Journal of Siberian Federal University. Engineering & Technologies: Machine Learning Approach to Simulation of Continuous Seeded Crystallization of Gibbsite

Journal of Siberian Federal University. Engineering & Technologies / Machine Learning Approach to Simulation of Continuous Seeded Crystallization of Gibbsite

Full text (.pdf)

Issue: Journal of Siberian Federal University. Engineering & Technologies. 2021 14 (8)
Authors: Golubev, Vladimir O.; Blednykh, Iliya V.; Filinkov, Matvey V.; Zharkov, Oleg G.; Shchelkonogova, Tatiyana N.
Contact information: Golubev, Vladimir O.: RUSAL Engineering and Research Center Department of Mathematical Modeling St. Petersburg, Russian Federation; vladimir.golubev2@rusal.com; Blednykh, Iliya V.: RUSAL Engineering and Research Center Department of Mathematical Modeling St. Petersburg, Russian Federation; Filinkov, Matvey V.: JSC «RUSAL URAL» in Kamensk-Uralsky Production Department Kamensk-Uralsky, Russian Federation; Zharkov, Oleg G.: RUSAL Engineering and Research Center Department for Technology and Technical Development of Alumina Production Kamensk-Uralsky, Russian Federation; Shchelkonogova, Tatiyana N.: RUSAL Engineering and Research Center Department for Technology and Technical Development of Alumina Production Kamensk-Uralsky, Russian Federation
Keywords: seeded crystallization; oscillation process; prediction of time series; deep learning; alumina production; long short-term memory; convolutional network
Abstract: Continuous seeded crystallization is characterized by oscillations of particle size distribution (PSD) and liquor productivity. To describe these oscillations using analytical methods is a complicated task due to non-linearity and slow response of the process. This paper uses a statistical approach to the preparation of initial data, determination of the significant factors and arrangement of the said factors by their impact on the dynamics of crystal population development. Various methods of machine learning were analyzed to develop a model capable of forecasting the time series of particle size distribution and composition of the final solution. The paper proposes to use deep learning methods for predicting the distribution of crystals by grades and liquor productivity. Such approach has never been used for these purposes before. The study shows that models based on long short-term memory (LSTM) cells provide for better accuracy with less trainable parameters as compared with other multilayer neural networks. Training of the models and the assessment of their quality are performed using the historical data collected in the hydrate crystallization area at the operating alumina refinery
Pages: 966–985
DOI: 10.17516/1999-494X-0366
Paper at repository of SibFU: https://elib.sfu-kras.ru/handle/2311/145049

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0).