151 / 2022-03-14 11:37:06

Predicting Dielectric Polymer Component from Different Properties via Machine Learning Method

 linear polymer,polymer design,Random forest method,Gaussian process classifier,possible seed fragments

Designing  linear polymer of excellent insulating properties  is always a disturbing  problem in  polymer design aspect, especially positively design, which means positively get structure formula from possible properties. Many inspiring methods have been put effort into the aspect.  In this manuscript, a new method has been proposed for predicting possible fragments in linear polymer and design the possible structure from targeted properties. Random forest method and Gaussian process classifier method has been used for establish the connection between five  properties and 362 possible seed fragments. In the end, a example with  properties values of PEI has been put through the method and different candidates with similar properties has been assembled including PEI polymer.