A Human-Centric Framework for Incremental and Active Learning in AI-Based Non-Destructive Testing

Abstract

Deploying AI models for Non-Destructive Testing (NDT) in production environments remains challenging due to the dynamic nature of industrial conditions. Over time, data drift caused by process variations alters input distributions; label noise arises from inconsistent or imperfect expert annotations; and unseen scenarios introduce new defect types or signal patterns not represented during training. Together, these factors lead to progressive performance degradation, reducing model reliability and operator trust. In an industry such as NDT, where inspection reliability directly impacts structural integrity and safety, model failure is simply not acceptable. To address this challenge, this study introduces an innovative human-centric framework that synergistically integrates incremental and active learning strategies in complex NDT inspections. Incremental learning methodologies are specifically designed to enable models to continuously adapt to evolving data distributions while preserving previously acquired knowledge. At the same time, AI-assisted inspection strategies based on active learning allows NDT inspection to maintain high levels of automation with a central role of the operator in the loop. Results show that the proposed approach provides critical AI-based support, enabling inspectors to certify component acceptance or rejection with greater reliability and confidence. This facilitates next-generation NDT 5.0 systems and empowers inspectors in highly automated environments.