Machine learning for rapid discovery of laminar flow channel wall modifications that enhance heat transfer

Abstract

Numerical simulation of fluid flow plays an essential role in modeling many physical phenomena, which enables technological advancements, contributes to sustainable practices, and expands our understanding of various natural and engineered systems. The calculation of heat transfer in fluid flow in simple flat channels is a relatively easy task for various simulation methods. However, once the channel geometry becomes more complex, numerical simulations become a bottleneck in optimizing wall geometries. We present a combination of accurate numerical simulations of arbitrary, flat, and non-flat channels as well as machine learning models trained on simulated data to predict the drag coefficient and Stanton number. We show that convolutional neural networks (CNNs) can accurately predict target properties at a fraction of the computational cost of numerical simulations. We use CNN models in a virtual high-throughput screening approach to explore a large number of possible, randomly generated wall architectures. Data augmentation techniques are incorporated to enforce physical invariances toward shifting and flipping, contributing to precise prediction for fluid flow and heat transfer characteristics. Moreover, we approach the interpretation of the trained model to better understand relevant channel structures and their influence on heat transfer. The general approach is not only applicable to simple flow setups as presented here but can be extended to more complex tasks, such as multiphase or even reactive unit operations in chemical engineering.