A HYBRID SURROGATE MODELING APPROACH FOR DATA REDUCTION AND DESIGN SPACE EXPLORATION OF TURBINE BLADES

The conventional iterative geometry optimization process for turbine blades using computer aided engineering (CAE) simulations is both cost and time consuming and has limitations in terms of computational requirements and data management. A particularly problematic aspect is that the generated 3D simulation data of computational fluid dynamics (CFD) and finite element analysis (FEA) cannot be fully reused for future optimizations. The data for multiple geometry variations of the turbine blade can range from several hundred gigabytes to multiple terabytes. This leads to difficulties in storing and accessing them for a longer period. To address this challenge, we introduce a methodology based on machine learning models for data reduction and forecast of 3D surface field data. Specifically, we develop a convolutional variational autoencoder (VAE) that combines two models: the encoder and the decoder. The encoder transforms the input data into a representation of reduced dimensionality in a latent space, and the decoder reconstructs the input data from the given latent representation in its original space. The latent representation of the input data and the trained VAE together result in much smaller data amounts, solving the issue of data storage for future use. Furthermore, we train a fully connected feed-forward mutilayer perceptron (MLP) that learns the mapping of the geometry parameters, responsible for generating the variations, to the latent space. Thereby, we combine the MLP with the trained decoder of the VAE to our proposed multilayer perceptron variational autoencoder (MLP-VAE) hybrid neural network model. The MLP-VAE predicts the surface field data results for new and unseen blade geometry variations and generates their latent representations without any additional cost.