Dynamic generation method for hydrological time series prediction model

A technology of hydrological time series and prediction model, which is applied in prediction, neural learning method, biological neural network model, etc., to achieve the effect of reducing data volume, improving efficiency and high precision

Pending Publication Date: 2022-07-29
HOHAI UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Preprocess the wate

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
  • Dynamic generation method for hydrological time series prediction model
  • Dynamic generation method for hydrological time series prediction model
  • Dynamic generation method for hydrological time series prediction model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The technical solutions of the present invention are described in detail below, but the protection scope of the present invention is not limited to the embodiments.

[0042] like figure 1 As shown, a method for dynamically generating a hydrological time series prediction model in this embodiment includes the following steps:

[0043] Step S1, select the historical water level information of the Lianhuatang hydrological station in the middle reaches of the Yangtze River, from 8:00 on February 26, 2014 to 14:00 on February 28, 2018, a total of 35119 pieces of hourly water level data, and organize them into hydrological time series data set. There are data missing and data errors in the water level sample data, so preprocessing is performed, including filling in missing data, correcting wrong data, and data standardization;

[0044] The normalization formula is as follows:

[0045]

[0046] where x represents the original data, x' represents the standardized data, mean...

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 hydrological time series prediction model dynamic generation method, which comprises the following steps of: acquiring water level data of a corresponding hydrological station, organizing into a hydrological time series data set and preprocessing; clustering is carried out on the segmented and symbolized sequences in combination with improved symbol distance UMD and DBSCAN clustering; dynamically forming a similar sequence set for each to-be-matched sequence and constructing and training a model, firstly measuring the distance between a representative sequence and a to-be-matched symbolized sequence and selecting similar categories to form candidate sets, secondly screening the similar sequence candidate sets by adopting an improved DTW algorithm, constructing the similar sequence set, and finally optimizing TCN model parameters to obtain a TCN model; training the model by using the similar sequence set to obtain a hydrological time sequence prediction model based on similarity search; the model obtained by the hydrological time series prediction model dynamic generation method is subjected to water level prediction, and the accuracy is higher.

Description

technical field [0001] The invention belongs to the hydrology prediction technology, in particular to a dynamic generation method of a hydrology time series prediction model. Background technique [0002] Time series data widely exists in various fields of society and life. Hydrological data that records hydrological phenomena that change with time in discrete form belong to typical time series data. Most of the hydrological time series data have the characteristics of large data volume, high noise, instability, fast update and high complexity, such as water level, flow, rainfall and other information. In today's social life, water conservancy informatization plays an increasingly important role. Its main work includes information collection, mining and analysis, etc. How to obtain effective features and knowledge from complex hydrological data to serve hydrological forecasting and Scheduling work is an urgent problem that needs to be solved now. [0003] The development o...

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): G06Q10/04G06Q10/06G06K9/62G06N3/04G06N3/08G06Q50/06
CPCG06Q10/04G06Q10/06393G06N3/08G06Q50/06G06N3/045G06F18/22
Inventor 聂青青万定生余宇峰
Owner HOHAI 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