Filtern
Dokumenttyp
- Zeitschriftenartikel (9)
- Beitrag zu einem Tagungsband (9)
- Vortrag (5)
- Posterpräsentation (5)
- Sonstiges (3)
Schlagworte
- Super resolution (18)
- Laser thermography (16)
- Thermography (12)
- Joint sparsity (8)
- VCSEL array (7)
- Virtual wave (7)
- 1d laser (6)
- High-power laser (6)
- Laser array (6)
- NDT (5)
Organisationseinheit der BAM
Paper des Monats
- ja (1)
Eingeladener Vortrag
- nein (5)
This article presents deep unfolding neural networks to handle inverse problems in photothermal radiometry enabling super-resolution (SR) imaging. The photothermal SR approach is a well-known technique to overcome the spatial resolution limitation in photothermal imaging by extracting high-frequency spatial components based on the deconvolution with the thermal point spread function (PSF). However, stable deconvolution can only be achieved by using the sparse structure of defect patterns, which often requires tedious, handcrafted tuning of hyperparameters and results in computationally intensive algorithms. On this account, this article proposes Photothermal-SR-Net, which performs deconvolution by deep unfolding considering the underlying physics. Since defects appear sparsely in materials, our approach includes trained block-sparsity thresholding in each convolutional layer. This enables to super-resolve 2-D thermal images for nondestructive testing (NDT) with a substantially improved convergence rate compared to classic approaches. The performance of the proposed approach is evaluated on various deep unfolding and thresholding approaches. Furthermore, we explored how to increase the reconstruction quality and the computational performance. Thereby, it was found that the computing time for creating high-resolution images could be significantly reduced without decreasing the reconstruction quality by using pixel binning as a preprocessing step.
Learned block iterative shrinkage thresholding algorithm for photothermal super resolution imaging
(2022)
Block-sparse regularization is already well known in active thermal imaging and is used for multiple-measurement-based inverse problems. The main bottleneck of this method is the choice of regularization parameters which differs for each experiment. We show the benefits of using a learned block iterative shrinkage thresholding algorithm (LBISTA) that is able to learn the choice of regularization parameters, without the need to manually select them. In addition, LBISTA enables the determination of a suitable weight matrix to solve the underlying inverse problem. Therefore, in this paper we present LBISTA and compare it with state-of-the-art block iterative shrinkage thresholding using synthetically generated and experimental test data from active thermography for defect reconstruction. Our results show that the use of the learned block-sparse optimization approach provides smaller normalized mean square errors for a small fixed number of iterations. Thus, this allows us to improve the convergence speed and only needs a few iterations to generate accurate defect reconstruction in photothermal super-resolution imaging.
Thermographic photothermal super resolution reconstruction enables the resolution of internal defects/inhomogeneities below the classical limit, which is governed by the diffusion properties of thermal wave propagation. Based on a combination of the application of special sampling strategies and a subsequent numerical optimization step in post-processing, thermographic super resolution has already proven to be superior to standard thermographic methods in the detection of one-dimensional defect/inhomogeneity structures. In our work, we report an extension of the capabilities of the method for efficient detection and resolution of defect cross sections with fully two-dimensional structured laser-based heating. The reconstruction is carried out using one of two different algorithms that are proposed within this work. Both algorithms utilize the combination of several coherent measurements using convex optimization and exploit the sparse nature of defects/inhomogeneities as is typical for most nondestructive testing scenarios. Finally, the performance of each algorithm is rated on reconstruction quality and algorithmic complexity. The presented experimental approach is based on repeated spatially structured heating by a high power laser. As a result, a two-dimensional sparse defect/inhomogeneity map can be obtained. In addition, the obtained results are compared with those of conventional thermographic inspection methods that make use of homogeneous illumination. Due to the sparse nature of the reconstructed defect/inhomogeneity map, this comparison is performed qualitatively.
We combine three different approaches to greatly enhance the defect reconstruction ability of active thermographic testing. As experimental approach, laser-based structured illumination is performed in a step-wise manner. As an intermediate signal processing step, the virtual wave concept is used in order to effectively convert the notoriously difficult to solve diffusion-based inverse problem into a somewhat milder wavebased inverse problem. As a final step, a compressed-sensing based optimization procedure is applied which efficiently solves the inverse problem by making advantage of the joint sparsity of multiple blind measurements. To evaluate our proposed processing technique, we investigate an additively manufactured stainless steel sample with eight internal defects. The concerted super resolution approach is compared to conventional thermographic reconstruction techniques and shows an at least four times better spatial resolution.
This paper presents deep unfolding neural networks to handle inverse problems in photothermal radiometry enabling super resolution (SR) imaging. Photothermal imaging is a well-known technique in active thermography for nondestructive inspection of defects in materials such as metals or composites. A grand challenge of active thermography is to overcome the spatial resolution limitation imposed by heat diffusion in order to accurately resolve each defect. The photothermal SR approach enables to extract high-frequency spatial components based on the deconvolution with the thermal point spread function. However, stable deconvolution can only be achieved by using the sparse structure of defect patterns, which often requires tedious, hand-crafted tuning of hyperparameters and results in computationally intensive algorithms. On this account, Photothermal-SR-Net is proposed in this paper, which performs deconvolution by deep unfolding considering the underlying physics. This enables to super resolve 2D thermal images for nondestructive testing with a substantially improved convergence rate. Since defects appear sparsely in materials, Photothermal-SR-Net applies trained blocksparsity thresholding to the acquired thermal images in each convolutional layer. The performance of the proposed approach is evaluated and discussed using various deep unfolding and thresholding approaches applied to 2D thermal images. Subsequently, studies are conducted on how to increase the reconstruction quality and the computational performance of Photothermal-SR-Net is evaluated.
Thereby, it was found that the computing time for creating high-resolution images could be significantly reduced without decreasing the reconstruction quality by using pixel binning as a preprocessing step.
Classification of Spot-Welded Joints in Laser Thermography Data Using Convolutional Neural Networks
(2021)
Spot welding is a crucial process step in various industries. However, classification of spot welding quality is still a tedious process due to the complexity and sensitivity of the test material, which drain conventional approaches to its limits. In this article, we propose an approach for quality inspection of spot weldings using images from laser thermography data. We propose data preparation approaches based on the underlying physics of spot-welded joints, heated with pulsed laser thermography by analyzing the intensity over time and derive dedicated data filters to generate training datasets. Subsequently, we utilize convolutional neural networks to classify weld quality and compare the performance of different models against each other. We achieve competitive results in terms of classifying the different welding quality classes compared to traditional approaches, reaching an accuracy of more than 95 percent. Finally, we explore the effect of different augmentation methods.
Die thermografische ZfP basiert auf der Wechselwirkung von thermischen Wellen mit Inhomogenitäten. Die Ausbreitung von thermischen Wellen von der Wärmequelle zur Inhomogenität und zur Detektionsoberfläche entsprechend der thermischen Diffusionsgleichung führt dazu, dass zwei eng beieinander liegende Defekte fälschlicherweise als ein Defekt im gemessenen Thermogramm erkannt werden können. Um diese räumliche Auflösungsgrenze zu durchbrechen, also eine Super Resolution zu realisieren, kann die Kombination von räumlich strukturierter Erwärmung und numerischen Verfahren des Compressed Sensings verwendet werden.
Für unsere Arbeiten benutzen wir Hochleistungs-Laser im Kilowatt-Bereich um die Probe entweder hochaufgelöst entlang einer Linie (1D) abzurastern oder strukturiert zu erwärmen. Die Verbesserung des räumlichen Auflösungsvermögens zur Defekterkennung hängt dann im klassischen Sinne direkt von der Anzahl der Messungen ab. Mithilfe des Compressed Sensings und Vorkenntnissen über das System ist es jedoch möglich die Anzahl der Messungen zu reduzieren und trotzdem Super Resolution zu erzielen. Wie viele Messungen notwendig sind und wie groß der Auflösungsgewinn gegenüber der konventionellen thermografischen Prüfung mit flächiger Erwärmung ist, hängt von einer Reihe von Messparametern, der Messstrategie, Probeneigenschaften und den verwendeten Rekonstruktionsalgorithmen ab.
Unsere Studien befassen sich mit dem Einfluss der experimentellen Parameter, wie z.B. der Pulslänge der Laserbeleuchtung und der Größe des Laserspots. Weiterhin haben wir uns mit der Wahl der Parameter in der Rekonstruktion auseinandergesetzt, die einen Einfluss auf das im Compressed Sensing zugrundeliegende Minimierungsproblem haben. Für jeden getesteten Parametersatz wurde eine Rekonstruktionsqualität berechnet. Schließlich wurden die Defektrekonstruktionen basierend auf den Parameternsätzen verglichen, sodass eine Parameterwahl für hohe Rekonstruktionsqualitäten mit thermografischer Super Resolution empfohlen werden kann.
The work to be presented focuses on our most recent studies to laser excited super resolution (SR) thermography. The goal of nondestructive testing with SR is to facilitate the separation of closely spaced defects. Photothermal SR can be realized by performing structured illumination measurements in com-bination with the use of deconvolution algorithms in post-processing. We explain that stepwise as well as continuous scanning techniques are applicable to generate structured illumination measurements. Finally, we discuss the effect of experimental parameters and image processing techniques to find the optimal SR technique which leads to the highest reconstruction quality within laser thermography.
Thermographic super-resolution techniques allow the resolution of defects/inhomogeneities beyond the classical limit, which is governed by the diffusion properties of thermal wave propagation. Photothermal super-resolution is based on a combination of an experimental scanning strategy and a numerical optimization which has been proven to be superior to standard thermographic methods in the case of 1D linear defects. In this contribution, we report on the extension of this approach towards a full frame 2D photothermal super-resolution technique. The experimental approach is based on a repeated spatially structured heating using high power lasers. In a second post-processing step, several measurements are coherently combined using mathematical optimization and taking advantage of the (joint) sparsity of the defects in the sample. In our work we extend the possibilities of the method to efficiently detect and resolve defect cross sections with a fully 2D-structured blind illumination.
Active thermography as a nondestructive testing modality suffers greatly from the limitations imposed by the diffusive nature of heat conduction in solids. As a rule of thumb, the detection and resolution of internal defects/inhomogeneities is limited to a defect depth to defect size ratio greater than or equal to one. Earlier, we demonstrated that this classical limit can be overcome for 1D and 2D defect geometries by using photothermal laser-scanning super resolution. In this work we report a new experimental approach using 2D spatially structured illumination patterns in conjunction with compressed sensing and computational imaging methods to significantly decrease the experimental complexity and make the method viable for investigating larger regions of interest.