Accelerating Design Space Exploration of Film Cooling with Parametric Machine Learning Based on High-Fidelity CFD.

Jan 1, 2026·
Sondak D
Nicolas Fougere
Nicolas Fougere
,
Higgins J
,
Jammalamadaka A
,
Laskowski G
,
Bi J
,
et al
· 0 min read
Image credit: simpleflying.com
Abstract
Shaped film cooling holes are a key element in cooling turbine components to increase their operating temperature while preventing component damage. There is therefore a need for designers to rapidly explore options and identify the optimum film cooling hole configuration. In this study, we propose a machine learning (ML) approach to evaluate the performance of a given film cooling hole shape in a matter of seconds using the publicly available 777-shaped hole design. The machine learning model was trained using data generated with a Lattice Boltzmann Method (LBM) numerical solver as part of a Design of Experiment with four different parameters the forward expansion angle, the lateral expansion angle, the slot injection angle, and the blowing ratio. Blind predictions from inference of the ML model were compared to results predicted by LBM and showed a mean error of ~3 percent for the area averaged film cooling effectiveness while preserving the design relative ranking. This suggests that the method described in this paper is viable by industry standards.
Publication
AIAA SCITECH 2026 Forum. 2026. p. 1966.
Status
Peer-reviewed
publications
ML Thermal Turbomachinery Film Cooling Aeronautics Aerospace
Nicolas Fougere
Authors
Nicolas Fougere (he/him)
Senior Manager Role Portfolio

Nicolas Fougere helps global manufacturers turn emerging technology into commercial strategy. As Senior Manager for the Fluids Portfolio at Dassault Systèmes, he sets the 3-year strategy for a multi-product CFD portfolio, owns the productization and pricing models decisions, and leads the portfolio’s shift toward AI enabled simulation.

He came into this role after eight years in technical sales, where he served as account lead for some of the company’s largest customers. That work gave him a close view of how large organizations actually decide to adopt new technology, which is a big part of why his current strategy work tends to hold up once it meets a real customer.

Earlier still, he worked on mission analysis and simulation research supporting NASA and the European Space Agency’s Rosetta mission, and published more than 40 peer-reviewed papers along the way. His engineering and scientific degrees are from the University of Michigan.

What distinguishes Nicolas is the ability to move fluidly between deep technical work and business decision-making, from a simulation review with engineers to a pricing or roadmap discussion with executives. That range is increasingly what organizations need when deciding whether a simulation or AI investment is worth making.