Incremental Sheet Forming of Continuous Fiber Reinforced Polymer Composites with Artificial Intelligence-Assisted Process Modeling

This award will focus on creating a manufacturing method for fabricating composite shell structures without dedicated molds. Continuous fiber reinforced polymer composites are widely used in spacecraft, aircraft, vehicles, energy systems, biomedical devices, and other applications where low weight and high mechanical performance are important. However, current methods for making customized composite shell structures often require costly tooling and long lead times, while providing limited design freedom. Incremental sheet forming offers a flexible alternative by gradually shaping a sheet with programmed tool motion, but its use with continuous fiber composites is challenging because stiff fibers can restrict the local deformation needed during forming, decreasing achievable formability and damaging the component. This research will address this challenge by combining additive manufacturing of tailored composite sheets with a fiber/matrix interfacial strategy that allows fibers to move during forming and then become firmly bonded in the final part through post-forming heating. The resulting knowledge can support faster and more economical production of customized composite components, strengthen competitiveness in advanced manufacturing, and expand design options for high-performance industries that are critical to the national interest. The research will also support education and workforce development through undergraduate and graduate student training and research, a web-based platform for interactive learning and virtual design, industry engagement, and outreach to K-12 students. The goal of the research is to establish the material, process, structure, and property relationships that enable incremental sheet forming of continuous fiber reinforced polymer composites. The research will create additively manufactured sheet feedstocks in which continuous fibers with engineered resin coatings are arranged in designed layouts and embedded in thermoplastic matrices. These sheets will also enable strategic geometric features, such as precisely placed holes and cutouts. Experimental studies and finite element simulations will determine how material properties, fiber architecture, resin coating, and forming conditions affect fiber motion, sheet thinning, springback, damage mechanisms, and final mechanical properties during incremental forming. Artificial intelligence-assisted process models will be trained using high-fidelity simulations and experimental validation to predict forming accuracy, fiber architecture, and component performance. These models will support an inverse design tool that determines the initial sheet geometry, thickness distribution, fiber layout, and toolpath needed to compensate for forming-induced deviations. The research will provide a science-based framework for manufacturing accurate, mechanically robust composite shells and establish design principles that can be extended to other composite sheet-forming processes. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.