An Advanced Physics-Informed Neural Operator for Comprehensive Design Optimization of Highly-Nonlinear Systems: An Aerospace Composites Processing Case Study
This work addresses rapid process design optimization for aerospace composites, with potential applications in other nonlinear engineering fields, though it appears incremental as an enhancement to existing physics-informed DeepONets.
The paper tackled the problem of accurately modeling highly nonlinear aerospace composites processing systems, where existing physics-informed neural operators fail with multiple input functions, by introducing an advanced physics-informed DeepONet with architectural and training enhancements that improved accuracy by two orders of magnitude over vanilla models.
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.