Deep Learning of Forced Convection Heat Transfer

Munku Kang, Beomjin Kwon

Research output: Contribution to journalArticlepeer-review

Abstract

We present the deep learning model for internal forced convection heat transfer problems. Conditional generative adversarial networks (cGAN) are trained to predict the solution based on a graphical input describing fluid channel geometries and initial flow conditions. Without interactively solving the physical governing equations, a trained cGAN model rapidly approximates the flow temperature, Nusselt number (Nu), and friction factor (f) of a flow in a heated channel over Reynolds number ranging from 100 to 27,750. For an effective training, we optimize the dataset size, training epoch, and a hyperparameter λ. The cGAN model exhibited an accuracy up to 97.6% when predicting the local distributions of Nu and f. We also show that the trained cGAN model can predict for unseen fluid channel geometries such as narrowed, widened, and rotated channels if the training dataset is properly augmented. A simple data augmentation technique improved the model accuracy up to 70%. This work demonstrates the potential of deep learning approach to enable cost-effective predictions for thermofluidic processes.

Original languageEnglish (US)
Article number021801
JournalJournal of Heat Transfer
Volume144
Issue number2
DOIs
StatePublished - Feb 1 2022

Keywords

  • conditional generative adversarial networks
  • deep learning
  • forced convection heat transfer
  • numerical simulation

ASJC Scopus subject areas

  • Materials Science(all)
  • Condensed Matter Physics
  • Mechanics of Materials
  • Mechanical Engineering

Fingerprint

Dive into the research topics of 'Deep Learning of Forced Convection Heat Transfer'. Together they form a unique fingerprint.

Cite this