NeuralDEM - Real-time Simulation of Industrial Particulate Flows

2024-11-14

arXiv.org

AI Summary

To address the prohibitively high computational cost and inability of discrete element method (DEM) to simulate large-scale industrial granular flows in real time—stemming from the inherent multiscale nature of particles—this paper proposes an end-to-end deep learning surrogate model. The method innovatively maps Lagrangian discrete particle systems onto continuous fields, incorporating macroscopic auxiliary field modeling. A scalable multi-branch neural operator is designed, enabling, for the first time, unified real-time modeling across the full spectrum of dynamics—from slow-varying to fast-varying regimes. By integrating a CFD-DEM coupled data-driven paradigm with learning of multiscale macroscopic observables, the model achieves 28-second trajectory prediction for a fluidized-bed reactor simulated on 160,000 CFD cells and 500,000 particles. Its computational speed exceeds conventional DEM by several orders of magnitude, thereby enabling real-time optimization of industrial processes.

Technology Category

• Machine Learning: Multimodal Learning
• Search and Optimization: Learning to Search
• Cognitive Modeling & Cognitive Systems: Computational Creativity

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Advancements in computing power have made it possible to numerically simulate large-scale fluid-mechanical and/or particulate systems, many of which are integral to core industrial processes. Among the different numerical methods available, the discrete element method (DEM) provides one of the most accurate representations of a wide range of physical systems involving granular and discontinuous materials. Consequently, DEM has become a widely accepted approach for tackling engineering problems connected to granular flows and powder mechanics. Additionally, DEM can be integrated with grid-based computational fluid dynamics (CFD) methods, enabling the simulation of chemical processes taking place, e.g., in fluidized beds. However, DEM is computationally intensive because of the intrinsic multiscale nature of particulate systems, restricting simulation duration or number of particles. Towards this end, NeuralDEM presents an end-to-end approach to replace slow numerical DEM routines with fast, adaptable deep learning surrogates. NeuralDEM is capable of picturing long-term transport processes across different regimes using macroscopic observables without any reference to microscopic model parameters. First, NeuralDEM treats the Lagrangian discretization of DEM as an underlying continuous field, while simultaneously modeling macroscopic behavior directly as additional auxiliary fields. Second, NeuralDEM introduces multi-branch neural operators scalable to real-time modeling of industrially-sized scenarios - from slow and pseudo-steady to fast and transient. Such scenarios have previously posed insurmountable challenges for deep learning models. Notably, NeuralDEM faithfully models coupled CFD-DEM fluidized bed reactors of 160k CFD cells and 500k DEM particles for trajectories of 28s. NeuralDEM will open many new doors to advanced engineering and much faster process cycles.

Problem

• Real-time simulation of industrial particulate flows
• Replacing slow numerical DEM routines with deep learning
• Modeling coupled CFD-DEM fluidized bed reactors

Innovation

• Deep learning surrogates
• Multi-branch neural operators
• Real-time industrial modeling