Support vector regression-based stratified reservoir water intake discharged water temperature prediction model and prediction method

A technology of support vector regression and prediction model, which is used in prediction, character and pattern recognition, complex mathematical operations, etc. It can solve the problem of difficult to meet the high-precision prediction of water temperature, and achieve fast calculation speed, ensure accuracy, and application prospects. Good results
CN113033618AActive Publication Date: 2021-06-25SICHUAN UNIV +2

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
SICHUAN UNIV
Publication Date
2021-06-25

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a support vector regression-based stratified reservoir water intake discharge water temperature prediction model and prediction method, and the method comprises the steps: firstly carrying out principal component analysis of the reservoir water temperature, the reservoir water level, the stoplog gate elevation, the reservoir flow, the outflow flow, the air temperature, the temperature chain vertical water temperature distribution, and the like; and taking the principal component with the total contribution rate greater than 99% as an input feature vector, and predicting the discharged water temperature through the trained support vector regression model. The influence of the reservoir water temperature, the reservoir water temperature distribution, the reservoir flow, the outflow flow, the reservoir water level, the air temperature and the stoplog gate elevation on the discharged water temperature and the interaction of all the influence factors are comprehensively considered, dimensionality reduction is conducted on data, and accurate prediction of the discharged water temperature is achieved on the basis of the support vector regression method. The invention is not limited by regions, can be carried out in the aspects of reservoir water temperature management, reservoir downstream ecological environment protection and the like, provides technical support for a reservoir operation scheduling scheme, can also carry out visual operation, and has a relatively good application prospect.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the technical field of reservoir water resources management, and relates to the research on the discharge water temperature of stratified reservoirs, in particular to a machine learning algorithm-based water intake and discharge temperature prediction technology for stratified reservoirs. Background technique

[0002] Building dams and reservoirs is a common engineering measure in the development and utilization of water resources. The storage of water in the reservoir not only regulates the natural river flow, but also regulates the heat in the reservoir.

[0003] Since the heat source of the water body of the reservoir mainly includes the influence of solar radiation and warm inflow, the solar radiation cannot reach the depth of the water body, so the surface water temperature is high and the density is low. The water temperature is low and the density is high, which causes the vertical stratification of the reservoir water ...

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