结合三维荧光指纹与图神经网络的雨水管网污染溯源方法
By combining three-dimensional fluorescent fingerprinting with graph neural networks, real-time data collection and analysis of stormwater pipe network data has solved the problems of slow response and low accuracy in pollution source tracing under complex pipe network conditions. This has enabled rapid and accurate pollution source tracing and emergency response, and improved the intelligence level of urban drainage systems.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- TONGJI UNIV
- Filing Date
- 2026-04-23
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies suffer from slow response, low accuracy, and insufficient robustness when facing complex pipeline network conditions, dynamic pollution characteristics, and multi-source mixed connection scenarios. They are unable to meet the real-time and accuracy requirements for tracing urban overflow pollution sources under high-frequency rainfall scenarios.
By combining three-dimensional fluorescence fingerprinting and graph neural network methods, a dynamic fluorescence database is constructed by deploying a fluorescence spectral sensor array to collect data in real time. A machine learning model is used for feature extraction and pattern recognition. The source tracing results are optimized by combining the pipeline network topology and Bayesian inference algorithm. The confidence assessment of pollution source type, location and mixed connection path is output, and a visual interface is used to provide feedback and early warning mechanism.
It enables rapid response and precise location of sudden mixed pollution incidents, significantly improves the robustness of the model and the efficiency of emergency response, enhances the spatial resolution and location accuracy of the source tracing results, forms a closed-loop system from perception to emergency response, and improves the intelligence level of the urban drainage system.
Smart Images
Figure CN122087429B_ABST