Application of CNN for multiple phase corrosion identification and region detection
dc.contributor.author | Oyedeji, Oluseyi Ayodeji | |
dc.contributor.author | Khan, Samir | |
dc.contributor.author | Erkoyuncu, John Ahmet | |
dc.date.accessioned | 2024-08-29T12:00:26Z | |
dc.date.available | 2024-08-29T12:00:26Z | |
dc.date.freetoread | 2024-08-29 | |
dc.date.issued | 2024-10-30 | |
dc.date.pubOnline | 2024-07-23 | |
dc.description.abstract | Corrosion is a significant issue that contributes negatively to the degradation of materials most especially metals. To ensure proper maintenance, enhance reliability and prevent breakdown, it is very essential to not only effectively detect corrosion but to also understand its locations and distributions on the materials. A Multiple phase Convolutional Neural Network (CNN) model is created for this purpose. The Multiple phase CNN model consists of custom designed deep learning algorithms at various stages. This created the opportunity to make use of binary classification, multi-label classification and patch distribution algorithm to detect and identify corrosion regions on metallic materials. Six (6) different labels of corrosion were modelled to represent different levels of degradation using 600 anonymized images. The images were used in the various stages of the framework for training the respective models. Results at the binary level shows 94.87 % of corrosion detection. The multiclass stage of the Multiple phase CNN records the highest accuracy of 92.1 %. The patch distribution stage recorded a highest accuracy of 96.5 % and 94.6 % for the Average Image and Average Pixel ROCAUC (Region of Concentration Area Under Cover). It also shows a region segment average accuracy detection of 91.5 % (image level) and 89.2 %(pixel level) for 9 distinct regions. The research provides a comprehensive and detailed reliability and maintenance information for Aerospace, Transport and Manufacturing Materials experts and non-experts. The framework shows a robust approach to detecting corrosion which is essential for critical and safety applications as well as preventing economic loss due to corrosion. This can also be extended to other domains beyond the corrosion case study. | |
dc.description.journalName | Applied Soft Computing | |
dc.identifier.citation | Oyedeji OA, Khan S, Erkoyuncu JA. (2024) Application of CNN for multiple phase corrosion identification and region detection. Applied Soft Computing, Volume 164, October 2024, Article number 112008 | |
dc.identifier.eissn | 1872-9681 | |
dc.identifier.elementsID | 549567 | |
dc.identifier.issn | 1568-4946 | |
dc.identifier.paperNo | 112008 | |
dc.identifier.uri | https://doi.org/10.1016/j.asoc.2024.112008 | |
dc.identifier.uri | https://dspace.lib.cranfield.ac.uk/handle/1826/22847 | |
dc.identifier.volumeNo | 164 | |
dc.language | English | |
dc.language.iso | en | |
dc.publisher | Elsevier BV | |
dc.publisher.uri | https://www.sciencedirect.com/science/article/pii/S1568494624007828?via%3Dihub | |
dc.rights | Attribution 4.0 International | en |
dc.rights.uri | http://creativecommons.org/licenses/by/4.0/ | |
dc.subject | Corrosion | |
dc.subject | Convolutional neural network (CNN) | |
dc.subject | Reliability | |
dc.subject | Maintenance | |
dc.subject | Degradation | |
dc.subject | 4605 Data Management and Data Science | |
dc.subject | 46 Information and Computing Sciences | |
dc.subject | Prevention | |
dc.subject | Networking and Information Technology R&D (NITRD) | |
dc.subject | Artificial Intelligence & Image Processing | |
dc.subject | 4602 Artificial intelligence | |
dc.subject | 4903 Numerical and computational mathematics | |
dc.title | Application of CNN for multiple phase corrosion identification and region detection | |
dc.type | Article | |
dc.type.subtype | Journal Article | |
dcterms.dateAccepted | 2024-07-06 |