Hybrid aero-engine performance modeling to enable real-time capability using physics-based analysis and machine learning

Abstract

The ability to achieve rapid and efficient computation is critical for real-time analysis or onboard implementation of aero engine performance models. This study presents a hybrid aero engine performance modeling approach that combines the accuracy of component map-based zero-dimensional cycle analysis with the speed of machine learning. Traditional models using iterative solvers like Newton-Raphson are computationally intensive and prone to convergence issues. To address this, a feedforward neural network was trained on data from diverse steady-state and dynamic conditions to replace the iterative solver. The machine learning -based solver reduced execution time by approximately 90 % while maintaining predictive accuracy. Applied to the F404 engine, the proposed method showed high agreement with conventional models under steady-state conditions and acceptable performance under dynamic scenarios. The distinct advantages of this integrated approach include significant computational savings, enhanced adaptability to operational changes, and improved stability, supporting real-time, onboard performance analysis and digital twin applications.