University Research

Accessibility

1

Academic department

Mechanical Engineering Department

Description

Traditional assessment of post-impact performance in carbon fiber reinforced polymer (CFRP) composites often relies on simplified scalar metrics that fail to capture the complex spatial interactions driving failure. This study addresses this limitation by developing an automated, end-to-end deep learning framework that shifts from manual feature extraction to the direct interpretation of raw damage morphology from ultrasonic C-scans. Using a ResNet18-based convolutional neural network (CNN) trained on 1,428 augmented images, the model achieved coefficients of determination (R2) of 0.7948 ± 0.0847 for compression after impact (CAI) strength and 0.9436 ± 0.0098 for impact energy. Beyond prediction, this dual-purpose methodology serves as an analytical tool to extract physical insights. Feature importance maps show that the model identifies physically salient regions, such as delamination and surface irregularities, that align with sub-laminate buckling and matrix crushing sites. Specifically, the framework distinguishes between elliptical delamination, which triggers localized instability, and circular patterns that reflect stable load redistribution. This work provides a high-fidelity assessment tool that bridges the gap between automated non-destructive evaluation and the fundamental mechanics of composite failure.

Publisher name

Elsevier

Grant Information

N/a

Data Management

N/A

Document Type

Article

Publication Date

5-1-2026

Publication Title

Advanced Engineering Informatics

Volume

72

Share

COinS