一种流域水库群系统防洪调度智能决策方法
By combining deep learning and iterative optimization algorithms with dynamic Bayesian networks, the flood control scheduling of a watershed reservoir group is optimized, solving the problems of insufficient real-time performance and accuracy in existing technologies, and achieving efficient and intelligent decision-making.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- HOHAI UNIV
- Filing Date
- 2025-02-20
- Publication Date
- 2026-07-17
AI Technical Summary
Existing flood control scheduling methods for river basin reservoir groups are insufficient in terms of real-time performance and accuracy. Decision results are significantly influenced by the subjective preferences of decision-makers, lack the ability to adjust risks in real time, and consume large amounts of computational resources.
Deep learning algorithms are used to predict watershed flood risks. Combined with iterative optimization algorithms and dynamic Bayesian networks, a risk reasoning-scheme optimization loop iterative optimization process is formed. By combining historical scenarios and real-time data, the flood control scheduling scheme is optimized.
It improves the decision-making efficiency and intelligence level of watershed flood control scheduling, reduces computation time costs, and enhances the real-time performance and accuracy of decision-making results within the watershed, meeting the needs of digital twin watersheds.
Smart Images
Figure CN120124930B_ABST