Defect detection using integration of ultrasonic least-squares reverse time migration and generative adversarial network

Accurate detection and characterisation of defects in high-density polyethylene (HDPE) materials are important for the safety of industrially critical structures. Ultrasonic non-destructive evaluation (UNDE) has proven to be a powerful tool for detecting and characterising defects in engineered materials. However, efficient and high-precision defect imaging in these highly attenuating materials remains a significant challenge for UNDE. Least-squares reverse time migration (LSRTM) offers the potential to reconstruct high-precision images of reflectivity. Yet, the conventional LSRTM iteratively updates the reflectivity model by minimising the data residuals, making it computationally expensive. In this paper, an efficient ultrasonic LSRTM algorithm within a deep learning framework is proposed. Building upon this, a generative adversarial network (GAN) is integrated to further enhance the reconstruction results by reducing artefacts in the images. Simulation and experimental results show that the proposed ultrasonic LSRTM-GAN can generate high-quality images, effectively enabling precise defect detection in HDPE.