CNN-based flow field prediction for bus aerodynamics analysis

Roberto Garcia-Fernandez, Koldo Portal-Porras, Oscar Irigaray, Zugatz Ansa, Unai Fernandez-Gamiz · 2023

Read CNN-based flow field prediction for bus aerodynamics analysis by Roberto Garcia-Fernandez, Koldo Portal-Porras, Oscar Irigaray, Zugatz Ansa, Unai Fernandez-Gamiz (2023) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-10692175.txt.

Description

Roberto Garcia-Fernandez and his team teach a neural network to call the flow of air around buses. Their study from twenty twenty-three swaps slow physics runs for a learned stand-in. Air flow tests shape fuel use and how steady heavy vehicles ride. Full physics runs for each new shape variant cost too much time and cash.

Three vehicle shapes gave the training runs their data. New variants of each shape made far more flow cases to learn from. Grid spacing shrank where velocity shifts fastest. The network then gave velocity and pressure fields in one step. Its outputs matched the physics runs closely in tests. Bus shapers could screen new shapes fast, well before a full run. Coach makers gain faster design cycles for airflow.

Catalog record

CREATORRoberto Garcia-Fernandez, Koldo Portal-Porras, Oscar Irigaray, Zugatz Ansa, Unai Fernandez-Gamiz
YEAR2023
COLLECTIONPAPERS
FORMATTXT
FILE SIZE62 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC10692175

Browse the full library · About the Tower of Babel