Machine learning approach to simulation of continuous seeded crystallization of gibbsite

Machine learning approach to simulation of continuous seeded crystallization of gibbsite

Автор: Golubev Vladimir O., Blednykh Iliya V., Filinkov Matvey V., Zharkov Oleg G., Shchelkonogova Tatiyana N.

Журнал: Журнал Сибирского федерального университета. Серия: Техника и технологии @technologies-sfu

Рубрика: Информационно-коммуникационные технологии

Статья в выпуске: 8 т.14, 2021 года.

Бесплатный доступ

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.

Еще

Seeded crystallization, oscillation process, prediction of time series, deep learning, alumina production, long short-term memory, convolutional network

Короткий адрес: https://sciup.org/146282354

IDR: 146282354   |   DOI: 10.17516/1999-494X-0366

Список литературы Machine learning approach to simulation of continuous seeded crystallization of gibbsite

  • Li M., Wu Y. Dynamic simulation of periodic attenuation in seeded precipitation of sodium aluminate solution. Hydrometallurgy, 2012, 113-114, 91-97.
  • Bekker A.V., Li T.S., Livk I. Dynamic response of a plant-scale gibbsite precipitation circuit Hydrometallurgy, 2016, 170, 24-33.
  • Bekker A.V., Li T.S., Livk I. Understanding oscillatory behavior of gibbsite precipitation circuits, Chemical engineering research and design,2015, 101, 113-124.
  • Raahauge B.E. Smelter Grade Alumina Quality in 40+ Year Perspective: Where to from Here? Light Metals, 2015, 73-78.
  • Ramkrishna D. Population balances. Theory and Applications to Particulate Systems in Engineering. London: Academic Press, 2000,p. 355.
  • Golubev V.O., Litvinova T.E. Dynamical simulation of industrial scale gibbsite crystallization. Journal of Mining Institute, to appear.
  • Balakin B.S., Hoffmann A.C., Kosinski P. Population Balance Model for Nucleation, Growth, Aggregation, and Breakage of Hydrate Particles in Turbulent Flow, AIChE Journal, 2010, 56(8), 2052-2062.
  • Farhadi F., Babaheidary M.B. Mechanism and estimation of Al(OH)3 crystal growth, Journal of Crystal Growth, 2002,234, 721-730.
  • Ilievski D. Development and application of a constant supersaturation, semi-batch crystallizer for investigating gibbsite agglomeration, Journal of Crystal Growth, 2001, 233, 846-862.
  • Salman A. G., Kanigoro B., Heryadi Y. Weather forecasting using deep learning techniques, 2015 International Conference on Advanced Computer Science and Information Systems (ICACSIS), 2015, 281-285.
  • Tsay R.S. Multivariate time series analysis: with R and financial applications. Chicago: School of Business, 2014, 502 p. ISBN 978-1-118-61790-8.
  • Long J. Sun Z., Pardalos P.M. et al. A robust dynamic scheduling approach based on release time series forecasting for the steelmaking-continuous casting production, Applied Soft Computing Journal, 2020, 92, 1-17.
  • Petropoulos F., Makridakis S., Stylianou N. COVID-19: Forecasting confirmed cases and deaths with a simple time-series model, International Journal of Forecasting, 2020, to appear.
  • Wei W.W.S. Multivariate Time Series Analysis and Applications. Oxford: Wiley, 2019, 518 p. ISBN: 978-1-119-50285-2.
  • Chollet F. Deep Learning with Python. New York: Manning Publications Co, 2018, 440 p.
  • Reinsel G.C. Vector ARMA Time Series Models and Forecasting. Elements of Multivariate Time Series Analysis, 1993, 21-51.
  • Almqvist O. A comparative study between algorithms for time series forecasting on customer prediction. Thesis. University of Skovde, Sweden, June, 2019.
  • Hastie T., Tibshirani R., Friedman J. The Elements of Statistical Learning. Data Mining, Inference and Prediction. Second edition. Springer, 2017, 764 p.
  • Breiman L. Random Forest, Machine Learning, 2001, 45(1), 5-32.
  • Zhang G.P. Neural Networks for Time-Series Forecasting. Handbook of Natural Computing, 2012, 461-477.
  • Shiblee M., Kalra P.K., Chandra B. Time Series Prediction with Multilayer Perceptron (MLP): A New Generalized Error Based Approach. International Conference on Neural Information Processing, 2008, 37-44.
  • Borovikov V., Milkov M. Statistical Analysis of Aluminate Liquor Precipitation Process with Statistica: Classic and Modern Data Mining Methods. TRAVAUX 48, Proceedings of the 37th International ICSOBA Conference andXXV Conference «Aluminum of Siberia», Krasnoyarsk, Russia, 16-20 September, 2019, 295-303.
  • Graves A., Schmidhuber J. Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Networks, 2005, 18(5-6), 602-610.
  • Hochreiter S., Schmidhuber J. Long Short-Term Memory, Neural Computation, 1997, 9(8), 1735-1780. doi: https://doi.org/10.1162/neco.1997.9.8.1735
  • Zhang N., Shen S.-L., Zhou A., Jin Y.-F. Application of LSTM approach for modelling stressstrain behavior of Soil. Applied Soft Computing Journal,2021, 100, 1-11.
  • Fang Z., Wang Y., Peng L., Hong H., Predicting flood susceptibility using longshort-term memory (LSTM) neural network model, Journal of Hydrology, 2020, 1-56.
  • Farah S., Zameer A., Muneeb M. Predictions for COVID-19 with deep learning models of LSTM, GRU and Bi-LSTM. Chaos, Solitons and Fractals 2020,140, 1-9.
  • Yan H., Qin Y., Xiang S., Wang Y. Chen H. Long-term gear life prediction based on ordered neurons LSTM neural networks. Measurement, 2020, 165, 1-11.
  • Yan J., Mu L., Ranjan R., Zomaya A.Y. Temporal Convolutional Networks for the Advance Prediction of ENSO. Scientific reports, 2020, 10:8055. 1-15.
  • LeCun Y., Boser B., Denker J.S., Henderson D., Howard R.E., Hubbard W., Jackel L.D.: Backpropagation Applied to Handwritten Zip Code Recognition, Neural Computation,1989, 1(4), 541-551.
  • Yann L., Bottou L., Bengio Y., Haffner P. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 1988, 86(11), 2278-2324.
  • Brownlee J. Deep Learning for Time Series Forecasting. Predict the Future with MLPs, CNNs and LSTMs in Python / Machine Learning Mastery, 2019, 555 p.
  • Lea C., Flynn M.D., Vidal R. et al. Temporal Convolutional Networks for Action Segmentation and Detection. arXiv:1611.05267v1, 2016, 1-10.
  • Bai S., Kolter J.Z., Koltun V. An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling.arXiv:1803.01271v2, 2018, 1-10.
  • Smiti A. A critical overview of outlier detection methods. Computer Science Review, 2020, 38.
  • Ramaswamy S.; Rastogi R.; Shim K. Efficient algorithms for mining outliers from large data sets. Proceedings of the 2000 ACM SIGMOD international conference on Management of data.2000, p. 427. ISBN 1-58113-217-4.
  • Gu X., Akoglu L., Rinaldo A. Statistical Analysis of Nearest Neighbor Methods for Anomaly Detection, 33rd Conference on Neural Information Processing Systems, Vancouver, 2019, 1-11.
  • Jackson A.C., Lacey S. The discrete Fourier transformation for seasonality and anomaly detection of an application to rare data, Data Technologies and Applications, 2020, 54(2), 121-132.
  • Plazas-Nossa L., Avila A., Miguel A., Torres A. Detection of Outliers and Imputing of Missing Values for Water Quality UV-VIS Absorbance Time Series, Ingeniería, 2017, 22(1),111-124.
  • Scholz M., Fraunholz M., Selbig J. Nonlinear Principal Component Analysis: Neural Network Models and Applications. Principal Manifolds for Data Visualization and Dimension Reduction, 2008, 44-67.
  • Keras. Simple. Flexible. Powerful. [Electronic resource] - Access: https://keras.io/guides/
  • Belkin M. Hsu D., Xu J. Two Models of Double Descent for Weak Features / M. Belkin, SIAM Journal on Mathematics of Data Science, 2020, 2(4),1167-1180.
  • Nakkiran P., Kaplun G., Bansal Y. et al. Deep Double Descent: Where Bigger Models and More Data Hurt / P. Nakkiran, arXiv:1912.02292, 2019, 1-24.
Еще
Статья научная
SciUp 2024 © 2024 ©