Abstract
The flow field distribution of compressor blades is critical to the performance of aero-engine. To efficiently obtain the aerodynamic loads on the blades, this study employs machine learning models to predict the aerodynamic characteristics of compressor blade surfaces. The predictive performances of these models are evaluated by applying random forest, multi-layer perceptron (MLP), one-dimensional convolutional neural network, and long short-term memory network based on simulation data of computational fluid dynamics (CFD). The results indicate that the MLP model performs exceptionally well among all test metrics, with its predictions closely matching the CFD simulation results. Further analysis using SHapley Additive exPlanations methods is performed to interpret the MLP model and reveal the importance of various input features. The research demonstrates the significant potential of machine learning methods in predicting the aerodynamics of compressor blades and providing accurate and reliable results.
Funder
National Natural Science Foundation of China
Natural Science Foundation of Tianjin Municipality