Image-Driven Deep Learning for Prediction and Analysis of Pipeline Leakage and Burst Events
Journal of Pipeline Systems Engineering and Practice · 01.11.2026 · 17 (4)
DOI: 10.1061/jpsea2.pseng-2231 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Pipeline Systems Engineering and Practice, erschienen am 01.11.2026. Verfasst von You Fu und 2 weiteren Autor:innen. Die Arbeit nennt 22 Literaturangaben.
Abstract (Originalsprache)
Addressing the challenge of leakage and burst identification in pressurized pipeline systems, this study investigates the pressure-response mechanisms and localization methods under burst events. A systematic analysis of pressure-wave propagation is conducted to reveal the distinct pressure characteristics associated with different burst modes: instantaneous bursts exhibit pronounced fluctuations with clear reflection structures, whereas progressive bursts show noticeable transitional disturbances and buffering stages. Because pressure-cloud maps simultaneously embed both temporal and spatial information, they provide a more comprehensive representation of the propagation trajectory and energy-attenuation pattern of burst-induced disturbances. Accordingly, a long short-term memory (LSTM) model based on time-series pressure data and another LSTM model driven by pressure-cloud-map features are constructed. Four data-partitioning schemes are applied to systematically compare their prediction performance across multiple burst-location scenarios. The results demonstrate that the cloud-map-driven model consistently outperforms the time-series model in all evaluation schemes, achieving lower errors in the root mean square error and mean absolute error, as well as a higher coefficient of determination ( R 2 ). Under conditions with strong pressure-field interference, the maximum R 2 of the cloud-map model reaches 0.98. Experiments on both instantaneous and progressive burst events further show that the cloud-map model maintains an R 2 above 0.95, indicating superior and more stable localization capability. By contrast, the time-series model is more susceptible to complex reflected waves, leading to larger prediction deviations. In summary, pressure-cloud maps represent an essential and highly effective feature modality for burst localization. Their integrated two-dimensional spatiotemporal structure significantly enhances the ability of deep-learning models to accurately identify burst positions.
Zitieren
APA
Fu, Y., Hui, Q., & Qiang, P. (2026). Image-Driven Deep Learning for Prediction and Analysis of Pipeline Leakage and Burst Events. Journal of Pipeline Systems Engineering and Practice, 17(4). https://doi.org/10.1061/jpsea2.pseng-2231
Vancouver
Fu Y, Hui Q, Qiang P. Image-Driven Deep Learning for Prediction and Analysis of Pipeline Leakage and Burst Events. Journal of Pipeline Systems Engineering and Practice. 2026;17(4). doi:10.1061/jpsea2.pseng-2231
BibTeX
@article{Fu2026,
author = {Fu, You and Hui, Qunzhi and Qiang, Pan},
title = {Image-Driven Deep Learning for Prediction and Analysis of Pipeline Leakage and Burst Events},
journal = {Journal of Pipeline Systems Engineering and Practice},
year = {2026},
volume = {17},
number = {4},
doi = {10.1061/jpsea2.pseng-2231}
}
EUVIMED