Saved in:
Bibliographic Details
Main Authors: Kamiński, Piotr, Wawrzak, Karol, Li, Yiqing, Noack, Bernd R., Tyliszczak, Artur
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.04030
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915478799122432
author Kamiński, Piotr
Wawrzak, Karol
Li, Yiqing
Noack, Bernd R.
Tyliszczak, Artur
author_facet Kamiński, Piotr
Wawrzak, Karol
Li, Yiqing
Noack, Bernd R.
Tyliszczak, Artur
contents This study explores heated wavy wall shape design in channel flow using machine learning, aiming to minimize temperature variation ($σ_T$) while limiting pressure loss ($Δp$). A cost function $J$ defined as a product of $σ_T$ and $Δp$ balances these competing objectives. Optimization is performed via Bayesian optimization (BO) coupled with Reynolds-Averaged Navier-Stokes (RANS) computations in an active learning loop involving up to 1000 subsequent iterations. Two shaping strategies are considered: a sinusoidal-type function defined by four parameters (two waviness amplitudes, wave count, and tilt), and a higher-dimensional approach employing a Piecewise Cubic Hermite Interpolation Polynomial (PCHIP) with 19 control points. Results show the sinusoidal design reduces $σ_T$ over $60$-fold but increases $Δp$ fourfold, while the PCHIP shape offers only a $15$-fold $σ_T$ reduction but with a twofold $Δp$ increase. Flow characteristics such as turbulent kinetic energy, pressure, temperature, and Nusselt number are examined for both optimal and suboptimal shapes along the Pareto front. The insights gained motivated a human-aided refinement of the BO result, leading to a further $17.7$\% reduction in $J$. This was achieved by replacing small-amplitude waviness periods with flat segments, which additionally significantly facilitates manufacturability.
format Preprint
id arxiv_https___arxiv_org_abs_2509_04030
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Design of the wavy wall in a partially heated channel using CFD simulations and human-assisted Bayesian optimization
Kamiński, Piotr
Wawrzak, Karol
Li, Yiqing
Noack, Bernd R.
Tyliszczak, Artur
Fluid Dynamics
This study explores heated wavy wall shape design in channel flow using machine learning, aiming to minimize temperature variation ($σ_T$) while limiting pressure loss ($Δp$). A cost function $J$ defined as a product of $σ_T$ and $Δp$ balances these competing objectives. Optimization is performed via Bayesian optimization (BO) coupled with Reynolds-Averaged Navier-Stokes (RANS) computations in an active learning loop involving up to 1000 subsequent iterations. Two shaping strategies are considered: a sinusoidal-type function defined by four parameters (two waviness amplitudes, wave count, and tilt), and a higher-dimensional approach employing a Piecewise Cubic Hermite Interpolation Polynomial (PCHIP) with 19 control points. Results show the sinusoidal design reduces $σ_T$ over $60$-fold but increases $Δp$ fourfold, while the PCHIP shape offers only a $15$-fold $σ_T$ reduction but with a twofold $Δp$ increase. Flow characteristics such as turbulent kinetic energy, pressure, temperature, and Nusselt number are examined for both optimal and suboptimal shapes along the Pareto front. The insights gained motivated a human-aided refinement of the BO result, leading to a further $17.7$\% reduction in $J$. This was achieved by replacing small-amplitude waviness periods with flat segments, which additionally significantly facilitates manufacturability.
title Design of the wavy wall in a partially heated channel using CFD simulations and human-assisted Bayesian optimization
topic Fluid Dynamics
url https://arxiv.org/abs/2509.04030