Abstract
We propose a procedure for developing an adaptive soft sensor using the example of an analyzer for a nonstationary mass-exchange process. The accuracy of the process output prediction is maximized (mean square error is minimized) by the process model error prediction, which is used as a correction to the process performance estimate. In the case of measurements of process characteristics equidistant in time, a measure of the proximity of the error spectrum distribution to the uniform distribution is used as an adaptation criterion. Such a criterion is essentially a “measure of proximity” of the process model to the optimal one. The advantage of the proposed criterion in comparison with the traditional ones, which measure the characteristics of the error spread, is that changes in the characteristics of the error spread of the model can be caused by reasons not related to the adequacy of the model. With nonequidistant measurements, the amplitudes of the harmonic components of the process are found, which permits one to reconstruct the values of the process characteristics at equidistant points in time using the inverse Fourier transform. In contrast to the traditionally used interpolation, this approach does not distort the spectrum of the process under consideration.
This is a preview of subscription content, log in via an institution to check access.
REFERENCES
Bakhtadze, N.N., Virtual analyzers: Identification approach, Autom. Remote Control, 2004, vol. 65, pp. 1691–1709. https://doi.org/10.1023/B:AURC.0000047885.52816.c7
Lototskii, V.A., Chadeev, V.M., Maksimov, E.A., and Bakhtadze, N.N., Prospects for the use of soft sensors in production control systems, Avtom. Prom-sti, 2004, no. 5, pp. 23–29.
Udugama, I.A., Camps, M.A., Taube, M.A., Thawita, C., Anantpinijwatna, A., Mansouri, S.S., and Yu, W., Novel soft sensor for measuring and controlling product recovery in a high-purity, multicomponent, side-draw distillation column, Ind. Eng. Chem. Res., 2019, vol. 58, no. 43, pp. 20026–20035. https://doi.org/10.1021/acs.iecr.9b04594
Bo, C.M., Li, J., Sun, C.Y., and Wang, Y.R., The application of neural network soft sensor technology to an advanced control system of distillation operation, Proc. Int. Joint Conf. Neural Networks (Portland, OR, 2003), vol. 2, pp. 1054–1058. https://doi.org/10.1109/IJCNN.2003.1223836
Vallejo, M., de la Espriella, C., Gуmez-Santamaria, J., Ramirez-Barrera, A.F., and Delgado-Trejos, E., Soft metrology based on machine learning: A review, Meas. Sci. Technol., 2019, vol. 31, no. 3, p. 032001. https://doi.org/10.1088/1361-6501/ab4b39
Kadlec, P., Gabrys, B., and Grbic, R., Review of adaptation mechanisms for data-driven soft sensors, Comput. Chem. Eng., 2011, vol. 35, pp. 1–24. https://doi.org/10.1016/j.compchemeng.2010.07.034
Curreri, F., Patanè, L., and Xibilia, M.G., Soft sensor transferability: A survey, Appl. Sci., 2021, vol. 11, no. 16, p. 7710. https://doi.org/10.3390/app11167710
Ditzler, G., Roveri, M., Alippi, C., and Polikar, R., Learning in nonstationary environments: A survey, IEEE Comput. Intell. Mag., 2015, vol. 10, no. 4, pp. 12–25. https://doi.org/10.1109/MCI.2015.2471196
Alakent, B., Soft sensor design using transductive moving window learner, Comput. Chem. Eng., 2020, vol. 140, p. 106941. https://doi.org/10.1016/j.compchemeng.2020.106941
Kaneko, H. and Funatsu, K., Adaptive soft sensor model using online support vector regression with time variable and discussion of appropriate hyperparameter settings and window size, Comput. Chem. Eng., 2013, vol. 58, pp. 288–297. https://doi.org/10.1016/j.compchemeng.2013.07.016
Kaneko, H., Estimating the reliability of predictions in locally weighted partial least-squares modeling, J. Chemometrics, 2021, p. e3364. https://doi.org/10.1002/cem.3364
Lu, J. and Zhao, N., Application of neural network algorithm in propylene distillation, 2021. arXiv:2104.01774.
Box, G.E.P., Jenkins, G.M., Reinsel, G.C., and Ljung, G.M., Time Series Analysis: Forecasting and Control, Hoboken, NJ: Wiley, 2016.
Qin, S., Statistical process monitoring: Basics and beyond, J. Chemometrics, 2003, vol. 17, no. 8–9, pp. 480–502. https://doi.org/10.1002/cem.800
Kolmogorov, A.N., On the empirical determination of the distribution law, in Teoriya veroyatnostei i matematicheskaya statistika (Theory of Probability and Mathematical Statistics), Prokhorov, Yu.V., Ed., Moscow: Nauka, 1986, pp. 134–141.
Marsaglia, G., Tsang, W.W., and Wang, J., Evaluating Kolmogorov’s distribution, J. Stat. Software, 2003, vol. 8, no. 18, pp. 1–4.
Klimchenko, V.V., Samotylova, S.A., and Torgashov, A.Yu., Feedback in a predictive model of a reactive distillation process, J. Comput. Syst. Sci. Int., 2019, vol. 58, no. 4, pp. 637–647. https://doi.org/10.1134/S1064230719040075
Snegirev, O.Yu. and Torgashov, A.Yu., Adaptation of the structure and parameters of nonlinear soft sensors by the example of an industrial reactive distillation process, Autom. Remote Control, 2021, vol. 82, no. 10, pp. 1774–1786. https://doi.org/10.1134/S0005117921100143
Funding
This work was supported in part by the Russian Foundation for Basic Research and the National Natural Science Foundation of China within the framework of research project no. 21-57-53005.
Author information
Authors and Affiliations
Corresponding authors
Additional information
Translated by V. Potapchouck
Rights and permissions
About this article
Cite this article
Klimchenko, V.V., Snegirev, O.Y., Shevlyagina, S.A. et al. Developing an Adaptive Soft Sensor Using a Predictive Filter for a Nonstationary Process. Autom Remote Control 83, 1984–1994 (2022). https://doi.org/10.1134/S00051179220120104
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S00051179220120104