Deploying deep learning in OpenFOAM with TensorFlow

TL;DR

This paper presents a new module for OpenFOAM that enables in-situ deployment of various deep learning models using TensorFlow, facilitating integration of machine learning with CFD simulations.

Contribution

The development of a flexible, architecture-agnostic deep learning module for OpenFOAM using TensorFlow C API, promoting open-source CFD and machine learning integration.

Findings

Supports all neural network types without restrictions

Enables in-situ deployment of trained models in CFD simulations

Fosters open-source, unified CFD and machine learning framework

Abstract

We outline the development of a data science module within OpenFOAM which allows for the in-situ deployment of trained deep learning architectures for general-purpose predictive tasks. This module is constructed with the TensorFlow C API and is integrated into OpenFOAM as an application that may be linked at run time. Notably, our formulation precludes any restrictions related to the type of neural network architecture (i.e., convolutional, fully-connected, etc.). This allows for potential studies of complicated neural architectures for practical CFD problems. In addition, the proposed module outlines a path towards an open-source, unified and transparent framework for computational fluid dynamics and machine learning.