Data driven reduced modeling for fluidized bed with immersed tubes based on PCA and Bi-LSTM neural networks--颗粒学报PARTICUOLOGY

Fang, J., Cu, W., Liu, H., Zhang, H., Liu, H., Wei, J., . . . Zheng, N. (2024). Data driven reduced modeling for fluidized bed with immersed tubes based on PCA and Bi-LSTM neural networks. Particuology, 91, 1-18. https://doi.org/10.1016/j.partic.2023.12.012

Data driven reduced modeling for fluidized bed with immersed tubes based on PCA and Bi-LSTM neural networks

Jiabin Fang, Wenkai Cu, Huang Liu, Huixin Zhang, Hanqing Liu, Jinjia Wei, Xiang Ma, Nan Zheng^*

School of Chemical Engineering and Technology, Xi'an Jiaotong University, Xi'an, Shaanxi 710049, China

10.1016/j.partic.2023.12.012

Volume 91, August 2024, Pages 1-18

Received 24 October 2023, Revised 30 November 2023, Accepted 18 December 2023, Available online 28 December 2023, Version of Record 19 January 2024.

E-mail: nanzheng@mail.xjtu.edu.cn

Highlights

• A novel nonintrusive reduced-order modeling method is proposed.

• Dynamic evolution characteristics of fluidized bed flow fields are captured.

• Computational efficiency is improved by five orders of magnitude.

Abstract

The fast and accurate reduced-order modeling of fluidized beds is a challenging task in the field of fluid dynamics, owing to their high dimensionality and nonlinear dynamic behavior. In this study, a nonintrusive reduced order modeling method, the reduced order model based on principal component analysis and bidirectional long short-term memory networks (PBLSTM ROM), was developed to capture complex spatio-temporal dynamics of fluidized beds. By combining principal component analysis and Bidirectional long- short-term memory networks, the PBLSTM ROM effectively extracted dynamic evolution information without any prior knowledge of governing equations, enabling reduced-order modeling of unsteady flow fields. The PBLSTM ROM was validated using the solid volume fraction and gas velocity flow fields of a fluidized bed with immersed tubes, showing superior performance over both the PLSTM and PANN ROMs in accurately capturing temporal changes in the fluidization fields, especially in the region near immersed tubes where severe fluctuations appear. Moreover, the PBLSTM ROM improved the simulation speed by five orders of magnitude compared to traditional computational fluid dynamics simulations. These findings suggest that the PBLSTM ROM presents a promising approach for analyzing the complex fluid flows in engineering practice.

Graphical abstract

Keywords

Reduced order modeling; Fluidized bed; Deep learning; Bi-LSTM

文章导读