Automated Defect Recognition of Castings defects using Neural Networks
This addresses the need for reliable and efficient defect detection in industries like aerospace and automotive, though it is incremental as it builds on existing neural network methods for a specific application.
The paper tackled the problem of subjective and time-consuming defect classification in industrial X-ray images by developing an Automated Defect Recognition system using a Convolutional Neural Network, achieving 94.2% accuracy on an automotive castings dataset and inference times under 400 ms per image.
Industrial X-ray analysis is common in aerospace, automotive or nuclear industries where structural integrity of some parts needs to be guaranteed. However, the interpretation of radiographic images is sometimes difficult and may lead to two experts disagree on defect classification. The Automated Defect Recognition (ADR) system presented herein will reduce the analysis time and will also help reducing the subjective interpretation of the defects while increasing the reliability of the human inspector. Our Convolutional Neural Network (CNN) model achieves 94.2\% accuracy (mAP@IoU=50\%), which is considered as similar to expected human performance, when applied to an automotive aluminium castings dataset (GDXray), exceeding current state of the art for this dataset. On an industrial environment, its inference time is less than 400 ms per DICOM image, so it can be installed on production facilities with no impact on delivery time. In addition, an ablation study of the main hyper-parameters to optimise model accuracy from the initial baseline result of 75\% mAP up to 94.2\% mAP, was also conducted.