一种基于机器学习的排水管网实时充满度评估方法
By establishing a drainage network topology model and a graph temporal neural network, the problem of real-time filling degree assessment under complex conditions in existing technologies is solved. This enables filling degree assessment with quantifiable credibility and traceable assessment process, supporting risk identification and scheduling decisions.
CN121836403BActive Publication Date: 2026-07-17NORTH CHINA MUNICIPAL ENG DESIGN & RES INST
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- NORTH CHINA MUNICIPAL ENG DESIGN & RES INST
- Filing Date
- 2026-03-16
- Publication Date
- 2026-07-17
Smart Images
Figure CN121836403B_ABST
Abstract
本发明公开了一种基于机器学习的排水管网实时充满度评估方法，具体涉及城市排水管网运行监测与智能评估技术领域，用于解决现有排水管网在观测不完备、传感器质量不稳定和管网结构复杂情况下，难以及时准确评估各管段充满度并进行风险预警的问题。通过在统一授时和运行切片约束下构建融合节点证据向量和水力连接属性的排水管网时序证据图，将其输入经离线训练且版本锁定的图时序神经网络，在质量守恒约束下对中间充满度表征进行物理一致性校正并输出带不确定性指标的充满度估计值，从而达到在观测不完备、传感器质量参差和管网结构复杂条件下为各管段提供物理约束一致、可信度可量化且过程可追溯可复现的排水管网充满度评估结果。
Need to check novelty before this filing date? Find Prior Art