A Hybrid FEM-CNN for Image-Based Severity Prediction of Corroded Offshore Pipelines
The combination of the Finite Element Method (FEM) with Convolutional Neural Networks (CNNs) presents a key breakthrough in the assessment of the structural integrity of offshore pipelines. The advantage of the standard FEM is in stress visualization, but it is time-consuming due to high computation...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2025-01-01
|
| Series: | E3S Web of Conferences |
| Online Access: | https://www.e3s-conferences.org/articles/e3sconf/pdf/2025/12/e3sconf_aere2025_04003.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832098463316180992 |
|---|---|
| author | Mohammad Fadzil Najwa Muda Mohd Fakri Abdul Shahid Muhammad Daniel Aziz Norheliena Mohd Mohd Hairil Mohd Amin Norliyati Mohd Hashim Mohd Hisbany |
| author_facet | Mohammad Fadzil Najwa Muda Mohd Fakri Abdul Shahid Muhammad Daniel Aziz Norheliena Mohd Mohd Hairil Mohd Amin Norliyati Mohd Hashim Mohd Hisbany |
| author_sort | Mohammad Fadzil Najwa |
| collection | DOAJ |
| description | The combination of the Finite Element Method (FEM) with Convolutional Neural Networks (CNNs) presents a key breakthrough in the assessment of the structural integrity of offshore pipelines. The advantage of the standard FEM is in stress visualization, but it is time-consuming due to high computational analysis. This research aims to quickly and accurately determine the severity of pipeline corrosion categorized as high, intermediate, or low through stress images generated from FEM. A transfer-learning algorithm was applied to refine and validate the model using a diverse image dataset of uniformly corroded pipelines (200x200 mm, 100x100 mm, 75x75 mm, 50x50 mm, and 10x10 mm), annotated with corresponding severity levels. Moreover, the model was validated for prediction with irregular-sized corroded pipelines (50x100 mm and 10x100 mm). Both samples are modeled for degrees of corrosion, 30%, 50%, and 70% of the corrosion depth, with API 5L X42 specifications. An exceptional predictive accuracy was observed, attaining average confidence levels between 97% and 100%. This work substantially augments the effectiveness of structural analyses that provide a better safety feature for critical infrastructural assets within the oil and gas industry and has great advantages to engineers, researchers, and academicians working on pipeline integrity management. |
| format | Article |
| id | doaj-art-ea9f66dc3d784c87b83f76fa0750c41c |
| institution | Kabale University |
| issn | 2267-1242 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | EDP Sciences |
| record_format | Article |
| series | E3S Web of Conferences |
| spelling | doaj-art-ea9f66dc3d784c87b83f76fa0750c41c2025-02-05T10:51:06ZengEDP SciencesE3S Web of Conferences2267-12422025-01-016120400310.1051/e3sconf/202561204003e3sconf_aere2025_04003A Hybrid FEM-CNN for Image-Based Severity Prediction of Corroded Offshore PipelinesMohammad Fadzil Najwa0Muda Mohd Fakri1Abdul Shahid Muhammad Daniel2Aziz Norheliena3Mohd Mohd Hairil4Mohd Amin Norliyati5Mohd Hashim Mohd Hisbany6School of Civil Engineering, College of Engineering, Universiti Teknologi MARACivil Engineering Studies, Universiti Teknologi MARA Pahang Branch, Jengka CampusSchool of Civil Engineering, College of Engineering, Universiti Teknologi MARASports Engineering & Artificial Intelligence Center (SEAIC), Universiti Teknologi MARADepartment of Maritime Technology, Faculty of Ocean Engineering Technology and Informatics, Universiti Malaysia TerengganuSchool of Civil Engineering, College of Engineering, Universiti Teknologi MARASchool of Civil Engineering, College of Engineering, Universiti Teknologi MARAThe combination of the Finite Element Method (FEM) with Convolutional Neural Networks (CNNs) presents a key breakthrough in the assessment of the structural integrity of offshore pipelines. The advantage of the standard FEM is in stress visualization, but it is time-consuming due to high computational analysis. This research aims to quickly and accurately determine the severity of pipeline corrosion categorized as high, intermediate, or low through stress images generated from FEM. A transfer-learning algorithm was applied to refine and validate the model using a diverse image dataset of uniformly corroded pipelines (200x200 mm, 100x100 mm, 75x75 mm, 50x50 mm, and 10x10 mm), annotated with corresponding severity levels. Moreover, the model was validated for prediction with irregular-sized corroded pipelines (50x100 mm and 10x100 mm). Both samples are modeled for degrees of corrosion, 30%, 50%, and 70% of the corrosion depth, with API 5L X42 specifications. An exceptional predictive accuracy was observed, attaining average confidence levels between 97% and 100%. This work substantially augments the effectiveness of structural analyses that provide a better safety feature for critical infrastructural assets within the oil and gas industry and has great advantages to engineers, researchers, and academicians working on pipeline integrity management.https://www.e3s-conferences.org/articles/e3sconf/pdf/2025/12/e3sconf_aere2025_04003.pdf |
| spellingShingle | Mohammad Fadzil Najwa Muda Mohd Fakri Abdul Shahid Muhammad Daniel Aziz Norheliena Mohd Mohd Hairil Mohd Amin Norliyati Mohd Hashim Mohd Hisbany A Hybrid FEM-CNN for Image-Based Severity Prediction of Corroded Offshore Pipelines E3S Web of Conferences |
| title | A Hybrid FEM-CNN for Image-Based Severity Prediction of Corroded Offshore Pipelines |
| title_full | A Hybrid FEM-CNN for Image-Based Severity Prediction of Corroded Offshore Pipelines |
| title_fullStr | A Hybrid FEM-CNN for Image-Based Severity Prediction of Corroded Offshore Pipelines |
| title_full_unstemmed | A Hybrid FEM-CNN for Image-Based Severity Prediction of Corroded Offshore Pipelines |
| title_short | A Hybrid FEM-CNN for Image-Based Severity Prediction of Corroded Offshore Pipelines |
| title_sort | hybrid fem cnn for image based severity prediction of corroded offshore pipelines |
| url | https://www.e3s-conferences.org/articles/e3sconf/pdf/2025/12/e3sconf_aere2025_04003.pdf |
| work_keys_str_mv | AT mohammadfadzilnajwa ahybridfemcnnforimagebasedseveritypredictionofcorrodedoffshorepipelines AT mudamohdfakri ahybridfemcnnforimagebasedseveritypredictionofcorrodedoffshorepipelines AT abdulshahidmuhammaddaniel ahybridfemcnnforimagebasedseveritypredictionofcorrodedoffshorepipelines AT aziznorheliena ahybridfemcnnforimagebasedseveritypredictionofcorrodedoffshorepipelines AT mohdmohdhairil ahybridfemcnnforimagebasedseveritypredictionofcorrodedoffshorepipelines AT mohdaminnorliyati ahybridfemcnnforimagebasedseveritypredictionofcorrodedoffshorepipelines AT mohdhashimmohdhisbany ahybridfemcnnforimagebasedseveritypredictionofcorrodedoffshorepipelines AT mohammadfadzilnajwa hybridfemcnnforimagebasedseveritypredictionofcorrodedoffshorepipelines AT mudamohdfakri hybridfemcnnforimagebasedseveritypredictionofcorrodedoffshorepipelines AT abdulshahidmuhammaddaniel hybridfemcnnforimagebasedseveritypredictionofcorrodedoffshorepipelines AT aziznorheliena hybridfemcnnforimagebasedseveritypredictionofcorrodedoffshorepipelines AT mohdmohdhairil hybridfemcnnforimagebasedseveritypredictionofcorrodedoffshorepipelines AT mohdaminnorliyati hybridfemcnnforimagebasedseveritypredictionofcorrodedoffshorepipelines AT mohdhashimmohdhisbany hybridfemcnnforimagebasedseveritypredictionofcorrodedoffshorepipelines |