Intelligent normal pool level optimal selection method based on genetic neural network models

A genetic neural network and intelligent optimization technology, which is applied in the field of normal water storage level optimization of hydropower stations, can solve problems such as relying on engineering experience and expert scoring, focusing on schemes, and ignoring the effectiveness of indicators

Active Publication Date: 2013-12-04
ZHEJIANG UNIV
View PDF4 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there are still some deficiencies: (1) Emphasis on the selection of programs, ignoring the selection of indicator effectiveness
(2) The optimization of the scheme relies too much on engineering experience and expert scoring, and the distribution of the weighted values ​​of each target is highly subjective. The determination of the weig

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Intelligent normal pool level optimal selection method based on genetic neural network models
  • Intelligent normal pool level optimal selection method based on genetic neural network models
  • Intelligent normal pool level optimal selection method based on genetic neural network models

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0076] (1) Determine the upper and lower limits of normal water storage levels and significant influencing factors to form a set of comparison options

[0077] Taking a large hydropower station at the intersection of Sichuan and Yunnan provinces as an example, collect relevant graphic survey data, and refer to the method of forming water storage level comparison and selection schemes in GIS ( figure 1 ) and the overall structure of the model ( figure 2 )’s significant index acquisition method, through computer technology, determine the 8 main factors of the hydropower station, and the data of each index are shown in Table 1. Therefore, it is determined that the input vector of the BP network is F={f1, f2, f3...f8}.

[0078] Table 1

[0079]

[0080] (2) Constitute a network learning sample, and the trained network uses four test samples to verify the results, and normalize the training samples and test samples

[0081] (3) Determine the BP network learning structure and...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses an intelligent normal pool level optimal selection method based on genetic neural network models. The method includes the steps of firstly, determining high-low limit of normal pool level; secondly, providing a normal pool level elevation threshold, acquiring area and volume index to form a draft selection scheme, and repeating the second step to form a comparison and selection scheme set; thirdly, selecting index evaluation factors, and selecting evident difference indexes to participate in model calculation; fourthly, forming network learning samples according to required sample number, and normalizing training samples and test samples; fifthly determining a BP network learning structure and initial genetic algorithm population; sixthly, using genetic algorithm to optimize neural network weights and thresholds; seventhly, fine adjusting BP neural network weights, and using built models to evaluate to-be-selected schemes. The method is significantly practical in the field of hydraulic and hydroelectric engineering, the influence of subjective factors is reduced effectively, and objectivity of index weight determination is increased.

Description

technical field [0001] The invention relates to the field of information technology of genetic neural network model and GIS technology in hydropower engineering construction, and in particular to a method for optimizing the normal water storage level of a hydropower station. Background technique [0002] With the rapid growth of the national economy, the demand for electricity continues to increase, and the energy structure dominated by coal will bring constraints on resources and the environment. Hydropower is a pollution-free renewable resource, and hydropower has entered a period of accelerated development. Therefore, to give priority to the development of hydropower projects, more advanced and scientific methods are needed to ensure the improvement of hydropower project construction efficiency and reduce construction costs. It is open and transparent, and reduces social and political influence. , Improve the scientific and technological content of water conservancy work....

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06N3/08G06N3/12
Inventor 刘仁义张丰杜震洪郜美娜郑晔郑少楠
Owner ZHEJIANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap