{"title":"基于傅里叶变换和局部二值模式算法的搅拌摩擦焊接接头表面质量分析","authors":"Akshansh Mishra","doi":"10.1590/0104-9224/si25.27","DOIUrl":null,"url":null,"abstract":"https://doi.org/10.1590/0104-9224/SI25.27 Abstract: Friction Stir Welding process is an advanced solid-state joining process which finds application in various industries like automobiles, manufacturing, aerospace and railway firms. Input parameters like tool rotational speed, welding speed, axial force and tilt angle govern the quality of Friction Stir Welded joint. Improper selection of these parameters further leads to fabrication of the joint of bad quality resulting groove edges, flash formation and various other surface defects. In the present work, a texture based analytic machine learning algorithm known as Local Binary Pattern (LBP) and Fourier transformation algorithm are used for the extraction of texture features of the Friction Stir Welded joints which are welded at a different rotational speed. It was observed that LBP algorithm can accurately detect any irregularities present on the surface of Friction Stir Welded joint and Fourier transformation method can detect the groovy edges present on the Friction Stir Welded joint. In the case study, an image based defect recognition system by using Fourier transformation method is constructed. Five types of filters i.e. Ideal Filter, Butterworth Filter, Low pass Filter, Gaussian Filter and High Pass Filter were used. The results showed that the high pass filter has more capability to detect the edges in comparison to other four filters. It was also observed that Ideal filter has a lot of distortions when compared to the Gaussian Filter and Butterworth","PeriodicalId":49500,"journal":{"name":"Soldagem & Inspecao","volume":null,"pages":null},"PeriodicalIF":0.3000,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Surface Quality Analysis of Friction Stir Welded Joints by Using Fourier Transformation and Local Binary Patterns Algorithms\",\"authors\":\"Akshansh Mishra\",\"doi\":\"10.1590/0104-9224/si25.27\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"https://doi.org/10.1590/0104-9224/SI25.27 Abstract: Friction Stir Welding process is an advanced solid-state joining process which finds application in various industries like automobiles, manufacturing, aerospace and railway firms. Input parameters like tool rotational speed, welding speed, axial force and tilt angle govern the quality of Friction Stir Welded joint. Improper selection of these parameters further leads to fabrication of the joint of bad quality resulting groove edges, flash formation and various other surface defects. In the present work, a texture based analytic machine learning algorithm known as Local Binary Pattern (LBP) and Fourier transformation algorithm are used for the extraction of texture features of the Friction Stir Welded joints which are welded at a different rotational speed. It was observed that LBP algorithm can accurately detect any irregularities present on the surface of Friction Stir Welded joint and Fourier transformation method can detect the groovy edges present on the Friction Stir Welded joint. In the case study, an image based defect recognition system by using Fourier transformation method is constructed. Five types of filters i.e. Ideal Filter, Butterworth Filter, Low pass Filter, Gaussian Filter and High Pass Filter were used. The results showed that the high pass filter has more capability to detect the edges in comparison to other four filters. It was also observed that Ideal filter has a lot of distortions when compared to the Gaussian Filter and Butterworth\",\"PeriodicalId\":49500,\"journal\":{\"name\":\"Soldagem & Inspecao\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.3000,\"publicationDate\":\"2020-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Soldagem & Inspecao\",\"FirstCategoryId\":\"88\",\"ListUrlMain\":\"https://doi.org/10.1590/0104-9224/si25.27\",\"RegionNum\":4,\"RegionCategory\":\"材料科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"METALLURGY & METALLURGICAL ENGINEERING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Soldagem & Inspecao","FirstCategoryId":"88","ListUrlMain":"https://doi.org/10.1590/0104-9224/si25.27","RegionNum":4,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"METALLURGY & METALLURGICAL ENGINEERING","Score":null,"Total":0}
Surface Quality Analysis of Friction Stir Welded Joints by Using Fourier Transformation and Local Binary Patterns Algorithms
https://doi.org/10.1590/0104-9224/SI25.27 Abstract: Friction Stir Welding process is an advanced solid-state joining process which finds application in various industries like automobiles, manufacturing, aerospace and railway firms. Input parameters like tool rotational speed, welding speed, axial force and tilt angle govern the quality of Friction Stir Welded joint. Improper selection of these parameters further leads to fabrication of the joint of bad quality resulting groove edges, flash formation and various other surface defects. In the present work, a texture based analytic machine learning algorithm known as Local Binary Pattern (LBP) and Fourier transformation algorithm are used for the extraction of texture features of the Friction Stir Welded joints which are welded at a different rotational speed. It was observed that LBP algorithm can accurately detect any irregularities present on the surface of Friction Stir Welded joint and Fourier transformation method can detect the groovy edges present on the Friction Stir Welded joint. In the case study, an image based defect recognition system by using Fourier transformation method is constructed. Five types of filters i.e. Ideal Filter, Butterworth Filter, Low pass Filter, Gaussian Filter and High Pass Filter were used. The results showed that the high pass filter has more capability to detect the edges in comparison to other four filters. It was also observed that Ideal filter has a lot of distortions when compared to the Gaussian Filter and Butterworth
期刊介绍:
The Journal Soldagem & Inspeção (S&I) js a techno-scientific journal created in 1995. Printed issues of this journal are distributed free of charge to libraries in Brazil, Latin America and the Iberian Peninsula. It has been printed regularly every quarter since September, 2002, and, since the beginning of 2007, its electronic version is available in the address: (http://www.abs-soldagem.org.br/s&i/). The journal is sponsored by the Brazilian Welding Association (ABS).
Since its creation several well known professionals working in welding contributed with the Journal Soldagem & Inspeção and its editorial board crosses the Brazilian borders. During its evolution the Journal received ta special contribution from the Editors-in-chief : Ronaldo Paranhos, Américo Scoti, Paulo Modenesi e Alexandre Bracarence. Since January 2012 the Editor-in-chief is Ana Sofia C. M. D’Oliveira, Full professor at Universidade Federal do Paraná (UFPR) . Her work focus mainly on Hardfacing and Physical Metallurgy. The jornal Soldagem & Inspeção also counts with 10 Associate Editors and a fix Editorial board of referees. short-term (Ad Hoc) referees can be invited to evaluate some papers submitted to the journal.
The Soldagem & Inspeção journal is the scientific divulgation channel of the Brazilian Welding Association (ABS). It aims to publish original papers related to the scientific and technological development of welding, inspection, and related fields. Review papers or letters on current and controversial subjects are also published in the Journal.
Its abbreviated title is Soldag. insp. (Impr.), which should be used in bibliographies, footnotes and bibliographical references and strips.