Enhancing gas-pipeline monitoring with graph neural networks: a new approach for acoustic emission analysis under variable pressure conditions.

Hasan, Md Junayed; Arifeen, Murshedul; Sohaib, Muhammad; Rohan, Ali; Kannan, Somasundar

Abstract

Traditional machine learning (ML) and deep learning (DL)-based acoustic emission (AE) data-driven condition monitoring models face several reliability issues due to factors such as fluid pressure changes, flange vibrations, inconsistent leak lengths, and noise in AE signals, which vary with pipeline conditions. Additionally, the noise, and variable pressure conditions complicate the interpretation of sensor data, especially in multivariate setups where understanding spatial relationships between sensors is challenging. In response, we have introduced Graph Convolutional Networks (GCNs) to overcome these challenges in AE-based pipeline monitoring for the first time. Our proposed method utilizes a publicly available pipeline monitoring dataset, named GPLA-12, which comprises AE signals to train and evaluate the GCN-based model. This innovative graph construction technique is designed to decipher and comprehend the subtleties in AE signals gathered under various pressure conditions from a multi-variate sensor setup. This approach can potentially establish a new standard in pipeline monitoring research and applications.

Citation

HASAN, M.J., ARIFEEN, M., SOHAIB, M., ROHAN, A. and KANNAN, S. 2024. Enhancing gas pipeline monitoring with graph neural networks: a new approach for acoustic emission analysis under variable pressure conditions. To be published in Proceedings of the 20th International conference on condition monitoring and asset management 2024 (CM 2024), 18-20 June 2024, Oxford, UK. Northampton: BINDT [online], (accepted). To be made available at: https://doi.org/10.1784/cm2024.4b3

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 20th International conference on condition monitoring and asset management 2024 (CM 2024)
• Start Date: Jun 18, 2024
• End Date: Jun 20, 2024
• Acceptance Date: May 2, 2024
• Online Publication Date: Jun 20, 2024
• Publication Date: Dec 31, 2024
• Deposit Date: Aug 26, 2024
• Publicly Available Date: Sep 24, 2024
• Publisher: British Institute of Non-destructive Testing
• Peer Reviewed: Peer Reviewed
• Series Title: Proceedings of the International conference on condition monitoring and asset management
• Series ISSN: 2632-637X
• ISBN: 9780903132848
• DOI: https://doi.org/10.1784/cm2024.4b3
• Keywords: Machine learning (ML); Deep learning (DL); Acoustic emission (AE); Pipeline monitoring
• Public URL: https://rgu-repository.worktribe.com/output/2423391