Neural network model applied to electromagnetic shielding effectiveness of ultra-light Ni/Cu coated polyester fibrous materials

Abstract

The purpose of effective electromagnetic interference (EMI) shielding is to prevent EMI from smartphone, wireless, and utilization of other electronic devices. The electrical conductivity of materials strongly influences on the EMI shielding properties. In this work, mainly focus to predict the EMI shielding effectiveness on the ultralight weight fibrous materials by artificial neural network (ANN). Prior to the ANN modelling, the ultra-lightweight fibrous materials were electroplated with different concentration of Ni/Cu and then coated with different silanes. This work utilizes the algorithm to provide accurate quantitative values of EMI shielding effectiveness (EM SE). To compare its performance, the experimental and the predicted EM SE values were validated by root-mean-square error (RMSE), mean absolute percentage error (MAPE) values and correlation coefficient ‘r’. The proposed ANN results accurately predict the experimental data with correlation coefficients of 0.991 and 0.997. Further due to its simplicity, reliability as well as its efficient computational capability the proposed ANN model permits relatively fast, cost effective and objective estimates to be made of serving in this industry.