced Control and Optimization for Chemical Processes, East China University of Science and Technology, Ministry of Education, Shanghai 200237, China

收稿日期:2019-12-29 修回日期:2020-05-30 出版日期:2020-12-28 发布日期:2021-01-11
通讯作者: Shaojun Li
基金资助:
The authors of this paper appreciate the support from the National Natural Science Foundation of China (No. 21676086).

A subspace ensemble regression model based slow feature for soft sensing application

Qiong Jia, Jun Cai, Xinyi Jiang, Shaojun Li

Key Laboratory of Advanced Control and Optimization for Chemical Processes, East China University of Science and Technology, Ministry of Education, Shanghai 200237, China

Received:2019-12-29 Revised:2020-05-30 Online:2020-12-28 Published:2021-01-11
Contact: Shaojun Li
Supported by:
The authors of this paper appreciate the support from the National Natural Science Foundation of China (No. 21676086).

摘要/Abstract

摘要： A novel adaptive subspace ensemble slow feature regression model was developed for soft sensing application. Compared to traditional single models and random subspace models, the proposed method is improved in three aspects. Firstly, sub-datasets are constructed through slow feature directions and variables in each subdatasets are selected according to the output related importance index. Then, an adaptive slow feature regression is presented for sub-models. Finally, a Bayesian inference strategy based on a slow feature analysis process that monitors statistics is developed for probabilistic combination. Two industrial examples were used to evaluate the proposed method.

关键词: Soft sensing, Slow feature regression, Subspace modeling, Ensemble learning

Abstract: A novel adaptive subspace ensemble slow feature regression model was developed for soft sensing application. Compared to traditional single models and random subspace models, the proposed method is improved in three aspects. Firstly, sub-datasets are constructed through slow feature directions and variables in each subdatasets are selected according to the output related importance index. Then, an adaptive slow feature regression is presented for sub-models. Finally, a Bayesian inference strategy based on a slow feature analysis process that monitors statistics is developed for probabilistic combination. Two industrial examples were used to evaluate the proposed method.

Key words: Soft sensing, Slow feature regression, Subspace modeling, Ensemble learning

Qiong Jia, Jun Cai, Xinyi Jiang, Shaojun Li. A subspace ensemble regression model based slow feature for soft sensing application[J]. 中国化学工程学报, 2020, 28(12): 3061-3069.

Qiong Jia, Jun Cai, Xinyi Jiang, Shaojun Li. A subspace ensemble regression model based slow feature for soft sensing application[J]. Chinese Journal of Chemical Engineering, 2020, 28(12): 3061-3069.

参考文献

[1] P. Kadlec, B. Gabrys, S. Strandt, Data-driven soft sensors in the process industry, Comput. Chem. Eng. 33(2009) 795-814.
[2] H. Lou, H. Su, L. Xie, Y. Gu, G. Rong, Inferential model for industrial polypropylene melt index prediction with embedded priori knowledge and delay estimation, Ind. Eng. Chem. Res. 51(2012) 8510-8525.
[3] P. Kadlec, R. Grbić, B. Gabrys, Review of adaptation mechanisms for data-driven soft sensors, Comput. Chem. Eng. 35(2011) 1-24.
[4] J.H. Zheng, Z.H. Song, Linear subspace principal domponent regression model for quality estimation of nonlinear and multimode industrial processes, Ind. Eng. Chem. Res. 56(2017) 6275-6285.
[5] B. Zhu, Z.S. Chen, Y.L. He, L.A. Yu, A novel nonlinear functional expansion based PLS (FEPLS) and its soft sensor application, Chemom. Intell. Lab. Syst. 161(2017) 108-117.
[6] S.J. Xue, X.F. Yan, A new kernel function of support vector regression combined with probability distribution and its application in chemometrics and the QSAR modeling, Chemom. Intell. Lab. Syst. 167(2017) 96-101.
[7] C. Shang, F. Yang, X.Q. Gao, X.L. Huang, J.A.K. Suykens, D.X. Huang, Concurrent monitoring of operating condition deviations and process dynamics anomalies with slow feature analysis, AIChE J. 61(2015) 3666-3682.
[8] J. Huang, O.K. Ersoy, X.F. Yan, Slow feature analysis based on online feature reordering and feature selection for dynamic chemical process monitoring, Chemom. Intell. Lab. Syst. 169(2017) 1-11.
[9] L. Wiskott, T.J. Sejnowski, Slow feature analysis:unsupervised learning of invariances, Neural Comput. 14(2002) 715-770.
[10] C. Shang, F. Yang, X.Q. Gao, D.X. Huang, Extracting Latent Dynamics From Process Data for Quality Prediction and Performance Assessment via Slow Feature Regression, American Control Conference, IEEE, Chicago, 2015912-917.
[11] C. Shang, B. Huang, F. Yang, D.X. Huang, Probabilistic slow feature analysis-based representation learning from massive process data for soft sensor modeling, AIChE J. 61(2015) 4126-4139.
[12] Z.Q. Ge, Z.H. Song, Subspace partial least squares model for multivariate spectroscopic calibration, Chemom. Intell. Lab. Syst. 125(2013) 51-57.
[13] L. Breiman, Bagging predictors, Mach. Learn. 24(1996) 123-140.
[14] Z.Q. Ge, Z.H. Song, Ensemble independent component regression models and soft sensing application, Chemom. Intell. Lab. Syst. 130(2014) 115-122.
[15] W. Konen, P. Koch, The slowness principle:SFA can detect different slow components in non-stationary time series, Int. J. Innov. Comput. Appl. 3(2011) 3-10.
[16] X.Q. Gao, C. Shang, F. Yang, D.X. Huang, Detecting and isolating plant-wide oscillations via slow feature analysis, American Control Conference (2015) 906-911.
[17] C. Shang, X.L. Huang, J.A.K. Suykens, D.X. Huang, Enhancing dynamic soft sensors based on DPLS:a temporal smoothness regularization approach, J. Process Contr. 28(2015) 17-26.
[18] F. Rossi, A. Lendasse, D. François, V. Wertz, M. Verleysen, Mutual information for the selection of relevant variables in spectrometric nonlinear modelling, Chemom. Intell. Lab. Syst. 80(2006) 215-226.
[19] R. Grbić, D. Slišković, P. Kadlec, Adaptive soft sensor for online prediction and process monitoring based on a mixture of Gaussian process models, Comput. Chem. Eng. 58(2013) 84-97.
[20] C.E. Shannon, Communication theory of secrecy systems, Bell Syst. Tech. J. 28(1949) 656-715.
[21] H.C. Peng, F.H. Long, C. Ding, Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy, IEEE Trans. Pattern Anal. Mach. Intell. 27(2005) 1226-1238.
[22] M.C. Jones, J.S. Marron, S.J. Sheather, A brief survey of bandwidth selection fordensity estimation, J. Am. Stat. Assoc. 91(1996) 401-407.
[23] J.J. Downs, E.F. Vogel, A plant-wide industrial process control problem, Comput. Chem. Eng. 17(1993) 245-255.
[24] Z. Ge, Quality prediction and analysis for large-scale processes based on multi-level principal componet modeling strategy, Control. Eng. Pract. 31(2014) 9-23.
[25] W.L. Xiong, Y.J. Li, Y.J. Zhao, B. Huang, Adaptive soft sensor based on time difference gaussian process regression with local time-delay reconstruction, Chem. Eng. Res. Des. 117(2017) 670-680.
[26] X. Yuan, L. Ye, L. Bao, Z. Ge, Z. Song, Nonlinear feature extraction for soft sensor modeling based on weighted probabilistic PCA, Chemom. Intell. Lab. Syst. 147(2015) 167-175.
[27] B. Bidar, J. Sadeghi, F. Shahraki, M. Khalilipour, Data-driven soft sensor approach for online quality prediction using state dependent parameter models, Chemom. Intell. Lab. Syst. 162(2015) 130-141.
[28] Z. Ge, Process data analytics via probablitistic latent variable models:a tutorial review, Ind. Eng. Chem. Res. 57(2018) 1246-1266.

A subspace ensemble regression model based slow feature for soft sensing application

A subspace ensemble regression model based slow feature for soft sensing application

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics

本文评价