Learning dense gas-solids flows with physics-encoded neural network model

• Published in: Chemical engineering journal (Lausanne, Switzerland : 1996) Vol. 485; p. 150072
• Main Authors: Guo, Xiaolin, Hu, Chenshu, Dai, Yuyang, Xu, Hongbo, Zeng, Lingfang
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.04.2024
• Subjects: Deep learning; Dense gas–solid flow; Fluidized bed; Mass conservation; Physics-encoded; Surrogate model; Deep learning; Dense gas–solid flow; Surrogate model; Physics-encoded; Mass conservation; Fluidized bed
• ISSN: 1385-8947; 1873-3212
• DOI: 10.1016/j.cej.2024.150072

•A physics-encoded neural network is developed to simulate dense gas–solid flows.•A novel module is designed to solve the issue of solid mass conservation.•The proposed method realizes a speedup of more than 1,000 times.•The model reasonably predicts gas–solid flow behaviors under different geometries.•The physics-encoded model greatly improves the predictions for unseen scenarios. Computational fluid dynamics (CFD) simulations are widely employed for investigating dense gas–solid flows. However, conducting numerical simulations covering varying geometries and operating conditions is prohibitively expensive. In recent years, neural network-based methods have shown immense potential for accelerating flow field simulation. Still, forecasting the spatiotemporal evolution of gas–solid flow fields remains an open challenge for surrogate models. This study presents a physics-encoded neural network model to predict gas–solid dynamics in bubbling fluidized beds with different geometry sizes. With a novel module to estimate the particle migration distribution, the model overcomes the limitation present in pure data-driven approaches and intrinsically ensures the conservation of solid mass in the system. Additionally, it not only utilizes grid-scale information but also learns particle-scale details, thereby enhancing the forecasting performance. Through comprehensive evaluations, the physics-encoded model demonstrates significant improvements in accuracy of predicting instantaneous distributions, time-averaged and fluctuating fields, as well as bubble characteristics, in comparison to traditional data-driven models. Furthermore, our approach exhibits robust generalization capabilities, enabling it to handle previously unseen conditions with varied particle number. In contrast, data-driven models tend to memorize flow patterns seen during training, resulting in drastic deviations. In summary, the proposed method offers for a thousand-fold speedup and provides reasonable predictions for gas–solid systems with varying geometrical dimensions.