Bed density analysis and prediction of ternary dense medium fluidized bed for oil shale separation using machine learning modeling--颗粒学报PARTICUOLOGY

Zhao, P., Ren, G., Guo, J., Yang, F., Zhou, C., & Zhang, B. (2025). Bed density analysis and prediction of ternary dense medium fluidized bed for oil shale separation using machine learning modeling. Particuology, 104, 165-177. https://doi.org/10.1016/j.partic.2025.06.012

Pengfei Zhao^{a b c}, Guangjian Ren^{a b c}, Junwei Guo^{a b c}, Fan Yang^{a b c}, Chenyang Zhou^{a b c}, Bo Zhang ^{a b c *}

a Key Laboratory of Coal Processing and Efficient Utilization of Ministry of Education, China University of Mining & Technology, Xuzhou, 221116, China
b School of Chemical Engineering & Technology, China University of Mining & Technology, Xuzhou, 221116, China
c Jiangsu Key Laboratory for Clean Utilization of Carbon Resources, China University of Mining & Technology, Xuzhou, 221116, China

10.1016/j.partic.2025.06.012

Volume 104, September 2025, Pages 165-177

Received 11 May 2025, Revised 17 June 2025, Accepted 24 June 2025, Available online 3 July 2025, Version of Record 10 July 2025.

E-mail: bzhang@cumt.edu.cn

Highlights

• A ternary dense medium is designed to improve density control in fluidized beds.

• Gradation rule is proposed for ternary medium beds in oil shale separation.

• Bed density prediction is accomplished by back-propagation neural network using seven key process parameters.

• Genetic-algorithm optimization is implemented to enhance BP model accuracy.

Abstract

Efficient dry beneficiation of low-grade oil shale requires precise regulation of bed density in high-density gas–solid fluidized beds. This study develops a ternary dense-medium system comprising ferrosilicon powder, magnetite powder and oil shale particles, and investigates the coupling between medium composition, hydrodynamics and machine-learning-assisted density prediction. The results demonstrated that the ternary density regulation strategy significantly enhances fluidization uniformity and separation efficiency in the dry dense-medium fluidized bed. When the oil-shale mass fraction increases from 0 % to 20 %, the critical fluidization velocity rises from 12.54 to 14.08 cm/s, while the bed expansion ratio grows from 5.19 % to 8.83 %. Compared with the conventional binary medium, the ternary system lowers the mean bed density from 2.567 to 2.382 g cm⁻³ and achieves the minimum density fluctuation (standard deviation, SD = 0.097) at an optimal oil-shale mass fraction of 8 %. A back-propagation neural network optimized by a genetic algorithm (GA-BP) using seven process features predicts bed density with correlation coefficient R = 0.979 and root-mean-square error (RMSE) of 0.049 on 167 test samples—an 18 % error reduction over the conventional BP model. The proposed ternary medium strategy and GA-BP predictor therefore offer a robust framework for stable, energy-efficient dry separation of oil shale.

Graphical abstract

Keywords

Oil shale separation; Gas–solid fluidized bed; Ternary dense medium; Machine learning; Neural network

文章导读