High-fidelity quantification of manufacturing-induced uncertainty in supersonic flow fields via deep autoencoder and spatially-adaptive polynomial chaos

Key Points

• Quantification reveals significant manufacturing-induced uncertainty in supersonic flow fields, impacting design robustness.
• Key evidence shows that deep autoencoder techniques enhance the understanding of flow variability characterized by polynomial chaos.
• Assessment employs advanced deep autoencoder and spatially-adaptive polynomial chaos methods to analyze complex flow fields.
• This analysis supports improved modeling practices, potentially leading to better design processes in aerospace engineering.