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

Construction method of reservoir daily inflow prediction model

A construction method and forecasting model technology, which is applied in the field of reservoir daily intake forecasting model construction, can solve the problems of sensitive and fragile sequence data and weak generalization ability, and achieve the goal of improving forecasting accuracy, overcoming sensitivity and vulnerability, and slowing down volatility Effect

Pending Publication Date: 2020-08-07
苏州丰华声赫智能科技有限公司
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the problems existing in the prior art, a method for constructing a reservoir daily intake forecasting model in the present invention utilizes the characteristics of different sensitivities of various models to different data, and overcomes the fact that a single model is sensitive to sequence data with complex characteristics. Fragility and weak generalization ability to achieve accurate prediction of daily inflow of reservoirs

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
  • Construction method of reservoir daily inflow prediction model
  • Construction method of reservoir daily inflow prediction model
  • Construction method of reservoir daily inflow prediction model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0034] Example: After logarithmic transformation of the input reservoir daily inflow data, the present invention uses an improved false nearest neighbor method to determine the embedding dimension, that is, the number of input nodes of the neural network, and then constructs different decomposition algorithms and different neural network model structures Combine multiple basic learning machines. In this embodiment, use EMB decomposition and LSTM network, EEMB decomposition and LSTM network, wavelet decomposition and LSTM network, use EMB decomposition and CNN network, and EEMB decomposition and CNN network. , Using wavelet decomposition combined with CNN network communication, a total of 6 basic learning machines, and finally the 6 basic learning machines are integrated through the weighted summation method to form a prediction model of the daily reservoir volume, which is used to predict. Attached below figure 1 with 2 The present invention is described in further detail.

[003...

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 construction method of a reservoir daily inflow prediction model. The construction method comprises the following steps: constructing a basic learning machine; enabling the learning machine to use a smoothing preprocessing method, adopting a time sequence decomposition method to obtain related components according to a processed sequence, then a prediction model is established for the components, a prediction result is reconstructed to obtain a related prediction result, a plurality of basic learning machines are obtained according to the above steps to be integrated,and the reservoir daily water inflow is predicted through the integrated model. The method mainly solves the problems of insufficient data feature information mining and low prediction accuracy of the existing reservoir daily storage capacity prediction algorithm.

Description

Technical field [0001] The invention relates to hydrological forecasting technology, in particular to a method for predicting the daily water inflow of a reservoir based on logarithmic transformation, time series decomposition and reconstruction, neural network and integrated learning. It is mainly used to predict the daily inflow of the reservoir to guide the reservoir The management operation of this system can reduce the release of unnecessary water resources, which can be used for drought management of reservoirs, flood control, irrigation water, hydroelectric power generation, industrial and domestic water. Background technique [0002] Reservoirs are an important part of water resources management, and effective reservoir operations can reduce water release. Reservoir inflow prediction is very important to the management and operation of reservoirs. Flow prediction can be used for flood control, drought resistance, power generation, domestic water use and improvement of the...

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): G06Q10/04G06Q50/06G06N3/04G06N3/08G06N20/00
CPCG06Q10/04G06Q50/06G06N3/08G06N20/00G06N3/044G06N3/045
Inventor 戚玉涛杨玲玲周詹翱
Owner 苏州丰华声赫智能科技有限公司