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

Air data complementation method and device, equipment and storage medium

An air data and completion technology, applied in the field of data processing, can solve the problem of inaccurate completion of missing data, achieve high-precision completion, and satisfy the effect of subsequent processing.

Inactive Publication Date: 2021-12-21
湖南工商大学 +1
View PDF4 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The patent with the publication number CN103514366A discloses a repair method for the missing data of urban air quality concentration monitoring, using artificial neural network to construct the prediction model of air quality data, and using the deviation information of other stations to predict the air quality data of the faulty station, However, this method is still not accurate enough for the completion of missing data.

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
  • Air data complementation method and device, equipment and storage medium
  • Air data complementation method and device, equipment and storage medium
  • Air data complementation method and device, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0073] like figure 1 As shown, the present embodiment provides a method for complementing air data, including the following steps:

[0074] S1: Collect raw time series data x raw , the raw time series data x raw Including non-missing time point data and missing time point data, for each time series data ,for Both are d-dimensional vectors, Represents time series data The j-th attribute value of the i-th observation of ;

[0075] S2: For the original time series data x raw carry out preprocessing;

[0076] S3: Construct a generation confrontation network, the generation confrontation network includes a generator and a discriminator, and the generator includes an encoder and a decoder;

[0077] S4: Train the generative confrontation network to obtain an air data completion model;

[0078] S5: Completing the original time series data through the air data completion model x raw Perform completion to obtain the completed air data.

[0079] Step S2 specifically i...

Embodiment 2

[0129] like figure 2 As shown, this embodiment provides an air data completion device, including:

[0130] a data collection module for collecting original time series data, the original time series data including non-missing time point data and missing time point data;

[0131] a data processing module for preprocessing the original time series data;

[0132] a network building module for constructing a generative adversarial network, the generative adversarial network includes a generator and a discriminator, the generator includes an encoder and a decoder;

[0133] a network training module for training the generative adversarial network to obtain an air data completion model;

[0134] The data completion module is used to complete the original time series data through the air data completion model to obtain the completed air data.

[0135] It should be understood that the device corresponds to the air data completion method in Embodiment 1, and can perform various step...

Embodiment 3

[0137] like image 3 As shown, this embodiment provides a terminal device, including a memory, a processor, and a computer program stored in the memory and running on the processor, and the processor implements the implementation when the computer program is executed. The air data completion method in Example 1.

[0138] This embodiment also provides a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the air data completion method in Embodiment 1 is implemented.

[0139] Wherein, the storage medium can be realized by any type of volatile or non-volatile storage device or their combination, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (Electrically Erasable Programmable Read-Only Memory, EEPROM for short), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), read-only Memory (R...

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 an air data complementation method and device, equipment and a storage medium. The method comprises the following steps: collecting original time sequence data, which comprises non-missing time point data and missing time point data; preprocessing the original time sequence data; constructing a generative adversarial network, wherein the generative adversarial network comprises a generator and a discriminator, and the generator comprises an encoder and a decoder; training the generative adversarial network to obtain an air data complementation model; and complementing the original time sequence data through the air data complementation model. By adopting an improved ILSTM unit and the generative adversarial network, time sequence factors of the time sequence data can be effectively captured, and the missing data can be accurately complemented by the generative adversarial network. By means of the method, high-precision complementation of air quality data can be achieved, and the requirements of the public for timely and accurate air quality concentration monitoring data are met.

Description

technical field [0001] The present invention relates to the technical field of data processing, in particular to an air data completion method, device, equipment and storage medium. Background technique [0002] In the routine air quality monitoring process, the monitoring equipment at the monitoring site location performs routine maintenance behaviors such as zero calibration and calibration of the monitoring equipment, or when there are instrument failures, communication failures, power outages, etc., it may lead to missing monitoring data at some points. At this time, there will be data missing in some sites in the real-time released data, and the lack of air quality monitoring data will affect the public's acquisition of air quality data in the required area, and use these data for some subsequent processing operations. . At present, there are not many domestic studies on the completion of air quality data. The patent with publication number CN103514366A discloses a me...

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): G06F17/10G06N3/04G06N3/08
CPCG06F17/10G06N3/08G06N3/048G06N3/044G06N3/045
Inventor 陈杰胡慧超陈晓红徐雪松刘利枚
Owner 湖南工商大学
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