Enhancing acoustic emission driven smart gas-pipeline monitoring with graph neural network.

Arifeen, Murshedul; Hasan, Md Junayed; Rohan, Ali; Kannan, Somasundar; Prathuru, Anil

Abstract

Conventional machine learning (ML) and deep learning (DL) strategies for acoustic emission (AE) data-driven condition monitoring exhibit a range of reliability concerns. These include variations due to fluid pressure, flange vibrations, varying leak dimensions, and AE signal noise, all of which shift with changing pipeline conditions. Furthermore, the complexity of interpreting sensor data is heightened by noise and fluctuating pressure conditions, particularly in multi-variate systems where discerning spatial relationships among sensors proves challenging. In response, we have pioneered the application of Graph Convolutional Networks (GCNs) to AE-based pipeline monitoring. This novel approach leverages a publicly accessible dataset, GPLA-12, which includes AE signals to both train and assess our GCN model. Our innovative graph construction method is crafted to decode and analyze the complexities of AE signals recorded under diverse pressure scenarios in a multi-sensor environment. This technique is poised to redefine standards in pipeline monitoring research and applications.

Citation

ARIFEEN, M., HASAN, M.J., ROHAN, A., KANNAN, S. and PRATHURU, A. 2025. Enhancing acoustic emission driven smart gas-pipeline monitoring with graph neural network. In Manjurul Islam, M.M., Baptista, M.L. and Tariq, F. (eds.) Artificial intelligence for smart manufacturing and industry X.0. Springer series in Advanced Manufacturing, Cham: Springer [online], pages 165-178. Available from: https://doi.org/10.1007/978-3-031-80154-9_8

• Online Publication Date: Mar 6, 2025
• Publication Date: Dec 31, 2025
• Deposit Date: Aug 25, 2025
• Publicly Available Date: Mar 7, 2026
• Publisher: Springer
• Peer Reviewed: Peer Reviewed
• Pages: 165-178
• Series Title: Springer Series in Advanced Manufacturing
• Series ISSN: 1860-5168; 2196-1735
• Book Title: Artificial intelligence for smart manufacturing and industry X.0
• ISBN: 9783031801532; 9783031801563
• DOI: https://doi.org/10.1007/978-3-031-80154-9_8
• Keywords: Pipe-line monitoring; Graph neural network; Feature engineering; Smart manufacturing; Industry X.0
• Public URL: https://rgu-repository.worktribe.com/output/2783042