Xavier Maldague’s research while affiliated with Université Laval and other places

The accuracy of identifying defects using specialized deep learning models can be affected by the circumstances in which the training data is curated. This is especially evident in digital X-ray radiography, where the depiction of flaws is significantly impacted by the exposure conditions. This study examines the effect of curating highquality data on deep learning models. The variation in contrast-to-noise ratio (CNR), which is a crucial metric of image quality between features of interest and an adjacent normal background, has been found to be a key factor in model generalization in digital X-ray radiography applications. By making systematic alterations to exposure conditions during data curation, it was possible to obtain several representations of flaws in each test component with varying contrast-to-noise ratios (CNR) in the resultant radiographs. To evaluate the efficacy of the model under various conditions, two distinct datasets were curated. Dataset 1 was obtained by acquiring images with a consistent exposure setting on 140 test samples. The samples contained 4 morphologically distinct classes of flat bottom holes with seven different depths and sizes. The contrast-to-noise ratio (CNR) representations of flaws in this dataset can be attributed only to differences in depth in Dataset 1. Additionally, Dataset 2 was curated with an expanded range of CNR values by methodically adjusting exposure settings during image acquisitions. Hence, only 42 % of the test pieces from Dataset 1, which had three distinct depths of flat bottom holes, were used. Each of the two datasets was used to separately train YOLOv8 for instance segmentation and Unet for multi-class semantic segmentation. Each model was trained under the same conditions, and their performances were assessed using test sets from both dataset groups. The model trained on Dataset 1 exhibited a notable decline in performance when evaluated on test sets from Dataset 2, suggesting a lack of generalization ability. Conversely, the model that was trained using Dataset 2 consistently achieved high accuracy on both test sets, demonstrating impressive performance and successful generalization. This work shows that the generalization abilities of deep learning models may be improved by varying the contrast-to-noise ratio (CNR) of features in the training data. This finding paves the way for practical applications in digital X-ray radiography.

Infrared thermography (IRT) is a widely used temperature measurement technology, but it faces the problem of measurement errors under interference factors. This paper attempts to summarize the common interference factors and temperature compensation methods when applying IRT. According to the source of factors affecting the infrared temperature measurement accuracy, the interference factors are divided into three categories: factors from the external environment, factors from the measured object, and factors from the infrared thermal imager itself. At the same time, the existing compensation methods are classified into three categories: Mechanism Modeling based Compensation method (MMC), Data-Driven Compensation method (DDC), and Mechanism and Data jointly driven Compensation method (MDC). Furthermore, we discuss the problems existing in the temperature compensation methods and future research directions, aiming to provide some references for researchers in academia and industry when using IRT technology for temperature measurement.

Infrared thermography has been widely applied in real industrial inspection of aerospace, energy management systems, engines, and electric systems. However, two-dimensional imaging modality limits its development. Here, a technique named frequency multiplexed photothermal correlation tomography (FM-PCT) was developed to enable non-destructive and contactless cross-sectional imaging for manufactured material evaluation and characterization. By combining advantages of photothermal tomography and pulsed thermography, FM-PCT facilitates the generation of three-dimensional thermal images through temporal superposition (stacking) of two-dimensional images from sequential subsurface depths. FM-PCT image processing involves pulsed excitation signals to which frequency delay and matched filtering techniques are applied. Major features of FM-PCT are high-resolution three-dimensional tomographic imaging under low camera frame-rate conditions with self-correcting capability for diffusion (blurring) correction of subsurface images due to cross-correlation processing of individual frequencies in the Fourier decomposition spectrum of the excitation pulse. Furthermore, FM-PCT extends truncated-correlation photothermal coherence tomography from chirp and pulsed signals to more general linear heating sources. Lock-in thermography and x-ray computed tomography validation demonstrate that 3D FM-PCT imaging accurately reveals subsurface discontinuities/defects in solids despite the diffusive nature of thermal-wave imaging.

Detecting defects on aerospace surfaces is critical to ensure safety and maintain the integrity of aircraft structures. Traditional methods often need more precision and efficiency for effective defect detection. This paper proposes an innovative approach that leverages deep learning and infrared imaging techniques to detect defects with high precision. The core contribution of our work lies in accurately detecting the size and depth of defects. Our method involves segmenting the size of the defect and calculating its centre to determine its depth. We achieve a more comprehensive and precise assessment of defects by integrating deep learning with infrared imaging based on the U-net model for segmentation and the CNN model for classification. The proposed model was rigorously tested on both a simulation dataset and an experimental dataset, demonstrating its robustness and effectiveness in accurately identifying and assessing defects on aerospace surfaces. The results indicate significant improvements in detection accuracy and computational efficiency, showing advancements over state-of-the-art methods and paving the way for enhanced maintenance protocols in the aerospace industry.