Abstract
We consider a clustering-based construction of a soft sensor with adaptive model structure and parameters and with the time factor taken into account by the example of an industrial reactive process. We propose to improve an earlier-developed adaptive soft sensor operation algorithm using a moving window and clustering by updating the model on the basis of the alternating conditional expectation algorithm with the time factor taken into account. The proposed adaptive soft sensor is shown to be advantageous in accuracy over the earlier-developed adaptation algorithm neglecting the time factor and over an adaptive soft sensor based on a neural network.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
REFERENCES
Wang, S. and Murphy, M., Estimating optimal transformations for multiple regression using the ACE algorithm, J. Data Sci., 2004, vol. 2, pp. 329–346.
AL-Qutami, T.A., Ibrahim, R., Ismail, I., and Ishak, M.A., Development of soft sensor to estimate multiphase flow rates using neural networks and early stopping, Int. J. Smart Sensing Intell. Syst., 2017, vol. 10, pp. 199–222.
Zheng, W., Liu, Y., Gao, Z., and Yang, J., Just-in-time semi-supervised soft sensor for quality prediction in industrial rubber mixers, Chemometrics Intell. Lab. Syst., 2018, vol. 180, pp. 36–41.
Xiong, W., Li, Y., Zhao, Y., and Huang, B., Adaptive soft sensor based on time difference Gaussian process regression with local time-delay reconstruction, Chem. Eng. Res. Des., 2017, vol. 117, pp. 670–680.
Yao, L. and Ge, Z., Moving window adaptive soft sensor for state shifting process based on weighted supervised latent factor analysis, Control Eng. Pract., 2017, vol. 61, pp. 72–80.
Pan, T.-H., Wong, D.S.-H., and Jang, S.-S., Development of a novel soft sensor using a local model network with an adaptive subtractive clustering approach, Ind. & Eng. Chem. Res., 2010, vol. 49(10), pp. 4738–4747.
Snegirev, O.Yu. and Torgashov, A.Yu., Clustering-based development of an adaptive soft sensor for industrial rectification columns, Avtom. Prom-sti, 2020, no. 8, pp. 44–50 (see pp. 1763–1773 in this issue of Autom. Remote Control for the English-language version).
Mozharovskii, I.S., Samotylova, S.A., and Torgashov, A.Yu., Predictive modeling of a mass-transfer technological plant using algorithm of alternating conditional expectations, Mat. Model., 2020, vol. 32, no. 3, pp. 127–147.
Zhirkov, V.F., Sushkova, L.T., Korolev, A.I., Bol’shakov, K.N., Obednin, A.A., and Prokof’ev, G.V., Polynomial interpolation in digital signal processing with high accuracy requirements, Zh. Radioelektron. [Elektron. Zh.], 2017, no. 4, pp. 1–22.
Willmott, C. and Matsuura, K., Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance, Climate Res., 2005, vol. 30, pp. 79–82.
Funding
This work was partly financially supported by the Russian Foundation for Basic Research, projects no. 20-37-90027 Post-graduates and no. 21-57-53005 GFEN_A.
Author information
Authors and Affiliations
Corresponding author
Additional information
Translated by V. Potapchouck
Rights and permissions
About this article
Cite this article
Snegirev, O.Y., Torgashov, A.Y. Adaptation of the Structure and Parameters of Nonlinear Soft Sensors by the Example of an Industrial Reactive Distillation Process. Autom Remote Control 82, 1774–1786 (2021). https://doi.org/10.1134/S0005117921100143
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S0005117921100143