A novel classification method for non-magnetic metals with complex surfaces.
Saved in:
| Title: | A novel classification method for non-magnetic metals with complex surfaces. |
|---|---|
| Authors: | Xu, Yuanchao1 (AUTHOR), Zhang, Zhijie1 (AUTHOR) zhangzhijie@nuc.edu.cn, Yin, Wuliang2 (AUTHOR), Li, Yingzhe1 (AUTHOR), Liu, Yan1 (AUTHOR) |
| Source: | Nondestructive Testing & Evaluation. Mar2026, Vol. 41 Issue 3, p1612-1629. 18p. |
| Subjects: | Classification, Eddy current testing, Image recognition (Computer vision), Nonferrous metals, Circular economy, Rough surfaces, Waste recycling |
| Abstract: | Metals have extremely high recycling value, and recycling and classification of metals using eddy current sensing technology can promote the sustainable utilisation of resources. Whereas most of the current research focuses on planar metals, the study of metals with complex surfaces is still insufficient. For the latter, the distance and angle between the sensor and the measured surface are constantly changing, which will seriously affect the classification accuracy. To address this problem, this paper proposes a novel method for classification that is immune to the complex surfaces of the samples. First, the equivalent height method is proposed, by which the metal samples with complex surfaces are converted into planar samples with equivalent heights. Then, image recognition technology is used to access the height information of the sample, and eddy current sensing technology is combined to eliminate the influence of height on the classification accuracy. After experimental verification, the classification accuracy of this method is 96.67%. [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.
|
|
| Abstract: | Metals have extremely high recycling value, and recycling and classification of metals using eddy current sensing technology can promote the sustainable utilisation of resources. Whereas most of the current research focuses on planar metals, the study of metals with complex surfaces is still insufficient. For the latter, the distance and angle between the sensor and the measured surface are constantly changing, which will seriously affect the classification accuracy. To address this problem, this paper proposes a novel method for classification that is immune to the complex surfaces of the samples. First, the equivalent height method is proposed, by which the metal samples with complex surfaces are converted into planar samples with equivalent heights. Then, image recognition technology is used to access the height information of the sample, and eddy current sensing technology is combined to eliminate the influence of height on the classification accuracy. After experimental verification, the classification accuracy of this method is 96.67%. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 10589759 |
| DOI: | 10.1080/10589759.2025.2502152 |
