Turbograd: An Open-source Differentiable Performance Model for Aeroengine Condition Monitoring

Abstract

Combining physics-based and data-driven models for aero-engine condition monitoring has attracted increasing research interest in Prognostics and Health Management. Hybrid methods that incorporate physics-based models into deep neural networks typically rely on pre-trained surrogate models of
the engine performance model, which serve as a differentiable proxy during training. However, constructing such surrogates requires extensive exploration of the parameter space to generate representative datasets, resulting in a rapidly increasing computational burden as the number of model parameters grow. To address this limitation, we present TurboGrad, an open-source differentiable aeroengine performance model that reformulates the Gas Turbine Simulation Program (GSPy) in PyTorch. Because the performance model is tracked as a computation graph, gradients with respect to any model parameter follow directly via backpropagation. We compared TurboGrad against GSPy for a single-spool turbojet, finding relative errors within 0.3%. Furthermore, we demonstrate gradient-based estimation of compressor and turbine efficiencies, converging to the ground truth after 30 epochs. TurboGrad is open-source and provides a differentiable foundation for integrating physics-based aeroengine models directly into deep learning pipelines.