Session: 36-03 Deep Learning based applications

Paper Number: 151476

Reduced Order Modeling of the Unsteady Pressure on Turbine Rotor Blades Using Deep Learning 

In transonic turbine stages, complex interactions between trailing edge shocks from nozzle guide vanes and rotor blades generate unsteady wall pressure fields, affecting the rotor aerodynamic performance and structural integrity. While shock-related phenomena are prominent, unsteady pressure fluctuations can also arise in subsonic regimes, where wake interactions alone are sufficient to induce instationarities. Traditional methods like URANS simulations, while sufficiently accurate, are computationally expensive. To address this, a novel Deep Learning (DL) based Reduced Order Model (ROM) is proposed to predict unsteady pressure fields on a turbine rotor blade. Specifically, the model consists of a Variational Auto-Encoder (VAE) integrated with a Gated Recurrent Unit (GRU) to capture time-series data, addressing the limitations of traditional linear ROMs in capturing efficiently nonlinear phenomena, such as moving shocks. The model is applied to an industrially relevant turbomachinery design and evaluated using a combination of machine learning quality metrics and design-oriented criteria, such as the accuracy of the first harmonic of the unsteady pressure field Fourier transform. Additionally, this work explores how these criteria can be integrated into model training to drive model specialization. Finally, the impact of the simulation database size on model performance is analyzed, acknowledging that the number of simulations required to achieve task-specific accuracy is a key constraint on the industrial applicability of such approaches.

Presenting Author: Joachim Dominique Cenaero

Presenting Author Biography: Joachim Dominique is a researcher at Cenaero, a leading research center specialized in computational methods and numerical simulation. He holds a PhD from the von Karman Institute for Fluid Dynamics, where he investigated noise generation in small ducted fans. Prior to joining Cenaero, Joachim worked at Safran Aero Boosters

Authors:

Joachim Dominique Cenaero
Lionel Salesses Cenaero
Jean-François Thomas Cenaero
Lieven Baert Cenaero
Tariq Benamara Cenaero
Franck Mastrippolito Safran Helicopter Engines
Theo Flament Safran Helicopter Engines