Advanced materials such as continuous carbon fiber-reinforced thermoplastic (CFRP) laminates are commonly used in many industries, mainly because of their strength, stiffness to weight ratio, toughness, weldability, and repairability. Structural components working in harsh environments such as satellites are permanently exposed to some sort of damage during their lifetimes. To detect and characterize these damages, non-destructive testing and evaluation techniques are essential tools, especially for composite materials. In this study, artificial intelligence was applied in combination with infrared thermography to detected and segment impact damage on curved laminates that were previously submitted to a severe thermal stress cycles and subsequent ballistic impacts. Segmentation was performed on both mid-wave and long-wave infrared sequences obtained simultaneously during pulsed thermography experiments by means of a deep neural network. A deep neural network was trained for each wavelength. Both networks generated satisfactory results. The model trained with mid-wave images achieved an F1-score of 92.74% and the model trained with long-wave images achieved an F1-score of 87.39%.

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.

Pulsed thermography is an indispensable tool in the field of non-destructive evaluation. However, the data generated by this technique can be challenging to analyze and require expertise to interpret. With the rapid progress in deep learning, image segmentation has become a well-established area of research. This has motivated efforts to apply deep learning methods to non-destructive evaluation data processing, including pulsed thermography. Despite this trend, there has been a lack of public pulsed thermography datasets available for the evaluation of various spatial-temporal deep learning models for segmentation tasks. This paper aims to address this gap by presenting the PVC-Infrared dataset for deep learning. In addition, we evaluated the performance of popular deep-learning-based instance segmentation models on this dataset. Furthermore, we examined the effect of the number of frames and data transformations on the performance of these models. The results of this study suggest that appropriate preprocessing techniques can significantly reduce the size of the data while maintaining the performance of deep learning models, thereby speeding up the data processing process. This highlights the potential for using deep learning methods to make non-destructive evaluation data analysis more efficient and accessible to a wider range of practitioners.

Pulsed thermography is an established nondestructive evaluation technology that excels at detecting and characterizing subsurface defects within specimens. A critical challenge in this domain is the accurate estimation of defect depth. In this paper, a new publicly accessible pulsed infrared dataset for PVC specimens is introduced. It was enriched with 3D positional information to advance research in this area. To ensure the labeling quality, a comparative analysis of two distinct data labeling methods was conducted. The first method is based on human domain expertise, while the second method relies on 3D CAD images. The analysis showed that the CAD-based labeling method noticeably enhanced the precision of defect dimension quantification. Additionally, a sophisticated deep learning model was employed on the data, which were preprocessed by different methods to predict both the two-dimensional coordinates and the depth of the identified defects.

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.

Pulsed thermography is a vital technique in the nondestructive evaluation field. However, its data analysis can be complex and requires skilled experts. Advances in deep learning have yielded exceptional results, including image segmentation. Therefore, many efforts have been made to apply deep learning methods to data processing for nondestructive evaluation. Despite this, there is currently no public Pulsed thermographic dataset available for evaluating various spatial-temporal deep methods of segmenting pulsed thermographic data. This article aims to provide such a dataset and assess the performance of commonly used deep learning-based instance segmentation models on it. Additionally, the impact of the number of frames and data transformations on model performance is examined. The findings suggest that suitable preprocessing methods can effectively reduce the data size without compromising the deep models’ performance.