基于图神经网络和LSTM网络的管道油气泄漏检测方法
By using a fusion model of graph neural networks and LSTM networks, combined with a distributed fiber optic temperature measurement system, the problem of the lack of consideration of the temporal and spatial relationships of signals in existing technologies is solved, and high-precision pipeline leak detection and location are achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHENGDU UNIVERSITY OF TECHNOLOGY
- Filing Date
- 2023-04-06
- Publication Date
- 2026-07-17
AI Technical Summary
Existing pipeline leak detection methods fail to effectively consider the temporal correlation and spatial relationship between signals, resulting in insufficient accuracy in abnormal temperature detection.
A fusion model based on graph neural networks and LSTM networks is adopted. Temperature data is collected through a distributed optical fiber temperature measurement system to construct graph structure data. The spatial relationship of the signal is captured by the graph neural network and the temporal characteristics are captured by the LSTM network. The Sigmoid function is used to determine abnormal temperature.
It improves the accuracy of abnormal temperature detection, enabling precise location of leaks in underground utility tunnels and ensuring safe operation.
Smart Images
Figure CN116447528B_ABST