Rapid Bayesian optimisation for synthesis of short polymer fiber materials
This work addresses the challenge of practical experimentation in complex materials synthesis for researchers and engineers, though it appears incremental as it applies existing optimization techniques to a new domain.
The authors tackled the problem of inefficient exploration of variables in materials synthesis by developing an iterative machine learning method for optimizing process development with multiple objectives, demonstrating it on a novel fluid processing platform for short polymer fibers to efficiently direct synthesis.
The discovery of processes for the synthesis of new materials involves many decisions about process design, operation, and material properties. Experimentation is crucial but as complexity increases, exploration of variables can become impractical using traditional combinatorial approaches. We describe an iterative method which uses machine learning to optimise process development, incorporating multiple qualitative and quantitative objectives. We demonstrate the method with a novel fluid processing platform for synthesis of short polymer fibers, and show how the synthesis process can be efficiently directed to achieve material and process objectives.