On Surrogate Modeling of Static Response of AM Short-Fiber Thermoplastics Using Graph Neural Networks
arXiv:2606.28996v1 Announce Type: new Abstract: Short-fiber thermoplastic (SFT) composites are increasingly employed in lightweight aerospace and automotive structures owing to their favorable strength-to-weight ratio, high production rates, and recyclability. Unlike continuous-fiber systems, the mechanical response of SFTs is governed by mesoscale interactions among fiber orientation, spatial clustering, and manufacturing-induced porosity. These features exhibit significant spatial variability in manufactured components and influence stiffness, damage initiation, and nonlinear deformation. Al
The increasing adoption of short-fiber thermoplastic composites in critical industries drives the need for advanced modeling techniques to predict their complex mechanical responses effectively.
Accurate surrogate modeling using Graph Neural Networks (GNNs) can significantly accelerate the design and validation phases for lightweight, high-performance materials, impacting manufacturing efficiency and structural reliability.
The ability to rapidly and accurately simulate material behavior of SFTs using GNNs changes how these materials are designed, tested, and integrated into complex applications, potentially reducing development cycles and costs.
- · Aerospace Industry
- · Automotive Industry
- · Advanced Materials Manufacturers
- · AI/ML in Engineering Software
- · Traditional long-cycle material testing labs
- · Computational fluid dynamics (CFD) / FEA software reliant solely on empirical mo
Improved material design and validation processes for SFTs.
Faster innovation and deployment of lightweight structures in various industries, leading to enhanced performance and energy efficiency.
Broader adoption of AI-driven material science, creating new industries focused on predictive material engineering and digital twins.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG