Research on the super-resolution reconstruction method of Lamb wave sparse TFM imaging.
Saved in:
| Title: | Research on the super-resolution reconstruction method of Lamb wave sparse TFM imaging. |
|---|---|
| Authors: | Sun, Liu-Jia1 (AUTHOR), Han, Qing-Bang1 (AUTHOR) 220220030002@hhu.edu.cn, Jin, Qi-Lin1 (AUTHOR) |
| Source: | Nondestructive Testing & Evaluation. Apr2026, Vol. 41 Issue 4, p1926-1941. 16p. |
| Subjects: | Sparse matrices, Transformer models, Lamb waves, High resolution imaging, Convolutional neural networks, Imperfection, Ultrasonic imaging |
| Abstract: | The sparse ultrasonic total focus method (TFM) encounters challenges such as Lamb wave mode conversion and diminished imaging resolution. In this paper, a sparse array solution method is proposed to simplify the imaging computation using sparse matrices. Furthermore, a nested U-Net network with a transformer architecture (TransNU-Net) was developed to address the limitations of conventional U-Net. These limitations include the absence of explicit modelling of distant connections and the lower representation capabilities of standard networks. The purpose of the TransNU-Net is to enhance the accuracy of sparse imaging results by enabling precise segmentation. This network architecture utilises a U-Net with different depths but common weights to effectively represent defects. It uses the transformer to recover local spatial information and improve the detection of small details. Experimental results show that the obtained sparse matrix reduces the imaging time by half while maintaining an effective aperture. Compared to mainstream U-Net variants, TransNU-Net exhibits a more lightweight network structure and superior performance. The imaging results demonstrate an improvement of 34.45% and 89.10% in defect centre spacing for defects with spacing greater than the resolution threshold, respectively. For defects with spacing less than the resolution threshold, this method achieves super-resolution reconstruction. [ABSTRACT FROM AUTHOR] |
| Copyright of Nondestructive Testing & Evaluation is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| FullText | Links: – Type: pdflink Text: Availability: 1 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 193857954 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Research on the super-resolution reconstruction method of Lamb wave sparse TFM imaging. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Sun%2C+Liu-Jia%22">Sun, Liu-Jia</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Han%2C+Qing-Bang%22">Han, Qing-Bang</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> 220220030002@hhu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Jin%2C+Qi-Lin%22">Jin, Qi-Lin</searchLink><relatesTo>1</relatesTo> (AUTHOR) – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Nondestructive+Testing+%26+Evaluation%22">Nondestructive Testing & Evaluation</searchLink>. Apr2026, Vol. 41 Issue 4, p1926-1941. 16p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Sparse+matrices%22">Sparse matrices</searchLink><br /><searchLink fieldCode="DE" term="%22Transformer+models%22">Transformer models</searchLink><br /><searchLink fieldCode="DE" term="%22Lamb+waves%22">Lamb waves</searchLink><br /><searchLink fieldCode="DE" term="%22High+resolution+imaging%22">High resolution imaging</searchLink><br /><searchLink fieldCode="DE" term="%22Convolutional+neural+networks%22">Convolutional neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Imperfection%22">Imperfection</searchLink><br /><searchLink fieldCode="DE" term="%22Ultrasonic+imaging%22">Ultrasonic imaging</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: The sparse ultrasonic total focus method (TFM) encounters challenges such as Lamb wave mode conversion and diminished imaging resolution. In this paper, a sparse array solution method is proposed to simplify the imaging computation using sparse matrices. Furthermore, a nested U-Net network with a transformer architecture (TransNU-Net) was developed to address the limitations of conventional U-Net. These limitations include the absence of explicit modelling of distant connections and the lower representation capabilities of standard networks. The purpose of the TransNU-Net is to enhance the accuracy of sparse imaging results by enabling precise segmentation. This network architecture utilises a U-Net with different depths but common weights to effectively represent defects. It uses the transformer to recover local spatial information and improve the detection of small details. Experimental results show that the obtained sparse matrix reduces the imaging time by half while maintaining an effective aperture. Compared to mainstream U-Net variants, TransNU-Net exhibits a more lightweight network structure and superior performance. The imaging results demonstrate an improvement of 34.45% and 89.10% in defect centre spacing for defects with spacing greater than the resolution threshold, respectively. For defects with spacing less than the resolution threshold, this method achieves super-resolution reconstruction. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Nondestructive Testing & Evaluation is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=193857954 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1080/10589759.2025.2490765 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 16 StartPage: 1926 Subjects: – SubjectFull: Sparse matrices Type: general – SubjectFull: Transformer models Type: general – SubjectFull: Lamb waves Type: general – SubjectFull: High resolution imaging Type: general – SubjectFull: Convolutional neural networks Type: general – SubjectFull: Imperfection Type: general – SubjectFull: Ultrasonic imaging Type: general Titles: – TitleFull: Research on the super-resolution reconstruction method of Lamb wave sparse TFM imaging. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Sun, Liu-Jia – PersonEntity: Name: NameFull: Han, Qing-Bang – PersonEntity: Name: NameFull: Jin, Qi-Lin IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 04 Text: Apr2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 10589759 Numbering: – Type: volume Value: 41 – Type: issue Value: 4 Titles: – TitleFull: Nondestructive Testing & Evaluation Type: main |
| ResultId | 1 |
