Characterisation of crack geometry via inductive thermography and machine learning Alexey Moskovchenko, Michal Švantner, Christoph Tuschl, Beate Oswald-Tranta Quantitative Infrared Thermography Journal, 2026 Inductive thermography provides a non-destructive approach for detecting and characterising cracks in metallic components. This study introduces a method to assess crack geometry – depth and inclination angle – by combining inductive thermography with machine learning. Thermographic sequences from inductively heated cracked specimens were processed using various techniques, including the Fourier transform, to generate phase images. A comparative analysis revealed that the fast Fourier transform (FFT) outperformed other methods, achieving the highest contrast-to-noise ratio (CNR) and effectively suppressing non-uniform heating effects. Phase profiles perpendicular to the crack, extracted at its midpoint, were used as input features. Two machine learning models were developed: one trained on simulated phase profiles to predict crack inclination angle, and a second to estimate crack depth based on the known angle and phase data. Validated against simulated datasets, the models demonstrated high accuracy, advancing the quantitative evaluation of crack geometry for structural integrity and predictive maintenance applications.
CRACK ANGLE ESTIMATION WITH INDUCTION THERMOGRAPHY AND MACHINE LEARNING Alexey MOSKOVCHENKO, Michal ŠVANTNER Metal International Conference on Metallurgy and Materials Conference Proceedings, 2025 Induction thermography is a well-established method for detecting and analysing cracks in metal products, such as rails.However, quantifying defects, particularly those with complex geometries, remains a challenging and intricate task.This paper addresses one critical aspect of defect quantification: the determination of crack inclination angles, which is essential for accurate depth estimation and hazard level assessment.We propose a novel approach that combines induction thermography data analysis with machine learning regression models to estimate crack angles.The regression model is trained on a dataset generated through numerical simulations, ensuring robust and reliable performance.The effectiveness of the proposed method is demonstrated through both numerical and experimental results, showcasing its potential for improving crack characterization in industrial applications.This work advances the field of non-destructive testing by providing a more precise and automated solution for crack inclination angle determination, contributing to enhanced structural integrity assessments.
FLASH-PULSE THERMOGRAPHY EVALUATION OF COLD SPRAY 316L STEEL COATINGS Alexey MOSKOVCHENKO, Michal ŠVANTNER, Marek VOSTŘÁK, Žaneta DLOUHÁ, Šárka HOUDKOVÁ Metal International Conference on Metallurgy and Materials Conference Proceedings, 2025 This study investigates the application of infrared (IR) thermography for evaluating thermal-sprayed coatings, focusing on distinguishing coatings subjected to different thermal treatments and varying porosity levels.Experimental thermographic analysis demonstrated the capability of IR thermography to differentiate between coating variants.The Fourier transform method and phase analysis at low frequencies proved remarkably effective.This approach enabled the visualization of areas with differing thicknesses in the thermographic images and facilitated detailed analysis through phase-frequency plots.The results highlight the potential of IR thermography as a powerful, non-destructive tool for characterizing thermal-sprayed coatings, offering insights into their structural and thermal properties.This method holds promise for quality control and optimization in industrial applications involving thermal spray processes.
Data processing methods for thermographic NDT with localised cryogenic cooling Alexey Moskovchenko, Giuseppe Dell’Avvocato, Michal Švantner, Fabrizio Sarasini, Stefano Sfarra Nondestructive Testing and Evaluation, 2025 Infrared thermographic non-destructive testing (NDT) is an effective technique for detecting defects in composite materials, particularly when paired with active thermal stimulation. This study investigates the use of localised cryogenic cooling as an alternative stimulation source in infrared thermographic NDT of fibre-reinforced polymer (FRP) composites. A low-cost handheld cryosurgical device (Histofreezer) was used to deliver precise, repeatable cooling, generating distinct thermal gradients recorded by a micro-bolometric camera. While localised cooling offers unique advantages, its strong non-uniformity complicates data processing and interpretation. This work focuses on identifying effective techniques for defect detection under such conditions. Experiments on carbon fibre reinforced polymer (CFRP) specimens impacted at ambient and cryogenic temperatures used contrast-to-noise ratio (CNR) as the performance metric. Wavelet transforms and polynomial background subtraction proved most effective in isolating defect signals; the former excelled when defect and cooling signals overlapped, while the latter worked best when cooling occurred away from defects. Combining polynomial background subtraction with principal component analysis (PCA) further improved contrast and segmentation quality. Localised cooling demonstrates strong potential as a precise, controllable, and low-cost stimulation method for thermographic NDT, supporting the development of portable and operator-safe field inspection systems.
Enhancing generalizability of a machine learning model for infrared thermographic defect detection by using 3d numerical modeling Vladimir Vavilov, Arsenii Chulkov, Alexey Moskovchenko Frattura Ed Integrita Strutturale, 2024 The paper describes the implementation of 3D numerical simulation in machine learning models used in infrared thermographic nondestructive testing. The enhancement of generalizability of such models emerges as a decisive factor for producing trust-worthy test results. First, it is demonstrated that the models trained on datasets with fixed parameters yield limited defect detection capabilities. The concept of training datasets, which include subtle variations in material thickness, thermal conductivity, as well as various combinations of material density and heat capacity, provides the best learning results and a noticeable ability to identify defects in all test datasets. Second, the model robustness in respect to noise is explored to demonstrate its ability to withstand additive and multiplicative random noise. Third, potentials of some known techniques of thermographic data processing, such as Thermographic Signal Reconstruction, Fast Fourier Transform and Temperature Contrast, are examined. In particular, the use of the Temperature Contrast data ensured sensitivity (True Positive Rate) better than 98% across all test datasets.
APPLICABILITY OF NDT METHODS FOR THE DETECTION OF TYPICAL DEFECTS IN SELECTIVE LASER MELTING PARTS Alexey MOSKOVCHENKO, Michal ŠVANTNER, Šárka HOUDKOVÁ Metal International Conference on Metallurgy and Materials Conference Proceedings, 2024 Nondestructive testing is an important part of any production process that is required to ensure the quality of materials and parts.The development of reliable nondestructive testing (NDT) methods applicable to novel materials and manufacturing processes such as additive manufacturing is a challenging task because of the complex geometry and anisotropic material properties.The majority of review publications related to the NDT methods in the additive manufacturing process are focused on only one aspect: either the defect classification or NDT methods and quality control systems.In this study, various NDT methods such as X-ray testing, acoustic emission, IR thermography, etc. were analyzed from the point of view of an application for selective laser melting (SLM, one of the most common additive manufacturing processes of metal parts).Typical defects appearing in SLM parts were classified and matched with NDT methods able to detect them.Recommendations on the use of different methods for in-situ process monitoring and printed parts inspection are given.
EFFECT OF ANTI-CORROSION PROTECTIVE PAINT ON THERMOGRAPHIC INSPECTION OF CURVED STEEL TUBE PARTS Michal ŠVANTNER, Alexey MOSKOVCHENKO, Lukáš MUZIKA Metal International Conference on Metallurgy and Materials Conference Proceedings, 2024 The use of anti-corrosion paint coatings on steel pipes is a common practice for their protection against corrosion. However, such coatings may have an impact on the results of the thermographic inspection, which can be used, for example, for their corrosion damage identification. In this study, we investigated the influence of anti-corrosion paint on the thermographic inspection of curved steel tube parts. Long pulse thermography inspection was conducted on painted and unpainted samples, and the results were compared. It was found that the used painting reduced the absorbed energy, however, the contrast of the found defect indications was better on painted samples. The experiments indicated that any inhomogeneity of an inspected surface due to, for example, the painting process, the presence of old painting layers, or the presence of surface corrosion, can cause irregular surface absorption patterns. It can result in signals from this unevenness that can reduce the contrast of the indications of defects. These findings can have significant implications for the use of thermography as a non-destructive testing technique for curved steel tube parts, for example, steel pipes, especially those in operation with correction paint or corrosion layers.
