Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Self-adaptive prediction method with embedded fuzzy set state and self-adaptive prediction system

An adaptive and self-adaptive fuzzy technology, applied in the field of prediction, can solve problems such as missing information

Inactive Publication Date: 2012-08-01
INST OF ATMOSPHERIC PHYSICS CHINESE ACADEMY SCI
View PDF3 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In this way, the statistical model neglects to measure the uncertainty of the numerical weather prediction (NWP) trend term, thus losing important information about the forecast state

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
  • Self-adaptive prediction method with embedded fuzzy set state and self-adaptive prediction system
  • Self-adaptive prediction method with embedded fuzzy set state and self-adaptive prediction system
  • Self-adaptive prediction method with embedded fuzzy set state and self-adaptive prediction system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] (Example 1: Atmospheric system forecast model)

[0040] Due to the ambiguity of the impact of the trend item on the forecast accuracy of the forecast model, simply adopting an either-or binary logic of "no influence" or "all influence" has very limited effect on improving the forecast model. It is a more natural method to describe the uncertain, unclear and incomplete state of the trend item in the atmospheric system forecast model by using the relevant methods in fuzzy theory. Due to the time-discrete characteristics of the large-scale trend item, it can only give a trend overview of limited time intervals, such as the instantaneous temperature conditions at intervals of 6 hours, so its influence on small-scale features is with the time process It shows a gradually increasing trend, so in the time period concerned by the short-term forecast, the influence of the trend item can be assigned in different periods, that is, different weights are given to its influence degre...

Embodiment 2

[0126] (Embodiment 2 realizes the system of multi-step forecasting method)

[0127] According to the multi-step forecast method of the atmospheric environment in the above embodiments, the present invention further provides a system for realizing the multi-step forecast method.

[0128] Figure 5 A structural schematic diagram of a multi-step forecasting system according to the present invention is shown.

[0129] Such as Figure 5 As shown, the multi-step forecasting system 100 of the present invention includes a fuzzy processing unit 101 , a model building unit 102 and a forecasting unit 103 . Among them, the fuzzy processing unit 101 performs, for example, figure 2 As shown in the adaptive fuzzification process, calculate the adaptive membership vector of the trend item, for example [u 00 , u 06 , u 12 , u 18 ]. The model construction unit 102 according to the adaptive membership degree vector of the trend item [u 00 , u 06 , u 12 , u 18 ], combined with past obs...

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 provides a multi-step prediction method and a multi-step prediction system. The multi-step prediction method comprises the steps of performing self-adaptive fuzzification processing to trend items of prediction elements and calculating self-adaptive membership degree vectors of the trend items; combining with observed values in the past to generate learning samples with fuzzification features according to the self-adaptive membership degree vectors of the trend items and establishing time series prediction models; and utilizing the time series prediction model to perform multi-step prediction. The self-adaptive prediction method with an embedded fuzzy set state and the self-adaptive prediction system can achieve prediction with high accuracy rate and low error rate.

Description

technical field [0001] The present invention relates to the technical field of forecasting, in particular to a multi-step forecasting method and system for forecasting elements of large-mass inertial systems (such as atmospheric systems and hydrological systems). Background technique [0002] Forecasting technology is widely used in the forecasting of target elements in various fields such as meteorology, hydrology, and ecological environment. For example, the well-known weather forecast is a long-term or short-term forecast of target elements such as temperature. [0003] Existing forecasting techniques are designed for the scale characteristics of forecasting objects. Taking the atmospheric system as an example, its motion has multi-scale characteristics whether it is resolved in space or time. Therefore, the forecast model describing the atmospheric system is also targeted in terms of scale in model design. According to the scale characteristics of different forecast obj...

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 Applications(China)
IPC IPC(8): G06F19/00G01W1/10
Inventor 马晓光
Owner INST OF ATMOSPHERIC PHYSICS CHINESE ACADEMY SCI
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com