Filtern
Dokumenttyp
- Vortrag (7)
- Beitrag zu einem Tagungsband (4)
- Zeitschriftenartikel (3)
- Posterpräsentation (2)
- Preprint (1)
Schlagworte
- Infrared Thermography (7)
- Laser (5)
- Deep Learning (4)
- Infrared thermography (4)
- NDE 4.0 (4)
- Non-destructive testing (4)
- Infrared imaging (2)
- Multispectral imaging (2)
- NDT (2)
- Non-destructive Evaluation (NDE) (2)
Organisationseinheit der BAM
Eingeladener Vortrag (wissenschaftliche Konferenzen)
- nein (7)
Die Integration von Automation und Robotik in die Prüfprozesse ermöglicht die
Untersuchung komplexer Bauteile. Diese Studie präsentiert die robotergestützte
Laserthermografie, um Risse in solchen Bauteilen zu identifizieren und analysieren. Diese Technik ermöglicht die automatisierte Rissprüfung welche im Vergleich zur Farbeindringprüfung auf viele, meist manuelle, Arbeitsschritte sowie die notwendigen Chemikalien verzichtet.
Zusätzlich wird ein automatisiertes Einscannen der Bauteile mithilfe eines
Linienscanners vorgestellt. Dieser Schritt ermöglicht eine detaillierte 3D-Rekonstruktion der Bauteilgeometrie und ermöglicht eine einfache Korrektur von Abweichungen in der Bauteilaufnahme und eröffnet Möglichkeiten zur adaptiven Bahnplanung bei Bauteilverformungen.
Die Rückprojektion der gefundenen Risse auf die Oberfläche des Bauteils kann
automatisiert erfolgen. Dieser Schritt erlaubt nicht nur die Identifikation der Risse, sondern auch eine genauere Analyse ihrer Geometrie und Lage am Bauteil.
Die Kombination von robotergestützter Laserthermografie, automatisiertem 3DScanning und Rückprojektion der Risse auf die Bauteiloberfläche eröffnet neue
Möglichkeiten in der zerstörungsfreien Prüfung von komplexen Bauteilen und erweitert damit mögliche Anwendungsfelder.
In this study, an age prediction model is developed for the real serviced thermal barrier coated (TBC) samples. TBC is a multilayer coating applied on metallic structures exposed to high temperatures, such as gas turbine blades and aeroengine parts, to extend the operational life. One of the main challenges for developing an age prediction model is the unavailability of serviced samples and labelled datasets. So, in this study, experimentally validated numerical models are used for data generation. The study considers samples with three different service times, i.e., 0 (newly coated), 500 hours, and 1000 hours. The age prediction is done in two stages: thermal diffusivity prediction for blind real serviced samples with a trained 1D-CNN model and classification of samples based on the service hours into different classes using AI classification models. The results demonstrate that our approach provides reliable age estimations with a high correlation between actual and predicted ages of samples. This method provides a non-destructive, efficient, and accurate method of evaluating the life of TBCs, which is a substantial improvement over traditional techniques that rely on complex destructive methods or microstructural analysis for the age evaluation.
Development of reliable age prediction models are crucial in monitoring the formation of oxide layer and degradation of TBC at regular intervals. This study proposes an automated classification of isothermal heat-treated TBC samples using temperature data, which helps in predicting the TBC life and monitoring the TBC degradation. TBC-coated samples are isothermal heat-treated at 1000 °C, and the initial growth of thermally grown oxide is monitored using a non-destructive thermal imaging technique. The proposed study integrates data-driven AI (DAI) models and feature extraction techniques to interpret complex thermal patterns measured from the TBC coating surface. The performance of the proposed classification framework is tested using deep learning and classical machine learning models with different types and window sizes of input data. Input data used for validation are raw experiment data, logarithmic of experiment data, polynomial fit data, and thermal signal reconstruction fit coefficients. The maximum c
Thermal Barrier Coatings (TBCs) are critical components in high-temperature applications, such as gas turbines and aerospace engines, where they protect the underlying substrate metals from extreme thermal stress and extend component life. Accurate evaluation of TBCs is essential to improve operational efficiency, optimize predictive maintenance strategies, and extend component life. Popular non-destructive evaluation (NDE) techniques such as infrared thermography (IRT) and terahertz (THz) imaging have been widely used for TBC inspection with limitations when used independently, including sensitivity to surface conditions, limited penetration depth, and challenges in inspecting multi-layer coatings and detecting subsurface defects. To address these challenges, our study proposes a novel framework called simulation-assisted multimodal deep learning (Sim-MDL) that integrates the strengths of IRT and THz imaging for a comprehensive evaluation of TBCs. To generalize the study to a range of thermophysical properties of TBCs, the study uses simulation-generated data along with experimental data for training deep learning models. The data from IRT and THz modalities are fused in the Sim-MDL models to enable characterization of the TBC topcoat layer. IRT and THz experimental data, together with simulations, form a large dataset that is used to train deep learning models. The framework is tested and optimized for multimodal data fusion using two DL architectures based on convolutional neural networks (CNN) and long short-term memory (LSTM), allowing the model to learn correlations and complex patterns across the IRT and THz modalities. The study is conducted on four newly coated samples ranging in thickness from 24 to 120 µm. An attention-based LSTM model trained on both simulation and experimental data shows high prediction accuracy with MAPE values ranging from 2.06–4.43% for thermal conductivity, 2.05–3.57% for heat capacity, 11.53–1.75% for topcoat thickness, and 0.27–1.05% for refractive index, respectively, for the topcoat layers of four samples. Our model outperformed the single-modality models and conventional parameter estimation methods in terms of accuracy and robustness, highlighting the potential of multimodal data for automated analysis of TBC in industrial settings.
Active thermographic testing is a versatile and powerful method of the non-destructive testing (NDT) family. With the advent of modern laser technology, new and significant fields of application have emerged. When combined with industrial robotics, laser thermography enables fully automated, large-area inspection of components with complex geometries for surface and near-surface cracks. This lecture will provide an overview of the fundamental principles of laser thermography, highlight recent developments and automation efforts within our department for thermographic surface-crack detection, and present an outlook on emerging research trends and modern thermography techniques shaping the future of NDT.
Infrared thermography is a widely recognized non-destructive testing (NDT) method used in material research and defect detection across various industrial applications. Moreover, thermography plays a crucial role in preserving cultural heritage, including historical paintings and buildings. This study focuses on the application of thermography in inspecting the historic Bücker Bü 181 aircraft, which was used in Germany during World War II. Over time, the original appearance of aircraft has often been altered as part of preservation efforts, either before or during their time in museums, leading to deviations from their historically original state. Additionally, the operational history of such objects is frequently undocumented or entirely lost, making it difficult to understand the presence of artifacts and historically significant data. These factors present major challenges in cultural heritage preservation, and destructive methods cannot be used to investigate such invaluable objects.
Therefore, thermography is implemented as a non-destructive and contactless examination method. Active flash thermography combined with phase analysis is a powerful tool for evaluating multilayer systems. In this study, multiple layers of old paint on the object posed a challenge in assessing defect conditions and retrieving other critical information beneath the surface coatings. Nevertheless, pulse thermography not only demonstrated its capability to identify defects and markings in multilayered coatings but also provided insights into the internal structure and subsections of the investigated aircraft.
Crack detection and segmentation in complex components are critical for maintaining the structural integrity and reliability of systems operating under extreme conditions, such as turbine blades in energy and aerospace applications. The integration of automated multimodal imaging-based non-destructive testing (NDT) with deep learning provides a promising path towards precise and automated defect characterization. In this study, a hybrid multimodal deep learning framework is proposed, combining the advantages of an unsupervised generative adversarial network (GAN) and a supervised U-Net segmentation model for comprehensive crack detection and quantification. The unsupervised multimodal GAN performs data fusion by integrating complementary features from high-resolution thermal and RGB images acquired using a robot-assisted flying laser-line thermography system. This data fusion improves the contrast and representation of surface and sub-surface cracks by leveraging spectral features across multiple imaging modalities. The GAN is trained to reconstruct crack free images and difference between the generated image and real crack image generates an error map that highlights the cracks. The unsupervised approach helps in reducing the need for manual labeled data and generalizes well across different surface conditions. The error maps from GAN are subsequently processed by a U-Net-based segmentation model trained on labeled datasets to achieve precise pixel-level crack localization and morphological estimation. The use of laser thermography induces localized heating on the component surface, providing transient thermal responses that make subtle cracks and defects visible beyond the limits of visual imaging. Experimental validation demonstrates that the proposed hybrid GAN–U-Net framework achieves significantly improved crack detection accuracy and segmentation performance compared to single modal NDE imaging, and data processing based on traditional threshold-based methods. This work underscores the potential of combining unsupervised multimodal fusion with supervised image segmentation to establish a new framework that helps in building automated, data-driven, and robot-assisted NDT systems for intelligent inspection and structural health monitoring of industrial components.
Robotic-Assisted 3D Scanning and Laser Thermography for Crack Inspection on Complex Components
(2024)
The integration of automation and robotics into non-destructive testing (NDT) marks a significant advancement in evaluating complex components. This paper introduces a novel approach using robotic-assisted laser thermography combined with automated 3D scanning to detect and analyze cracks in complex structures. The system uses an integrated line scanner with a robotic arm to capture high-resolution data, creating detailed 3D models for adaptive path planning and precise alignment correction. Laser thermography, based on localized heating and the "flying spot" approach, detects surfacenear cracks with high precision. Crack detection is achieved using the Canny algorithm optional on Fourier-transformed thermograms, offering robust results with minimal computation. This study highlights the potential of robotic-assisted 3D scanning and laser thermography as efficient and precise methods for crack inspection, advancing NDT technologies and ensuring the structural integrity of modern components.
Thermal Barrier Coatings (TBCs) are critical for high-temperature applications, such as gas turbines and aerospace engines, protecting metallic substrates from extreme thermal stress and degradation. Accurate evaluation of TBCs is essential to improve operational efficiency, optimize predictive maintenance strategies, and extend component life. Conventional non-destructive evaluation (NDE) techniques such as infrared thermography (IRT) and terahertz (THz) imaging have been widely used for TBC inspection with limitations when used independently, including sensitivity to surface conditions, limited penetration depth mainly in multi-layer coatings. This study proposes a novel framework called simulation-assisted multimodal deep learning (Sim-MDL) that combines IRT and THz data for a comprehensive evaluation of TBCs. To generalize the study to varying thermophysical properties of TBCs, the study uses simulation-generated data along with experimental data for training deep learning models. Two deep learning frameworks based on a 1D convolutional neural networks (CNN) and a long short-term memory (LSTM) with attention were developed for the multimodal feature fusion. The IR-THz fused frameworks enable simultaneous prediction of key TBC topcoat properties including thermal conductivity, heat capacity, topcoat thickness and refractive index. Experiments were conducted on four newly coated samples topcoat thicknesses ranging from 24 to 120 μm. An attention-based LSTM model trained on both simulation and experimental data shows high prediction accuracy with MAPE values ranging from 2.06% to 4.43% for thermal conductivity, 2.05% to 3.57% for heat capacity, 11.53% to 1.75% for topcoat thickness, and 0.27% to 1.05% for refractive index, respectively, for the topcoat layers of four samples. The proposed Sim-MDL framework outperformed single-modality and conventional parameter estimation methods in accuracy and robustness, highlighting the potential of multimodal data for automated analysis of TBC in industrial settings.
Anisotropy investigation of a single crystal superalloy using laser-spot infrared thermography
(2024)
Thermal property investigation of anisotropic materials such as single crystal superalloys are still in interest of practical and fundamental reasons but remains challenging using conventional testing methods. In this study, a single crystal superalloy is tested using laser-spot thermography, and its thermal anisotropy is investigated. Determining anisotropic thermal conductivity at microscopic scales is challenging, as it appears isotropic at the macroscopic scale. Infrared thermography is one of the best-known techniques for measuring material heat transfer properties and facilitating visualization of temperature distribution through the specimen. The proposed study uses the active thermography method of laser-spot infrared thermography, in which a laser spot is focused onto the sample surface and the thermal response is captured from the surface of the specimen with an infrared camera. A detailed analysis of temperature gradients and heat diffusion patterns aids in the measurement of thermal conductivity values along the sample's different crystallographic directions. The directional bonding characteristics and inherent crystallographic structure of the alloy account for the in-plane thermal conductivities calculated from experimental thermal measurements. The laser-spot thermography method has proven to be an effective tool for mapping the material's thermal conductivity anisotropy with high sensitivity and high spatial and temporal resolution. The investigation into the anisotropy of the material provides an insight into heat flow in the structure and helps in optimizing the design and overall performance of the material system.
