Machine learning guided formulation design of digital light processing printable elastomers beyond viscosity stretchability tradeoff

The development of high-performance resins for vat photopolymerization-based three-dimensional printing is frequently hindered by inherent trade-offs among critical properties such as viscosity, curing kinetics, and mechanical performance. Traditional printing-based screening methods often fail to evaluate formulations that exhibit high viscosity or slow curing, thereby limiting material discovery. This research proposes a data-efficient workflow that integrates small-volume formulation screening with machine learning optimization and functional validation to enable constraint-aware material design. By establishing a comprehensive library of formulations, encompassing both printable and non-printable regimes, a small-volume mold curing approach is employed to decouple material characterization from printing limitations, thus expanding the training domain for predictive models. Regression models are subsequently trained

on key properties including viscosity, curing time, elongation at break, and tensile modulus. This methodology successfully identifies an optimized formulation that demonstrates suitable processability and high stretchability. Further thermomechanical analyses confirm a homogeneous network structure and enhanced stability, while printed components exhibit robust durability. This work presents a generalizable blueprint for the rapid formulation of photopolymers, facilitating the constraint-aware design of functional materials for applications in soft robotics and programmable three-dimensional devices.

Message: Hi FE, I need help with “Machine learning guided formulation design of digital light processing printable elastomers beyond viscosity stretchability tradeoff” in “Advanced Manufacturing & Materials Science”