Artificial intelligence-driven non-destructive testing and structural health monitoring of natural fibre-reinforced composites: advances, challenges and future directions

Natural fibre-reinforced composites (NFRCs) are gaining popularity as an eco-friendly option to replace synthetic composites because of their light weight, renewable, biodegradable and environmentally friendly characteristics. Yet, their global use is limited due to issues of material heterogeneity, moisture sensitivity, porosity, interfacial debonding and delamination, which have a detrimental impact on the integrity and service life. The objective of this review is to critically assess the latest developments of defect detection and condition assessment technologies based on artificial intelligence (AI) and non-destructive testing (NDT) and structural health monitoring (SHM) for NFRCs. To analyse AI-assisted ultrasonic testing, acoustic emission, infrared thermography, X-ray computed tomography, computer vision and other advanced inspection techniques, the literature was systematically reviewed. The results suggest that the application of machine learning, deep learning, explainable AI, Edge AI and hybrid AI–NDT approaches has led to a significant enhancement in defect detection, damage characterisation and predictive monitoring, with several studies reporting classification accuracy of above 90–98%. The review also highlights several issues involving material variation, lack of benchmark datasets, model generalisation, computational complexity and model standardisation. The value of this research is in the development of a comprehensive framework that correlates the intelligent inspection technologies with sustainable composite engineering. This review offers important insights for researchers and industry practitioners looking to speed up the adoption of AI-based monitoring solutions in the aerospace, automotive, marine and civil infrastructure sectors.