Please use this identifier to cite or link to this item:
http://hdl.handle.net/10603/527437
Title: | Characterization Of Weld Defect Using Phased Array Ultrasonic Method |
Researcher: | JAYA SUDHA J C |
Guide(s): | LALITHAKUMARI S |
Keywords: | Engineering Engineering and Technology Engineering Electrical and Electronic |
University: | Sathyabama Institute of Science and Technology |
Completed Date: | 2022 |
Abstract: | In the recent past, weldment inspection became automated in newlinemetal industry. The weldment inspection had been previously conducted newlineperceivably, then physically and then recently automatically using newlineinstrumental techniques such as ultrasound. Impacts of asymmetrical newlinewelding region and warp variation of ultrasonic replication locus in newlineenclosure measure, weld make it difficult to differentiate welding defect newlinewave from inside replication wave successfully in traditional ultrasonic newlinewelding defect testing that leads to error detection and imprecise location newlineof welding defects. The Non-Destructive Testing (NDT) is conscious to newlinegenerate weldment defect detection and assist undeniable weld defect newlinesuch as lack of fusion, cavities, slag, porosity, root defects and crack. newlinePhased Array Ultrasonic Testing technique (PAUT) could govern the newlineemphasis and refraction of ultrasound stream of light beam by regulating newlinethe excitation duration of every piezoelectric chip in phased array that is newlineused to enhance the detection efficiency and accuracy. newlinePAUT plays vital role in non-destructive testing for welding newlinedefect identification. The Digital Image Processing (DIP) plays newlinesignificant role in weldment inspection. In this research, novel cascaded newlinealgorithms are proposed for welding defect detection and classification newlineusing PAUT. The image analysis qualitatively gives the characteristics of newlinewelding defects. Principally incorporation of artificial intelligence is newlinebeing collaborated more and more in efficient processes, the newlinecharacteristics that is formerly resolute is qualitatively ahead significance. newlineIn this contribution, it is proposed to use Deep Learning (DL) to achieve newlinesemantic classification of PAUT images of multifaceted weld region to newlineix newlineattain the automatic identification and weld defect characteristics. In newlinegeneration PAUT images are poor in quality and highly affected by newlinevarious noises during scanning processing. newlineInitially, PAUT image should be pre-processed by applying newlineeffective and novel image processing techniques. |
Pagination: | vi, 158 |
URI: | http://hdl.handle.net/10603/527437 |
Appears in Departments: | ELECTRONICS DEPARTMENT |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
10.chapter 6.pdf | Attached File | 885.67 kB | Adobe PDF | View/Open |
11.chapter 7.pdf | 19.47 kB | Adobe PDF | View/Open | |
12.annexure.pdf | 6.44 MB | Adobe PDF | View/Open | |
1.title.pdf | 79.83 kB | Adobe PDF | View/Open | |
2.prelim pages.pdf | 601.9 kB | Adobe PDF | View/Open | |
3.abstract.pdf | 11.93 kB | Adobe PDF | View/Open | |
4.contents.pdf | 98.67 kB | Adobe PDF | View/Open | |
5.chapter 1.pdf | 273.77 kB | Adobe PDF | View/Open | |
6.chapter 2.pdf | 377.25 kB | Adobe PDF | View/Open | |
7.chapter 3.pdf | 278.47 kB | Adobe PDF | View/Open | |
80_recommendation.pdf | 79.83 kB | Adobe PDF | View/Open | |
8.chapter 4.pdf | 288.22 kB | Adobe PDF | View/Open | |
9.chapter 5.pdf | 259.29 kB | Adobe PDF | View/Open |
Items in Shodhganga are licensed under Creative Commons Licence Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0).
Altmetric Badge: