Coded Thermal Wave Imaging based Defect Detection in Composites using Neural Networks

Industry 4.0 focuses on the deployment of artificial intelligence in various fields for automation variety industrial applications like aerospace, defence, material manufacturing, etc. Application these principles to active thermography, facilitates automatic defect detection without human intervention and helps assessing integrity product quality. This paper employs neural network (ANN) based classification post-processing modality exploring subsurface anomalies with improved resolution enhanced detectability. A modified bi-phase seven-bit barker coded thermal wave imaging is used simulate specimens. Experimentation has been carried over CFRP GFRP specimens using artificially made flat bottom holes sizes depths. phase theoretical model also developed quantitative assessment depth anomaly experimentally cross verified a maximum error 3%. Additionally, are compared probability (POD) signal noise ratio (SNR). ANN provides better visualization defects 96% even small aspect contrast conventional post processing modalities.