Saved in:
| Main Authors: | , , , , |
|---|---|
| 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 |