Kevin Helvig, Pauline Trouvé-Peloux, Ludovic Gaverina, Baptiste Abeloos, Jean-Michel Roche
{"title":"Automated crack detection on metallic materials with flying-spot thermography using deep learning and progressive training","authors":"Kevin Helvig, Pauline Trouvé-Peloux, Ludovic Gaverina, Baptiste Abeloos, Jean-Michel Roche","doi":"10.1080/17686733.2023.2266176","DOIUrl":"https://doi.org/10.1080/17686733.2023.2266176","url":null,"abstract":"ABSTRACTIn non-destructive testing for metallic materials, ‘Flying-spot’ thermography allows the detection of cracks thanks to the scanning of samples by a local laser heat source observed in the infrared spectrum. However, distinguishing a crack from other surface structures such as air ducts or non-planar shapes on the material surface can be challenging in an automation perspective. To address this, we propose to use deep learning techniques, which can exploit contextual information but require a significant amount of labelled data. This study presents a training method based on curriculum learning and recent denoising diffusion models to generate synthetic images. The protocol progressively increases the complexity of training images, using successively simulated data from a multi-physics finite-element software, synthetically generated data with diffusion process, and finally real data. Several detection scores are measured for various machine learning and deep learning architectures, demonstrating the benefits of the proposed approach for regular application cases and degraded experimental conditions, consisting of limited thermal enlightenment recordings.KEYWORDS: Non-destructive testingflying-spot thermographydeep learningcurriculum learningdenoising diffusion models Disclosure statementNo potential conflict of interest was reported by the author(s).Additional informationFundingThe work was supported by the Agence de l’innovation de Défense.Notes on contributorsKevin HelvigKevin Helvig is a Ph.D. student currently doing research at ONERA Palaiseau in France. His work is dedicated to the application of computer vision techniques to laser thermography for non-destructive materials testing, in particular exploring the coupling between active IR and visible spectrum examinations. He is graduated with an engineering degree from IMT Mines Albi, specializing in non-destructive testing and materials.Pauline Trouvé-PelouxPauline Trouvé-Peloux after completing her engineering training in optics at the Institut d'Optique Graduate School, Pauline Trouvé-Peloux obtained her doctorate in Information and Mathematics Science and Technologies from the Ecole Centrale de Nantes in 2012, specializing in signal and image processing. Since 2012, she has held the position of research engineer at ONERA, within the Information Processing and Systems Department (DTIS). Her research activities focus on the joint design, or co-design, of an imager through joint optimization approaches of its optics and processing parameters. The application areas of her work particularly concern compact 3D sensors for robotics or industrial inspection.Ludovic GaverinaLudovic Gaverina graduated with an engineering degree from Telecom Saint-Etienne and a master of research in optic, image, and computer vision from Jean Monnet University in 2013. In 2017, he received the PhD degree (title of his thesis: “Thermal characterization of heterogeneous material by flying spot laser and infrar","PeriodicalId":20889,"journal":{"name":"Quantitative InfraRed Thermography","volume":"191 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135730100","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sergey Lugin, David Müller, Michael Finckbohner, Udo Netzelmann
{"title":"Automated surface defect detection in forged parts by inductively excited thermography and magnetic particle inspection","authors":"Sergey Lugin, David Müller, Michael Finckbohner, Udo Netzelmann","doi":"10.1080/17686733.2023.2266901","DOIUrl":"https://doi.org/10.1080/17686733.2023.2266901","url":null,"abstract":"Inductively excited thermography has been shown to detect cracks in metallic components with good sensitivity. It is discussed as an alternative to magnetic particle testing. An open question to achieve acceptance in the industry is its testing reliability. A study with in total 200 forged steel parts was performed in order to compare the testing reliability of automated inductively thermographic testing and magnetic particle inspection. A robot supported thermographic inspection station was used. An inductor with orientation-independent crack detection was built up and tested. The thermographic phase images obtained were analysed by an automatic defect detection procedure based on machine learning techniques. Results of magnetic particle inspection served as a reference. Depending on the type of test object, an agreement of 68% to 82% was achieved, if only large indications of thermography were considered. The weak thermographic indications turned out to be due to shallow cracks (<150 µm depth). Improvement of the testing speed can be achieved by inspection inside large coils.","PeriodicalId":20889,"journal":{"name":"Quantitative InfraRed Thermography","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135351951","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jan Verstockt, Ruben Somers, Filip Thiessen, Isabelle Hoorens, Lieve Brochez, Gunther Steenackers
{"title":"Finite element skin models as additional data for dynamic infrared thermography on skin lesions","authors":"Jan Verstockt, Ruben Somers, Filip Thiessen, Isabelle Hoorens, Lieve Brochez, Gunther Steenackers","doi":"10.1080/17686733.2023.2256998","DOIUrl":"https://doi.org/10.1080/17686733.2023.2256998","url":null,"abstract":"ABSTRACTSkin cancer is a significant global health concern, with increasing incidence rates and a high number of deaths each year. Early detection plays a crucial role in improving survival rates, but current screening methods, such as total body skin examination, often lead to unnecessary invasive excisions. This research aims to explore the use of dynamic infrared thermography (DIRT) in combination with other technologies to potentially eliminate the need for biopsies in the future and gather information about the stage or depth of malignant skin lesions. The study involves data acquisition using a thermal camera and a finite element skin model. The FEM skin model employed in this research follows the commonly used five-layer model and is constructed in Siemens Simcenter 3D to be able to simulate the cryogenic cooling on the skin. It is possible to improve the thermal images by choosing an appropriate cooling method, cooling sequence and optimised measurement setup. While the FEM skin model shares certain similarities with the measurement data, there is room for further enhancements to optimise its performance. The acquired data is analysed to assess the effectiveness of the combined technique compared to existing clinical and diagnostic methods.KEYWORDS: Finite element modelskin cancerdynamic infrared thermographydata augmentationFEMPennes Disclosure statementNo potential conflict of interest was reported by the author(s).Additional informationFundingThis research is funded by the Research Foundation-Flanders via support for the FWO research project, “Optimized skin tissue identification by combined thermal and hyperspectral imaging methodology”. (Project number 41882 [FWO G0A9720N] Jan Verstockt).Notes on contributorsJan VerstocktJan Verstockt graduated Magna cum laude in 2016 from Ghent University, Belgium, he earned his Master of Science in Electromechanical Engineering Technology. In 2019, his pursuit of knowledge led him to Halmstad University in Sweden, where he achieved a Master of Science in Mechanical Engineering, a remarkable accomplishment crowned with the prestigious Student of the Year award for the 2018-2019 academic year. Following these academic triumphs, Jan embarked on a career at the University of Antwerp, Belgium, where he commenced as an assistant lecturer, eager to share his expertise and passion for the subject matter. In 2020, his journey reached a pivotal milestone as he embarked on a groundbreaking Ph.D. endeavor, titled ”Thermal Measurement and Numerical Modelling Methodology for Skin Pathology Screening.”Ruben SomersRuben Somers graduated in 2022 from the University of Antwerp with a Master of Science in Electromechanical Engineering Technology. His master thesis was on the subject of finite element modelling of human skin in combination with thermography. He currently works as a mechanical engineer and designer in various industries such as food, (bio-) pharma and industrial applications.Filip ThiessenFilip Thiesse","PeriodicalId":20889,"journal":{"name":"Quantitative InfraRed Thermography","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135396430","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}