Structural Health Monitoring of CFRP Composite Structures Using a Hybrid CNN-Vision Transformer Model

Advanced Structural Health Monitoring (SHM) systems are essential for aging aerospace
infrastructure and Carbon Fiber Reinforced Polymer (CFRP) structures. Though Lamb wave-based
Non-Destructive Testing (NDT) effectively monitors CFRP, traditional methods struggle with
complex wave patterns, environmental variations, and large data volumes from continuous
monitoring. This research overcomes these limitations by developing an AI system that integrates
Lamb wave testing with Vision Transformer. The approach captures Lamb wave signals via
actuators and sensors settled on CFRP structures, converting them into Continuous Wavelet
Transform (CWT) inputs, and automates damage identification. This framework improves detection
accuracy and reliability, enabling real-time assessment.