Unlock instant, AI-driven research and patent intelligence for your innovation.

Prediction model and method of stratified reservoir intake and discharge water temperature based on support vector regression

A support vector regression and forecasting model technology, applied in forecasting, character and pattern recognition, data processing applications, etc., can solve problems such as difficult to meet the high-precision forecasting of water temperature in the discharge, achieve fast calculation speed, reduce prediction difficulty, and memory usage little effect

Active Publication Date: 2022-03-15
SICHUAN UNIV +2
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

According to the researchers’ prototype observations of engineering examples, it is found that the temperature of the discharged water is affected by various factors such as the water level in the reservoir area, the vertical water temperature distribution, the elevation of the logger door, the number of layers of the logger door, and the number of units in operation. There is a complex mutual influence relationship, and the existing discharge water temperature prediction methods are difficult to meet the needs of high-precision prediction of the discharge water temperature by using reservoir scheduling operations

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
  • Prediction model and method of stratified reservoir intake and discharge water temperature based on support vector regression
  • Prediction model and method of stratified reservoir intake and discharge water temperature based on support vector regression
  • Prediction model and method of stratified reservoir intake and discharge water temperature based on support vector regression

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0103] This embodiment is provided with a layered reservoir to take a water release temperature prediction model construction method based on the supported vector return. figure 1 As shown, including the following steps:

[0104] S1 gets monitoring data within a given time period

[0105] The monitoring data involved in this embodiment includes a warehousing water temperature, a reservoir water level, a laminate elevation, a storage flow, an effluent flow rate, a temperature distribution of a temperature chain in front of the water, and a lower venting temperature.

[0106] The specific acquisition of each of the above elements include:

[0107] (1) Temperature is obtained by field monitoring or national meteorological data center (http: / / data.cma.cn / ).

[0108] (2) Reservoir water level, laminate elevation, inventory flow and traffic flow through the reservoir schedule operation information.

[0109] (3) Surface water temperature sensor uses Kangkang Instrument Co., Ltd. Customiz...

Embodiment 2

[0173] This embodiment utilizes a hierarchical Example 1 Construction of reservoir water outflow temperature prediction model for predicting outflow temperature conditions (April 1, 2019 - monitoring data May 19, 2019 acquisition period) is predicted, comprising the following steps:

[0174] S1 'obtain a layered reservoirs to be predictive condition monitoring data

[0175] Condition monitoring data to be predicted comprises storage temperature, reservoir water level, Stoplog elevation, inflow, outflow flow rate, temperature, inlet temperature before the vertical water temperature distribution chain, and as the characteristic variable.

[0176] Each specific element data acquisition method, see Example 1.

[0177] Abnormality prediction value filter condition to the monitoring data for a given time period, manual data weed out the vertical water temperature distribution abnormality (see Example 1 specific operation).

[0178] In this embodiment, the monitoring data to April 1, 201...

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 a support vector regression-based predictive model and method for predicting the water temperature of the intake and discharge of stratified reservoirs. Conduct principal component analysis on water temperature distribution, etc., and then use the principal component with a total contribution rate greater than 99% as the input feature vector, and predict the discharge water temperature through the trained support vector regression model. The present invention comprehensively considers the influence of the inflow water temperature, the distribution of the reservoir water temperature, the inflow flow, the outflow flow, the water level of the reservoir, the air temperature and the elevation of the logger door on the discharge water temperature, and the interaction of various influencing factors, and reduces the dimensionality of the data. Based on the support vector regression method, the accurate prediction of the discharge water temperature is realized. The invention is not restricted by region, can be implemented in the aspects of reservoir water temperature management, ecological environment protection downstream of the reservoir, etc., provides technical support for reservoir operation and scheduling schemes, and can also perform visual operations at the same time, and has good application prospects.

Description

Technical field [0001] The present invention belongs to the field of reservoir water resources management, involving draining temperature under a layered reservoir, in particular, relating to a layered reservoir of a machine learning algorithm, a prediction technique for water release temperature. Background technique [0002] Building a dam construction library is a common measures commonly used in water resources. The reservoir water storage is not only regulated on natural river traffic, but also the heat in the library has regulated. [0003] Since the heat of the reservoir water is mainly included in the influence of solar radiation and warmth flow, solar radiation cannot reach the depth of the water body, so the surface water temperature is high, the density is small, and the water flow capacity of the reservoir area is weak, and the vertical water exchange capacity is insufficient. The water temperature in the water is low, the density is large, thereby causing the water t...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/62G06F17/18G06F17/16G06Q10/04G06Q50/06
CPCG06F17/16G06F17/18G06Q10/04G06Q50/06G06F18/214
Inventor 脱友才樊皓徐火清卢永澳严忠銮邓云惠军梁乃生李斐杨颜菁卢晶莹孙干杨小倩
Owner SICHUAN UNIV