Industrial sequential data missing filling method based on sectional state displaying

A sequence data and sequence technology, which is applied in the filling field of missing industrial sequence data, to achieve the effect of fast running speed and high precision
CN103246702AActive Publication Date: 2013-08-14DALIAN UNIV OF TECH
4 Cites 20 Cited by

Patent Information

Authority / Receiving Office
CN Β· China
Patent Type
Applications(China)
Current Assignee / Owner
DALIAN UNIV OF TECH
Publication Date
2013-08-14

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention relates to an industrial sequential data missing filling method based on sectional state displaying. The industrial sequential data missing filling method includes: firstly, separating to-be-filled target sequences in a non-equidistant manner, displaying states for the separated sequences through three characteristic quantities including amplitude level, variation tendency and wave magnitude, and then establishing a method for computing a similarity factor of state displaying, searching similar sequences by the computed similarity factor, and finally utilizing a machine learning method to train the similar sequences of the to-be-filled sequences so as to establish a data missing filling model to fill the missing data sequences. The industrial sequential data missing filling method can fill missing sequential data caused by data storage or transmission fault and the like in an industrial process, can further complete monitoring data, and can improve data reliability so as to provide guarantees to data based optimization, control and scheduling operation realized in the industrial process.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the field of information technology, and relates to sequence non-equidistant segmentation, sequence shape representation, similar sequence search and echo state network modeling theory, and is a filling method for missing industrial sequence data based on segmented state representation. The present invention utilizes the existing historical data of the industrial site, first performs non-equidistant segmentation on the target sequence to be filled, and then expresses the shape of the segmented sequence through the three characteristic quantities of amplitude level, change trend and fluctuation size, and further calculates the sequence shape Represent the similarity coefficient, use the calculated similarity coefficient to find similar sequences, and finally use the machine learning method to establish a data missing filling model to realize the filling of missing data sequences. Thereby effectively guaranteeing the integrity and ...

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