Metal loss defect detection and depth estimation using multi-spectral image analysis of cooling excited steel specimen with corrosion
Abstract Imaging techniques have considerably improved corrosion-induced metal loss defect detection and severity estimation in recent decades. Even though the detection of defects using imaging techniques in steel is well established, determining the severity remains difficult due to the necessity...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-07-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-88528-w |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849335249268375552 |
|---|---|
| author | Shamendra Egodawela Amirali K. Gostar H. A. D. Samith Buddika W. A. N. I. Harischandra A. J. Dhammika Mojtaba Mahmoodian |
| author_facet | Shamendra Egodawela Amirali K. Gostar H. A. D. Samith Buddika W. A. N. I. Harischandra A. J. Dhammika Mojtaba Mahmoodian |
| author_sort | Shamendra Egodawela |
| collection | DOAJ |
| description | Abstract Imaging techniques have considerably improved corrosion-induced metal loss defect detection and severity estimation in recent decades. Even though the detection of defects using imaging techniques in steel is well established, determining the severity remains difficult due to the necessity of estimating the depth information of the defect from 2-dimensional image data. This study used a steel test specimen with artificial defects of varying depths and diameters, subjected to accelerated corrosion. A Multi-Spectral Imaging setup observed the specimen’s spectral response at different temperatures following a cooling excitation. Reflected intensities at specific wavelengths indicated defect presence and allowed quantification of corrosion-induced metal loss. Principal Component Analysis and machine learning regression were used to transform discrete defect depths into continuous assessments. Support Vector Regression, Decision Tree Regressor, Random Forest Regressor, Gradient Boosting Regressor, and a Feedforward Neural Network (FNN) were tested for this task. The FNN showed the best results in solving the regression problem with a least Root Mean Square Error of 0.2829 and an R2 score 0.976. The 700 nm–900 nm range was identified as the optimal wavelength span for spectral imaging. |
| format | Article |
| id | doaj-art-df94bbab8f7045a68c4485cead0a64e2 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-df94bbab8f7045a68c4485cead0a64e22025-08-20T03:45:20ZengNature PortfolioScientific Reports2045-23222025-07-0115111610.1038/s41598-025-88528-wMetal loss defect detection and depth estimation using multi-spectral image analysis of cooling excited steel specimen with corrosionShamendra Egodawela0Amirali K. Gostar1H. A. D. Samith Buddika2W. A. N. I. Harischandra3A. J. Dhammika4Mojtaba Mahmoodian5School of Engineering, RMIT UniversitySchool of Engineering, RMIT UniversityFaculty of Engineering, University of PeradeniyaFaculty of Engineering, University of PeradeniyaFaculty of Engineering, University of PeradeniyaSchool of Engineering, RMIT UniversityAbstract Imaging techniques have considerably improved corrosion-induced metal loss defect detection and severity estimation in recent decades. Even though the detection of defects using imaging techniques in steel is well established, determining the severity remains difficult due to the necessity of estimating the depth information of the defect from 2-dimensional image data. This study used a steel test specimen with artificial defects of varying depths and diameters, subjected to accelerated corrosion. A Multi-Spectral Imaging setup observed the specimen’s spectral response at different temperatures following a cooling excitation. Reflected intensities at specific wavelengths indicated defect presence and allowed quantification of corrosion-induced metal loss. Principal Component Analysis and machine learning regression were used to transform discrete defect depths into continuous assessments. Support Vector Regression, Decision Tree Regressor, Random Forest Regressor, Gradient Boosting Regressor, and a Feedforward Neural Network (FNN) were tested for this task. The FNN showed the best results in solving the regression problem with a least Root Mean Square Error of 0.2829 and an R2 score 0.976. The 700 nm–900 nm range was identified as the optimal wavelength span for spectral imaging.https://doi.org/10.1038/s41598-025-88528-wNon-destructive testingCorrosion severity estimationMulti-spectral imagingMachine learning |
| spellingShingle | Shamendra Egodawela Amirali K. Gostar H. A. D. Samith Buddika W. A. N. I. Harischandra A. J. Dhammika Mojtaba Mahmoodian Metal loss defect detection and depth estimation using multi-spectral image analysis of cooling excited steel specimen with corrosion Scientific Reports Non-destructive testing Corrosion severity estimation Multi-spectral imaging Machine learning |
| title | Metal loss defect detection and depth estimation using multi-spectral image analysis of cooling excited steel specimen with corrosion |
| title_full | Metal loss defect detection and depth estimation using multi-spectral image analysis of cooling excited steel specimen with corrosion |
| title_fullStr | Metal loss defect detection and depth estimation using multi-spectral image analysis of cooling excited steel specimen with corrosion |
| title_full_unstemmed | Metal loss defect detection and depth estimation using multi-spectral image analysis of cooling excited steel specimen with corrosion |
| title_short | Metal loss defect detection and depth estimation using multi-spectral image analysis of cooling excited steel specimen with corrosion |
| title_sort | metal loss defect detection and depth estimation using multi spectral image analysis of cooling excited steel specimen with corrosion |
| topic | Non-destructive testing Corrosion severity estimation Multi-spectral imaging Machine learning |
| url | https://doi.org/10.1038/s41598-025-88528-w |
| work_keys_str_mv | AT shamendraegodawela metallossdefectdetectionanddepthestimationusingmultispectralimageanalysisofcoolingexcitedsteelspecimenwithcorrosion AT amiralikgostar metallossdefectdetectionanddepthestimationusingmultispectralimageanalysisofcoolingexcitedsteelspecimenwithcorrosion AT hadsamithbuddika metallossdefectdetectionanddepthestimationusingmultispectralimageanalysisofcoolingexcitedsteelspecimenwithcorrosion AT waniharischandra metallossdefectdetectionanddepthestimationusingmultispectralimageanalysisofcoolingexcitedsteelspecimenwithcorrosion AT ajdhammika metallossdefectdetectionanddepthestimationusingmultispectralimageanalysisofcoolingexcitedsteelspecimenwithcorrosion AT mojtabamahmoodian metallossdefectdetectionanddepthestimationusingmultispectralimageanalysisofcoolingexcitedsteelspecimenwithcorrosion |