Explainable artificial intelligence prediction of defect characterization in composite materials

Abstract

Non-destructive evaluation (NDE) techniques are integral across diverse applications for void detection within composites. Infrared (IR) thermography (IRT) is a prevalent NDE technique that utilizes reverse heat transfer principles to infer defect characteristics by analyzing temperature distribution. Although the forward heat transfer problem is well-posed, its inverse counterpart lacks uniqueness, posing non-unique solutions. The present study performs simulations using finite element analysis (FEA) in defective (a penny-shaped defect) composites through which the heat transfer flux is modeled. A total of 2100 simulations with various defect positions and sizes (depth, size, and thickness) are executed, and the corresponding surface temperature vs. time and vs. distance diagrams are extracted. The FEA outputs provide ample input data for developing an explainable artificial intelligence (XAI) model to estimate the defect characteristics. A detailed feature engineering task is performed to select the representative information from the diagrams. Explainable decision tree-based machine learning (ML) models with transparent decision paths based on derived features are developed to predict the defect depth, size, and thickness. The ML models’ results suggest superb accuracy (R2 = 0.92 to 0.99) across all three defect characteristics. The provided workflow sets a benchmark applicable to a range of fields, including health monitoring.