An Advanced Physics-Informed Neural Operator for Comprehensive Design Optimization of Highly-Nonlinear Systems: An Aerospace Composites Processing Case Study

TL;DR

This paper presents an advanced physics-informed neural operator that significantly improves the accuracy and efficiency of designing highly nonlinear aerospace composite processes, enabling rapid, zero-shot predictions across broad design spaces.

Contribution

It introduces a novel physics-informed DeepONet with architectural and training enhancements for complex, multi-input systems, outperforming existing models by two orders of magnitude.

Findings

Outperforms vanilla DeepONet by two orders of magnitude in accuracy.

Enables zero-shot predictions across broad design spaces.

Accelerates aerospace composite process design and optimization.

Abstract

Deep Operator Networks (DeepONets) and their physics-informed variants have shown significant promise in learning mappings between function spaces of partial differential equations, enhancing the generalization of traditional neural networks. However, for highly nonlinear real-world applications like aerospace composites processing, existing models often fail to capture underlying solutions accurately and are typically limited to single input functions, constraining rapid process design development. This paper introduces an advanced physics-informed DeepONet tailored for such complex systems with multiple input functions. Equipped with architectural enhancements like nonlinear decoders and effective training strategies such as curriculum learning and domain decomposition, the proposed model handles high-dimensional design spaces with significantly improved accuracy, outperforming the vanilla physics-informed DeepONet by two orders of magnitude. Its zero-shot prediction capability across a broad design space makes it a powerful tool for accelerating composites process design and optimization, with potential applications in other engineering fields characterized by strong nonlinearity.