A completion method and a completion device for industrial monitoring data loss

A technology for monitoring data and industry, applied in the direction of electrical digital data processing, special data processing applications, digital data information retrieval, etc., can solve the problem of poor filling effect of data sets, achieve the effect of improving accuracy and reducing noise

Active Publication Date: 2019-05-28
UNIV OF SCI & TECH BEIJING +1
View PDF3 Cites 28 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] The technical problem to be solved by the present invention is to provide a complementing method and a complementing device for missing industrial monitoring 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
  • A completion method and a completion device for industrial monitoring data loss
  • A completion method and a completion device for industrial monitoring data loss
  • A completion method and a completion device for industrial monitoring data loss

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0066] Example one

[0067] Such as figure 1 with figure 2 As shown, the method for complementing missing industrial monitoring data provided by the embodiment of the present invention includes:

[0068] Step 1. Obtain an original data set, where the original data set is an original industrial monitoring data set whose missing type is completely randomly missing;

[0069] Step 2: Construct an automatic encoder according to the acquired original data set; among them, when constructing the automatic encoder, noise is added to the input original data to retrain the automatic encoder, and the trained automatic encoder is used to realize the original data Upgrading and reducing the dimensionality of the feature vector;

[0070] Step 3: Build a generative model based on the acquired original data set;

[0071] Step 4: Combine the constructed automatic encoder with the generative model, and use the original data set to optimize the training of the combined model to obtain generated data simi...

Example Embodiment

[0192] Example two

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 complementing method and a complementing device for industrial monitoring data loss, which can improve the data complementing effect. The method comprises the steps of obtaining an original data set, wherein the original data set is an original industrial monitoring data set with the missing type being completely random missing; constructing an automatic coding machine according to the obtained original data set, wherein when the automatic coding machine is constructed, noise is added into input original data, then the automatic coding machine is trained, and the trained automatic coding machine is used for achieving dimensionality increase and dimensionality reduction of feature vectors in the original data; establishing a generative model according to the obtained original data set; and combining the constructed automatic coding machine with the generative model, and carrying out optimization training on the combined model by utilizing the original data set to obtain generated data similar to the original data feature distribution. The invention relates to the field of industrial production and data mining.

Description

technical field [0001] The invention relates to the fields of industrial production and data mining, in particular to a complementing method and a complementing device for missing industrial monitoring data. Background technique [0002] In the industrial field, people pay more and more attention to the value of data, and machine learning and data mining methods are usually used to obtain rules and information from data. The core factor for the success of data mining projects is the quality of the data set. If the quality of the data set is poor or not strongly related to the research problem, no matter how advanced the method of feature selection and model building is, it will not be able to achieve the expected results. [0003] Missing data is a common problem faced by industrial monitoring data. The main reasons for missing data can include: [0004] (a) The working state of the instrument is unstable: on-site environmental factors or human factors cause some instrument...

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): G06F16/215G06N3/04
Inventor 班晓娟刘婷袁兆麟王贻明王青海赵占斌
Owner UNIV OF SCI & TECH BEIJING
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