一种基于改进孪生支持向量机的径流区间预报方法
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- HOHAI UNIV
- Filing Date
- 2023-08-23
- Publication Date
- 2026-07-17
AI Technical Summary
Existing runoff forecasting models are unable to accurately characterize and describe the nonlinear, fluctuating, and complex features of runoff, resulting in deterministic values that cannot reflect the possible range of runoff fluctuations, and a single model cannot provide comprehensive information.
An improved twin support vector machine method was adopted, and the whale optimization algorithm was improved by combining nonlinear convergence factor and nonlinear adaptive weight factor. By introducing Lagrange multipliers and Karush-Kuhn-Tucker conditions, the model parameters were optimized, and upper and lower boundary functions were generated for runoff interval forecasting.
It has achieved high-quality runoff interval forecasting, reduced forecast uncertainty, provided a quantitative description of runoff value fluctuation range, and improved the reliability and clarity of forecasts.
Smart Images
Figure CN117371805B_ABST