[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125232-en":3,"doc-seo-125232-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},125232,1099514067438,"River Wang","https://ap-avatar.wpscdn.com/avatar/100002539ee87300030?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780474512215547542",8,"Research & Report","A Machine Learning Approach to Ultrasonic Testing Signal Degradation - Project Overview","Ultrasonic testing (UT) enables non-destructive measurement of cladding thickness and bonding using high-frequency ultrasonic waves, but immersion in water disperses high frequencies and degrades scan signals. Different fuel types further affect how reliable measurements are obtained, especially when signals are missing or corrupted in nuclear research reactor fuel plate inspections. This project uses multiple machine learning models to reconstruct degraded scans from neighboring successful ones, aiming to reduce nuisance detections while preserving sensitivity for long-term preprocessing and analysis in non-destructive testing workflows.","A Machine Learning Approach to Ultrasonic Testing Signal Degradation  \nAbigail Brown, Joshua Suetterlein, Jodi Fasteen, Theodore Wendt, Shaye Bodine, Irvin Lopez-Audetat, Michael Catalan  \nSeptember 10th, 2024  \n2  \nAbstract  \nUltrasonic testing (UT) is a form of non-destructive testing used within many disciplines of research and product inspection. This includes the fabrication of research and test reactor fuels. These scans utilize high frequency ultrasonic waves to take measurements to detect cladding thickness and bonding. Generally, the higher the frequency, the greater the precision and resolution, often at the cost of increased noise and artifact detection. However, since the material being scanned must be submerged underwater, high level frequencies get dispersed upon contact with the water, thus degrading the signal. Unique challenges are posed by different fuel types, inspection of a monolithic fuel is different than a dispersion fuel. A solution has been researched to solve signal issues found in UT scans of nuclear research reactor fuel plates. The goal of this project is to look at scans where the signal was missing or degraded and reconstruct it based on neighboring successful scans utilizing various machine learning (ML) models. Longer term, the work is anticipated to reduce nuisance detections (i.e. sharp edges, impurities, or noise induced) while maintaining sensitivity to cladding thickness and bonding. This project is still underdevelopment, but upon completion will be helpful for long-term data preprocessing and analysis, along with aiding in various non-destructive testing analyses.  \n1. Introduction  \nUltrasonic testing (UT) is a method of non-destructive testing. UT is extremely useful for measuring the thicknesses of the layers of material without destroying the material being tested. UT is used in many different industries to test materials, a few of which include the marine oil industry, automotive industry, aerospace industry, and the construction industry 1. Each of these industries depend upon their materials being of topquality to ensure efficient operations. However, there are many use cases where destruction of materials for testing is not a viable (or efficient) option: underwater oil rigs, active pipelines, and, in our case, nuclear research reactor fuel plates. Fuel plates consist of a metal cladding exterior surrounding a fuel meat interior. The contents of these fuel plates should not undergo destructive testing measures, thus non-destructive testing technologies are highly beneficial to ensure the thickness of materials within are within quality assurance guidelines.  \nNon-destructive testing is also a preferred version of testing when material waste is of major concern. Destructive testing (DT) requires manipulating the material to ensure quality, including cutting up material, bending material, using strong pressure against the material, along with other destructive techniques. This causes a large amount of material waste as DT often renders the tested material useless. With fuel plates, it’s not possible to cause this waste, making DT an unviable form of testing.  \n1 OnestopNDT,“A Materials Guide to Ultrasonic Testing Applications,” OnestopNDT, August 28, 2021, [https://www.onestopndt.com/ndt-articles/materials-guide-ultrasonic-testing-applications](https://www.onestopndt.com/ndt-articles/materials-guide-ultrasonic-testing-applications).  \n3  \nThis being said, non-destructive testing is not always perfect. A couple major issues are presented with immersive UT scans of research reactor fuel plates: water versus probe frequency and the smoothness of material being scanned.  \nImmersive UT requires that the material being scanned is submerged under water. This is so the variability of coupling quality, which is the quality of the connections between the probe and the material, is reduced2. Because of this, however, there is a need for critical fine tuning of the frequency of the wave emitt","cbCaikeUd4rC9BWp","https://ap.wps.com/l/cbCaikeUd4rC9BWp","pdf",2414001,1,24,"English","en",105,"# Abstract\n# Introduction\n## Motivation: Non-destructive needs\n## Key challenges in immersive UT\n## Frequency effects and water dispersion\n## Surface roughness effects\n## Risk: misclassification and false defects\n## Proposed solution: ML-based reconstruction","[{\"question\":\"Why does immersive ultrasonic testing degrade UT signals?\",\"answer\":\"Immersive UT requires submerging the scanned material in water. High-frequency waves disperse after contacting the water, and the reflected-signal timing becomes difficult to detect because it is buried in dispersion noise.\"},{\"question\":\"How do different fuel types impact the inspection process?\",\"answer\":\"The document notes that a monolithic fuel behaves differently from a dispersion fuel during UT scanning, introducing unique signal-analysis challenges depending on fuel type.\"},{\"question\":\"What is the goal of the machine learning approach in this project?\",\"answer\":\"The project targets UT scans where the signal is missing or degraded, reconstructing the signal using neighboring successful scans via various ML models. The expected outcome is fewer nuisance detections while maintaining sensitivity for thickness analysis and defect classification.\"}]","A Machine Learning Approach to Ultrasonic Testing Signal Degradation - Project Overview | PDF",1785897633,60,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"a-machine-learning-approach-to-ultrasonic-testing-signal-degradation-project-overview","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/a-machine-learning-approach-to-ultrasonic-testing-signal-degradation-project-overview/125232/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why does immersive ultrasonic testing degrade UT signals?","Question",{"text":75,"@type":76},"Immersive UT requires submerging the scanned material in water. High-frequency waves disperse after contacting the water, and the reflected-signal timing becomes difficult to detect because it is buried in dispersion noise.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How do different fuel types impact the inspection process?",{"text":80,"@type":76},"The document notes that a monolithic fuel behaves differently from a dispersion fuel during UT scanning, introducing unique signal-analysis challenges depending on fuel type.",{"name":82,"@type":73,"acceptedAnswer":83},"What is the goal of the machine learning approach in this project?",{"text":84,"@type":76},"The project targets UT scans where the signal is missing or degraded, reconstructing the signal using neighboring successful scans via various ML models. The expected outcome is fewer nuisance detections while maintaining sensitivity for thickness analysis and defect classification.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,109,114,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":29,"slug":108},5,"Comic","comic",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]