Physics guided machine learning modelling of compressor stall flutter

Abstract

Modern aircraft engines need to meet ever more stringent requirements that greatly increase the complexity of design, which strives for enhanced performance, reduced operating costs, emissions and noise simultaneously. The drive for performance leads to the development of thin, lightweight, highly loaded fan and compressor blades which are increasingly more prone to incur high, sustained vibratory stresses and aeroelastic problems such as flutter. The current practice employs preliminary design tools for flutter that are often based on empiricism or simplified analytical models, requiring extensive use of computational fluid dynamics to verify aeroelastic stability. As the industry moves to new designs, fast and accurate prediction tools are needed. In this work, data-driven techniques are employed to model the aeroelastic response of compressor blades. Machine learning has been applied to a plethora of engineering problems, with particular success in the field of turbulence modelling. However, conventional, black-box data-driven methods based on simple input parameters require large databases and are unable to generalise. In this work a combination of machine learning techniques and reduced order models is proposed to address both limitations at the same time. Previous knowledge of flutter is introduced in the physics guided framework by formulating relevant, steady state input features, and by injecting results from low-fidelity analytical models. The models are tested on several unseen cascades and it is found that training on even a single geometry yields accurate results. The models developed here allow flutter prediction of fan and compressor flutter stability based on the steady state flow only without a need for any CPU intensive unsteady simulations. Hence, one can predict flutter stability of a given blade for different mechanical properties (mode shape, frequency) at near zero additional cost once the mean flow is known.