Cross-Linking Nitroxide-Mediated Radical Copolymerization from a Bayesian Experimental Design Angle

摘要

In an attempt to collect ‘‘meaningful’’ experimental data in cross-linking nitroxide-mediated radical copolymerization of stryene and divinyl benzene, a Bayesian design approach was used to derive optimal experimental sequences to be carried out in the laboratory. Since a considerable amount of prior knowledge about this polymerization system was already available from previous experimental and modeling efforts, application of the Bayesian design of experiments seemed like a perfect approach. In addition, the implementation of the Bayesian approach would, in principle, result in running fewer experiments, hence saving considerable time and resources.