GA-BP neural network-based island-type fishway high-flow-velocity region area ratio prediction method
By applying the BP neural network method optimized by genetic algorithm in island fishing paths, the high flow rate area ratio is accurately predicted, which solves the limitations of geometric parameter selection and optimization in traditional methods, and achieves efficient flow characteristics optimization.
CN119918137APending Publication Date: 2025-05-02CHINA JILIANG UNIV
View PDF 0 Cites 0 Cited by
Patent Information
- Application Number
- CN202411977626.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-31
- Publication Date
- 2025-05-02
Smart Images
Figure CN119918137A_ABST
Abstract
The invention relates to a GA-BP neural network-based island-type fishway high-flow-velocity region area ratio prediction method. According to the method, a BP neural network is optimized by using a genetic algorithm, an island type fishway high-flow-velocity region area ratio prediction model is established in combination with numerical simulation, and four influence factors of the model are an island width factor, an island length factor, an island distance factor and a pseudo vertical seam factor respectively. Through prediction error judgment of the prediction model, the BP neural network optimized by the genetic algorithm is high in prediction accuracy and good in fitting effect, and the result shows that the method reduces the experiment cost and the numerical simulation calculation amount, reduces the waste of manpower and material resources, and is of great significance to fine research of subsequent structure adjustment.
Need to check novelty before this filing date? Find Prior Art