Optimization of the semi-sphere vortex generator for film cooling using generative adversarial network

Abstract Film cooling has shown great potential in protecting hot section of high-pressure turbine from melting down. A counter-rotating vortex pair (CVP) is produced downstream of the cooling hole and reduces the lateral diffusion of the jet. To enhance the film cooling effectiveness, a semi-sphere vortex generator (SVG) is proposed to be installed downstream of the cooling hole. To optimize the performance of the semi-sphere vortex generator, it is necessary to predict the dimensionless temperature distribution accurately using surrogate models. Conventional surrogate models in the literature usually predict the lateral-averaged temperature distribution. In the current study, a conditional generative adversarial neural network (CGAN) model is developed to build the non-linear and high-dimensional mapping between the input parameters and the surface temperature distribution downstream of the SVG. The computational Fluid Dynamics (CFD) method was utilized to provide the training data. With rigorously testing and validation, it is found that the model shows high robustness and accuracy. Integrated with this low cost deep learning model, an optimization framework based on the sparrow search algorithm (SSA) was established to adjust and search the optimal parameters of SVG. The optimized design features a vortex pair rotating in the reverse direction of the CVP. The film cooling effectiveness is greatly improved when compared with the configuration without SVG. It is proved that the attempt of introducing machine learning to optimize the parameters of SVG is successful.