An advanced physics-informed neural operator for comprehensive design optimization of highly-nonlinear systems: An aerospace composites processing case study

Milad Ramezankhani, Anirudh Deodhar, Rishi Yash Parekh, Dagnachew Birru

Abstract: Highlights•The proposed physics-informed DeepONet achieves higher accuracy than vanilla DeepONet.•Incorporates nonlinear decoders and curriculum learning to handle high-dimensional design spaces.•Demonstrates robust zero-shot prediction, enhancing versatility and potential applications.•Accelerates aerospace composites process design and optimization effectively.