Machine-learning assisted novel insulation layer stripping technology for upgrading the transparent EMI shielding materials

Abstract

Silver nanowires (AgNW) hold immense potential to be promoted as competitive transparent electromagnetic interference (EMI) shielding materials. To remove the insulating polyvinyl pyrrolidone (PVP) layer on the surface of AgNW, a machine learning prediction framework (MLPF) is proposed to offer guidance for a novel approach to remove insulating layers of AgNW in the films state. The trained machine learning model achieves an R² value of 0.82 on the test set, demonstrating exceptional generalization capabilities. Through experimental validation, the machine-learning assisted stripping process significantly improves the SE values of AgNW film from 20.81 dB to 28.66 dB, representing a percentage improvement of 37.72 % and maintaining high light transmittance of 82 % at 550 nm. Designed framework not only provides a brand new strategy to remove the PVP effectively, but also expands the application of machine learning in the realm of upgrading transparent EMI shielding materials for the first time.