Digital transformation for offshore assets: a deep learning framework for weld classification in remote visual inspections.

Toral-Quijas, Luis Alberto; Elyan, Eyad; Moreno-García, Carlos Francisco; Stander, Jan

Abstract

Inspecting circumferential welds in caissons is a critical task for ensuring the safety and reliability of structures in the offshore industry. However, identifying and classifying different types of circumferential welds can be challenging in subsea environments, due to low contrast, variable illumination and suspended particles. To address this challenge, we present a framework for automating the classification of circumferential welds using deep learning-based methods. We used a dataset of 4,000 images for experimental purposes and utilised three state-of-the-art, pre-trained Convolutional Neural Network (CNN) architectures, including MobileNet V2, Xception and EfficientNet. Our results showed superior performance of EfficientNet, with high levels of accuracy (86.75%), recall (91%), and F1-score (87.29%), as well as demonstrating efficient time. These findings suggest that leveraging deep learning-based methods can significantly reduce the time required for inspection tasks. This work opens a new research direction toward digitally transforming inspection tasks in the oil and gas industry.

Citation

TORAL-QUIJAS, L.A., ELYAN, E., MORENO-GARCÍA, C.F. and STANDER, J. 2023. Digital transformation for offshore assets: a deep learning framework for weld classification in remote visual inspections. In Iliadis, L, Maglogiannis, I., Alonso, S., Jayne, C. and Pimenidis, E. (eds.) Proceedings of the 24th International conference on engineering applications of neural networks (EAAAI/EANN 2023), 14-17 June 2023, León, Spain. Communications in computer and information science, 1826. Cham: Springer [online], pages 217-226. Available from: https://doi.org/10.1007/978-3-031-34204-2_19

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 24th International conference on engineering applications of neural networks (EAAAI/EANN 2023)
• Start Date: Jun 14, 2023
• End Date: Jun 17, 2023
• Acceptance Date: Mar 28, 2023
• Online Publication Date: Jun 7, 2023
• Publication Date: Dec 31, 2023
• Deposit Date: Jul 4, 2023
• Publicly Available Date: Jun 8, 2024
• Publisher: Springer
• Peer Reviewed: Peer Reviewed
• Pages: 217-226
• Series Title: Communications in computer and information science (CCIS)
• Series Number: 1826
• Series ISSN: 1865-0929; 1865-0937
• ISBN: 9783031342035
• DOI: https://doi.org/10.1007/978-3-031-34204-2_19
• Keywords: Remote sensing; Image recognition; Image classification; Welding; Machine learning; Circumferential welds; Offshore; Remote visual inspections; EfficientNet
• Public URL: https://rgu-repository.worktribe.com/output/1982527