CLC number: TP277
On-line Access: 2021-09-10
Received: 2020-08-24
Revision Accepted: 2020-12-23
Crosschecked: 2021-07-22
Cited: 0
Clicked: 5101
Citations: Bibtex RefMan EndNote GB/T7714
https://orcid.org/0000-0003-0144-6015
https://orcid.org/0000-0002-7512-0168
Yuxue Xu, Yun Wang, Tianhong Yan, Yuchen He, Jun Wang, De Gu, Haiping Du, Weihua Li. Quality-related locally weighted soft sensing for non-stationary processes by a supervised Bayesian network with latent variables[J]. Frontiers of Information Technology & Electronic Engineering, 2021, 22(9): 1234-1246.
@article{title="Quality-related locally weighted soft sensing for non-stationary processes by a supervised Bayesian network with latent variables",
author="Yuxue Xu, Yun Wang, Tianhong Yan, Yuchen He, Jun Wang, De Gu, Haiping Du, Weihua Li",
journal="Frontiers of Information Technology & Electronic Engineering",
volume="22",
number="9",
pages="1234-1246",
year="2021",
publisher="Zhejiang University Press & Springer",
doi="10.1631/FITEE.2000426"
}
%0 Journal Article
%T Quality-related locally weighted soft sensing for non-stationary processes by a supervised Bayesian network with latent variables
%A Yuxue Xu
%A Yun Wang
%A Tianhong Yan
%A Yuchen He
%A Jun Wang
%A De Gu
%A Haiping Du
%A Weihua Li
%J Frontiers of Information Technology & Electronic Engineering
%V 22
%N 9
%P 1234-1246
%@ 2095-9184
%D 2021
%I Zhejiang University Press & Springer
%DOI 10.1631/FITEE.2000426
TY - JOUR
T1 - Quality-related locally weighted soft sensing for non-stationary processes by a supervised Bayesian network with latent variables
A1 - Yuxue Xu
A1 - Yun Wang
A1 - Tianhong Yan
A1 - Yuchen He
A1 - Jun Wang
A1 - De Gu
A1 - Haiping Du
A1 - Weihua Li
J0 - Frontiers of Information Technology & Electronic Engineering
VL - 22
IS - 9
SP - 1234
EP - 1246
%@ 2095-9184
Y1 - 2021
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/FITEE.2000426
Abstract: soft sensors are widely used to predict quality variables which are usually hard to measure. It is necessary to construct an adaptive model to cope with process non-stationaries. In this study, a novel quality-related locally weighted soft sensing method is designed for non-stationary processes based on a Bayesian network with latent variables. Specifically, a supervised Bayesian network is proposed where quality-oriented latent variables are extracted and further applied to a double-layer similarity measurement algorithm. The proposed soft sensing method tries to find a general approach for non-stationary processes via quality-related information where the concepts of local similarities and window confidence are explained in detail. The performance of the developed method is demonstrated by application to a numerical example and a debutanizer column. It is shown that the proposed method outperforms competitive methods in terms of the accuracy of predicting key quality variables.
[1]Al-Jlibawi A, Othman MLB, Al-Huseiny MS, et al., 2019. Efficient soft sensor modelling for advanced manufacturing systems by applying hybrid intelligent soft computing techniques. Int J Simul Syst Sci Technol, 19(3):15.1-15.7.
[2]Atkeson CG, Moore AW, Schaal S, 1997. Locally weighted learning. In: Aha DW (Ed.), Lazy Learning. Springer, Dordrecht, p.11-73.
[3]Ben‐Gal I, 2008. Bayesian networks. In: Ruggeri F, Kenett RS, Faltin FW (Eds.), Encyclopedia of Statistics in Quality and Reliability. John Wiley & Sons, Chichester, p.1.
[4]Bidar B, Sadeghi J, Shahraki F, et al., 2017. Data-driven soft sensor approach for online quality prediction using state dependent parameter models. Chemom Intell Lab Syst, 162:130-141.
[5]Bishop CM, 1998. Latent variable models. In: Jordan MI (Ed.), Learning in Graphical Models. MIT Press, Cambridge, p.371-403.
[6]Cain C, 2016. Modelling latent variables for Bayesian networks. Undergraduate Research Symp. Available from https://digitalcommons.morris.umn.edu/urs_2016/2/
[7]Chang SY, Baughman EH, McIntosh BC, 2001. Implementation of locally weighted regression to maintain calibrations on FT-NIR analyzers for industrial processes. Appl Spectrosc, 55(9):1199-1206.
[8]Chen GF, Yu HL, 2007. Bayesian network and its application in maize diseases diagnosis. Proc Int Conf on Computer and Computing Technologies in Agriculture, p.917-924.
[9]Fortuna L, Graziani S, Rizzo A, et al., 2007. Soft Sensors for Monitoring and Control of Industrial Processes. Springer, London, UK.
[10]Frank E, Trigg L, Holmes G, et al., 2000. Technical note: naive Bayes for regression. Mach Learn, 41(1):5-25.
[11]Frank E, Hall M, Pfahringer B, 2002. Locally weighted naive Bayes. Proc 19th Conf on Uncertainty in Artificial Intelligence, p.249-256.
[12]Ge ZQ, 2016. Supervised latent factor analysis for process data regression modeling and soft sensor application. IEEE Trans Contr Syst Technol, 24(3):1004-1011.
[13]Ge ZQ, 2018. Process data analytics via probabilistic latent variable models: a tutorial review. Ind Eng Chem Res, 57(38):12646-12661.
[14]Ge ZQ, Song ZH, Ding SX, et al., 2017. Data mining and analytics in the process industry: the role of machine learning. IEEE Access, 5:20590-20616.
[15]Geiger D, Heckerman D, 1994. Learning Gaussian networks. In: de Mantaras RL, Poole D (Eds.), Uncertainty in Artificial Intelligence: Proceedings of the Tenth Conference (1994). Morgan Kaufmann Publishers, California, USA, p.235-243.
[16]Jiang LX, Cai ZH, Zhang H, et al., 2013. Naive Bayes text classifiers: a locally weighted learning approach. J Exp Theor Artif Intell, 25(2):273-286.
[17]Kadlec P, Gabrys B, Strandt S, 2009. Data-driven soft sensors in the process industry. Comput Chem Eng, 33(4):795-814.
[18]Kadlec P, Grbić R, Gabrys B, 2011. Review of adaptation mechanisms for data-driven soft sensors. Comput Chem Eng, 35(1):1-24.
[19]Kano M, Fujiwara K, 2012. Virtual sensing technology in process industries: trends and challenges revealed by recent industrial applications. J Chem Eng Jpn, 46(1):1-17.
[20]Kim JS, Jun CH, 2013. Ranking evaluation of institutions based on a Bayesian network having a latent variable. Knowl-Based Syst, 50:87-99.
[21]Kim S, Okajima R, Kano M, et al., 2013. Development of soft-sensor using locally weighted PLS with adaptive similarity measure. Chemom Intell Lab Syst, 124:43-49.
[22]Li CQ, Jiang LX, Li HW, 2014. Naive Bayes for value difference metric. Front Comput Sci, 8(2):255-264.
[23]Liu F, Xu DX, Yuan C, et al., 2006. Image segmentation based on Bayesian network-Markov random field model and its application to in vivo plaque composition. Proc 3rd IEEE Int Symp on Biomedical Imaging: Nano to Macro, p.141-144.
[24]Liu Q, Zhuo J, Lang ZQ, et al., 2018. Perspectives on data-driven operation monitoring and self-optimization of industrial processes. Acta Autom Sin, 44(11):1944-1956 (in Chinese).
[25]Liu ZW, Ge ZQ, Chen GJ, et al., 2018. Adaptive soft sensors for quality prediction under the framework of Bayesian network. Contr Eng Pract, 72:19-28.
[26]Masmoudi K, Abid L, Masmoudi A, 2019. Credit risk modeling using Bayesian network with a latent variable. Expert Syst Appl, 127:157-166.
[27]Mohammadi A, Zarghami R, Lefebvre D, et al., 2019. Soft sensor design and fault detection using Bayesian network and probabilistic principal component analysis. J Adv Manuf Process, 1(4):e10027.
[28]Montáns FJ, Chinesta F, Gómez-Bombarelli R, et al., 2019. Data-driven modeling and learning in science and engineering. Compt Rend Mécan, 347(11):845-855.
[29]Murphy KP, 2001. The Bayes net toolbox for Matlab. Comput Sci Stat, 33(2):1024-1034.
[30]Nie SQ, Zheng M, Ji Q, 2018. The deep regression Bayesian network and its applications: probabilistic deep learning for computer vision. IEEE Signal Process Mag, 35(1):101-111.
[31]Shao WM, Tian XM, Wang P, 2015. Supervised local and non-local structure preserving projections with application to just-in-time learning for adaptive soft sensor. Chin J Chem Eng, 23(12):1925-1934.
[32]Steurtewagen B, van den Poel D, 2020. Machine learning refinery sensor data to predict catalyst saturation levels. Comput Chem Eng, 134:106722.
[33]Tang H, Liu S, 2007. Basic theory of fuzzy Bayesian networks and its application in machinery fault diagnosis. Proc 4th Int Conf on Fuzzy Systems and Knowledge Discovery, p.132-137.
[34]Vallejo M, de la Espriella C, Gómez-Santamaría J, et al., 2019. Soft metrology based on machine learning: a review. Meas Sci Technol, 31(3):032001.
[35]Wang JB, Shao WM, Song ZH, 2019. Semi-supervised variational Bayesian student’s t mixture regression and robust inferential sensor application. Contr Eng Pract, 92: 104155.
[36]Wu J, Wu B, Pan SR, et al., 2015. Locally weighted learning: how and when does it work in Bayesian networks? Int J Comput Intell Syst, 8(S1):63-74.
[37]Yao L, Ge ZQ, 2017a. Locally weighted prediction methods for latent factor analysis with supervised and semisupervised process data. IEEE Trans Autom Sci Eng, 14(1):126-138.
[38]Yao L, Ge ZQ, 2017b. Moving window adaptive soft sensor for state shifting process based on weighted supervised latent factor analysis. Contr Eng Pract, 61:72-80.
[39]Yuan XF, Ge ZQ, Song ZH, 2014. Locally weighted kernel principal component regression model for soft sensing of nonlinear time-variant processes. Ind Eng Chem Res, 53(35):13736-13749.
[40]Yuan XF, Huang B, Ge ZQ, et al., 2016. Double locally weighted principal component regression for soft sensor with sample selection under supervised latent structure. Chemom Intell Lab Syst, 153:116-125.
[41]Yuan XF, Huang B, Wang YL, et al., 2018. Deep learning-based feature representation and its application for soft sensor modeling with variable-wise weighted SAE. IEEE Trans Ind Inform, 14(7):3235-3243.
Open peer comments: Debate/Discuss/Question/Opinion
<1>