U-Net-based deep learning framework for transient and time-averaged predictions in gas–solid fluidized beds

Gulia, RS, Rajodiya, P, Dave, S, Chakraborty, B, Bapat, P, Halder, K, Shekhar, S, Georgoulas, A ORCID: 0000-0002-8833-2178 and Gohil, TB (2025) U-Net-based deep learning framework for transient and time-averaged predictions in gas–solid fluidized beds. Chemical Engineering Journal, 523. p. 168324. ISSN 1385-8947

Text U Net based deep learning framework for transient and time-averaged predictions in gas solid fluidized beds.pdf - Accepted Version Access Restricted until 11 September 2026. Available under License Creative Commons Attribution Non-commercial No Derivatives. Download (11MB)

Abstract

This work proposes a U-Net-based convolutional neural network (CNN) with skip connections to predict transient and time-averaged flow characteristics in a two-phase fluidised bed. Conventional CFD simulations for gas-solid fluidised beds are computationally expensive, and prior ML models often lack generalisation or have high training complexity. A key novelty lies in introducing time as an input channel, enabling the U-Net to handle transient flow prediction without the complexity of recurrent structures. Additionally, the model simultaneously predicts multiple physical and turbulence-related quantities—such as gas and particle volume fractions, velocities, pressure, Reynolds stresses, and turbulent kinetic energy (TKE)—within a unified framework, offering both spatial and temporal fidelity. Trained on 135 CFD simulations with 85 snapshots each, the model generates high-resolution (0.001 s) predictions and shows strong agreement with OpenFOAM CFD results, with deviations below 10 % for volume fractions and under 1 % for pressure, including unseen test cases. The model accurately replicates turbulence features and passes domain-wide error analysis. Computationally, it achieves a 50× speed-up over traditional CFD, covering time-series generation, time-averaging, and turbulence quantification. This establishes the U-Net model as an efficient tool for real-time analysis and large-scale parametric studies in complex multiphase systems. Future work may extend the framework to include heat and mass transfer for thermally reactive or catalytic fluidised beds.

Item Type:	Article
Uncontrolled Keywords:	4012 Fluid Mechanics and Thermal Engineering; 40 Engineering; Machine Learning and Artificial Intelligence; Networking and Information Technology R&D (NITRD); 0904 Chemical Engineering; 0905 Civil Engineering; 0907 Environmental Engineering; Chemical Engineering; 4004 Chemical engineering; 4011 Environmental engineering; 4016 Materials engineering
Subjects:	T Technology > TA Engineering (General). Civil engineering (General) T Technology > TP Chemical technology
Divisions:	Engineering
Publisher:	Elsevier
Date of acceptance:	9 September 2025
Date Deposited:	03 Dec 2025 15:36
Last Modified:	03 Dec 2025 15:36
DOI or ID number:	10.1016/j.cej.2025.168324
URI:	https://researchonline.ljmu.ac.uk/id/eprint/27614

View Item