Soft Sensor Based on Recurrent Neural Networks: Application to Monitoring of the Production of Nitrile Rubber
DOI:
https://doi.org/10.70567/mc.v41i20.104Keywords:
Inferential sensor, batch process, NBR rubber, deep learningAbstract
In Argentina, nitrile rubber (NBR) is produced in an emulsion polymerization carried out in a batch reactor. Measuring polymer quality variables (e.g., with online analyzers or in laboratory) does not ensure an adequate monitoring of the reaction. In this work, a soft-sensor (SS) is developed to online estimate some quality variables. The complexity lies in the highly non-linear dynamics involved in the process. Therefore, the proposed SS uses recurrent neural networks. The evaluation of the estimation tool is carried out through a numerical simulator of the NBR process adjusted to the industrial plant. The estimates obtained in different reactor operation scenarios are promising. The SS could be implemented in the industrial plant in a simple way.
References
Bishop, C. M., and Bishop, H., Deep learning: Foundations and concepts. Springer Nature, 2023. https://doi.org/10.1007/978-3-031-45468-4
Cho, K., Van Merriënboer B., Gulcehre C., Bahdanau D., Bougares F., Schwenk H., and Bengio Y., Learning Phrase Representations Using RNN Encoder-Decoder for Statistical Machine Translation. arXiv:1406.1078[cs.CL], 2014. https://doi.org/10.3115/v1/D14-1179
Clementi, L. A., Suvire, R. B., Rossomando, F. G., and Vega, J. R., A Closed-Loop Control Strategy for Producing Nitrile Rubber of Uniform Chemical Composition in a Semibatch Reactor: A Simulation Study. Macromolecular Reaction Engineering, 12:1700054, 2018. https://doi.org/10.1002/mren.201700054
Goodfellow I., Bengio Y., and Courville A., Deep Learning. MIT press, 2016.
Perera, Y. S., Ratnaweera, D. A. A. C., Dasanayaka, C. H., and Abeykoon, C., The role of artificial intelligence-driven soft sensors in advanced sustainable process industries: A critical review. Engineering Applications of Artificial Intelligence, 121:105988, 2023 https://doi.org/10.1016/j.engappai.2023.105988
Sangoi, E., SBR and NBR industrial processes energetically coupled: dynamic simulation, estimation of variables and new power contributions to the energy system of the industrial complex" Ph.D. dissertation, National Technological Univ., Santa Fe, Argentina, 2021.
Sanseverinatti, C. I., Perdomo, M. M., Clementi, L. A., and Vega, J. R., An Adaptive Soft Sensor for On-Line Monitoring the Mass Conversion in the Emulsion Copolymerization of the Continuous SBR Process. Macromolecular Reaction Engineering, 17:2300025, 2023. https://doi.org/10.1002/mren.202300025
Madhuranthakam, C. M. and Penlidis, A. Improved Operating Scenarios for the Production of Acrylonitrile-Butadiene Emulsions. Polym. Eng. & Sci., 53:9-20, 2013. https://doi.org/10.1002/pen.23231
Perdomo, M. M, Clementi, L. A and Vega, J. R., Estimation of quality variables in a continuous train of reactors using recurrent neural networks-based soft sensors. Chemometrics and Intelligent Laboratory Systems, 253:105204, 2024. https://doi.org/10.1016/j.chemolab.2024.105204
Saldívar-Guerra, E., Infante-Martínez, R. and Islas-Manzur, J. M, Mathematical Modeling of the Production of Elastomers by Emulsion Polymerization in Trains of Continuous Reactors. Processes, 8:1508, 2020. https://doi.org/10.3390/pr8111508
Vega, J.R., Gugliotta, L.M., Bielsa, R.O., Brandolini, M.C. and Meira, G.R., Emulsión Copolymerization of Acrylonitrile and Butadiene. Mathematical Model of an Industrial Reactor. Ind. Eng. Chem. Res. 36:1238-1246, 1997. https://doi.org/10.1021/ie9605342
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Argentine Association for Computational Mechanics
This work is licensed under a Creative Commons Attribution 4.0 International License.
This publication is open access diamond, with no cost to authors or readers.
Only those papers that have been accepted for publication and have been presented at the AMCA congress will be published.
