Enhancing Inspector Training Through the Integration of Artificial Defect Data in Guided Wave Testing

Inspector training in non-destructive testing (NDT) is often limited by the scarcity of high-quality test samples containing defects, despite the abundance of defect-free datasets. Guided Ultrasonics Limited (GUL) has developed an innovative approach that combines real-world defect-free pipe data with artificially generated defect data to address this challenge. This synthetic data is created using the 'POGO' finite element program from Imperial College, which accurately replicates sensor configurations, pipe geometries, and data collection parameters. The resulting artificial data sets closely mimic the reflections of actual defects, enabling the integration of a wide range of defect scenarios into training and examination materials. This method has significantly enhanced the interpretation phase of guided wave training by providing diverse and standardised examination sets. These sets not only facilitate unique but consistently challenging individual assessments, but also accelerate inspector training and improve the performance of assisted analysis tools within the software. This advancement represents a significant step forward in the field of NDT, offering a scalable and effective solution for inspector training and competency assessment.