In response to the growing inspection demand exerted by process automation in component manufacturing, non-destructive testing (NDT) continues to explore automated approaches that utilize deep-learning algorithms for defect identification, including within digital X-ray radiography images. This necessitates a thorough understanding of the implication of image quality parameters on the performance of these deep-learning models. This study investigated the influence of two image-quality parameters, namely signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR), on the performance of a U-net deep-learning semantic segmentation model. Input images were acquired with varying combinations of exposure factors, such as kilovoltage, milli-ampere, and exposure time, which altered the resultant radiographic image quality. The data were sorted into five different datasets according to their measured SNR and CNR values. The deep-learning model was trained five distinct times, utilizing a unique dataset for each training session. Training the model with high CNR values yielded an intersection-over-union (IoU) metric of 0.9594 on test data of the same category but dropped to 0.5875 when tested on lower CNR test data. The result of this study emphasizes the importance of achieving a balance in training dataset according to the investigated quality parameters in order to enhance the performance of deep-learning segmentation models for NDT digital X-ray radiography applications.

Industrial radiography is a pivotal non-destructive testing (NDT) method that ensures quality and safety in a wide range of industrial sectors. Conventional human-based approaches, however, are prone to challenges in defect detection accuracy and efficiency, primarily due to the high inspection demand from manufacturing industries with high production throughput. To solve this challenge, numerous computer-based alternatives have been developed, including Automated Defect Recognition (ADR) using deep learning algorithms. At the core of training, these algorithms demand large volumes of data that should be representative of real-world cases. However, the availability of digital X-ray radiography data for open research is limited by non-disclosure contractual terms in the industry. This study presents a pipeline that is capable of modeling synthetic images based on statistical information acquired from X-ray intensity distribution from real digital X-ray radiography images. Through meticulous analysis of the intensity distribution in digital X-ray images, the unique statistical patterns associated with the exposure conditions used during image acquisition, type of component, thickness variations, beam divergence, anode heel effect, etc., are extracted. The realized synthetic images were utilized to train deep learning models, yielding an impressive model performance with a mean intersection over union (IoU) of 0.93 and a mean dice coefficient of 0.96 on real unseen digital X-ray radiography images. This methodology is scalable and adaptable, making it suitable for diverse industrial applications.

Process automation utilizes specialized technology and equipment to automate and enhance production processes, leading to higher manufacturing efficiency, higher productivity, and cost savings. The aluminum die casting industry has significantly gained from the implementation of process automation solutions in manufacturing, serving safety-critical sectors such as automotive and aerospace industries. However, this method of component fabrication is very susceptible to generating manufacturing flaws, hence necessitating adequate non-destructive testing (NDT) to ascertain the fitness for use of such components. Machine learning has taken the center stage in recent years as a tool for developing automated solutions for detecting and classifying flaws in digital X-ray radiography. These machine learning-based solutions have increasingly been developed and deployed for component inspection, to keep pace with the high production throughput in manufacturing industries. This work focuses on the development of a defect grading algorithm that assesses detected flaws to ascertain if they constitute a defect that could render a component unfit for use. Guided by ASTM 2973-15; Standard Digital Reference Images for Inspection of Aluminum and Magnesium Die Castings, a grading pipeline utilizing K-D (k-dimensional) trees was developed to effectively structure detected flaws, enabling the system to make decisions based on acceptable grading terms. This solution is dynamic in terms of its conformity to different grading criteria and offers the possibility to achieve automated decision making (Accept/Reject) in digital X-ray radiography applications.

In response to the growing inspection demand exerted by process automation in component manufacturing, Non-destructive testing (NDT) continues to explore automated approaches that utilize deep learning algorithms for defect identification, including within digital X-ray radiography images. This necessitates a thorough understanding of the implication of image quality parameters on the performance of these deep learning models. This study investigates the influence of two image quality parameters, namely Signal-to-Noise Ratio (SNR) and Contrast-to-Noise Ratio (CNR), on the performance of U-net deep learning segmentation model. Input images were acquired with varying combinations of exposure factors such as kilovoltage, milli-ampere, and exposure time, which altered the resultant quality. The data was sorted into 5 different datasets according to their measured SNR and CNR values. The deep learning model was trained 5 distinct times, utilizing a unique dataset for each training session. Training the model with high CNR values yielded an intersection over Union (IoU) metric of 0.9594 on test data of the same category but drops to 0.5875 when tested on lower CNR test data. The result in this study emphasizes the importance of achieving a balance in training dataset according to the investigated quality parameters, to enhance the performance of deep learning segmentation models in NDT radiography applications.

This study investigates the semantic segmentation of common concrete defects when using different imaging modalities. One pre-trained Convolutional Neural Network (CNN) model was trained via transfer learning and tested to detect concrete defect indications, such as cracks, spalling, and internal voids. The model’s performance was compared using datasets of visible, thermal, and fused images. The data were collected from four different concrete structures and built using four infrared cameras that have different sensitivities and resolutions, with imaging campaigns conducted during autumn, summer, and winter periods. Although specific defects can be detected in monomodal images, the results demonstrate that a larger number of defect classes can be accurately detected using multimodal fused images with the same viewpoint and resolution of the single-sensor image.

Industrial radiography is a pivotal non-destructive testing (NDT) method that ensures quality and safety in a wide range of industrial sectors. Conventional human-based approaches, however, are prone to challenges in defect detection accuracy and efficiency, primarily due to the high inspection demand from manufacturing industries with high production throughput. To solve this challenge, numerous computer-based alternatives have been developed, including Auto-mated Defect Recognition (ADR) using deep learning algorithms. At the core of training, these algorithms demand large volumes of data that should be representative of real-world cases. However, the availability of digital X-ray radiography data for open research is limited by non-disclosure contractual terms in the industry. This study presents a pipeline that is capable of modeling synthetic images based on statistical information acquired from X-ray intensity distribution from real digital X-ray radiography images. Through meticulous analysis of the intensity distribution in digital X-ray images, the unique statistical patterns associated with the exposure conditions used during image acquisition, type of component, thickness variations, beam divergence, anode heel effect, etc., are extracted. The realized synthetic images were utilized to train deep learning models, yielding an impressive model performance with mean intersection over union (IoU) of 0.93, and mean dice coefficient of 0.96, on real unseen digital X-ray radiography images. This methodology is scalable and adaptable, making it suitable for diverse industrial applications.