Unlock instant, AI-driven research and patent intelligence for your innovation.

A Method of Restoring Monitoring Data of Industrial System Based on Online PCA

A technology for monitoring data and industrial systems, applied in electrical digital data processing, digital data information retrieval, special data processing applications, etc., can solve problems such as large amount of calculation and large amount of effective sensor data, and achieve the effect of avoiding accidents

Active Publication Date: 2022-01-07
BEIJING SGITG ACCENTURE INFORMATION TECH CO LTD
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the amount of data of the effective sensor is large, and the information is directly used to restore it, which requires a large amount of calculation. Therefore, dimensionality reduction is data compression, and then the compressed data is used to restore the missing data of the faulty sensor.

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 Method of Restoring Monitoring Data of Industrial System Based on Online PCA
  • A Method of Restoring Monitoring Data of Industrial System Based on Online PCA
  • A Method of Restoring Monitoring Data of Industrial System Based on Online PCA

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0040] The present invention is a kind of industrial system monitoring data recovery method based on online PCA, and the flow chart is as follows figure 1 As shown, the specific steps are as follows:

[0041] Step 1. Collect the monitoring data of the industrial system and sort them in time series. Specifically, follow the steps below:

[0042] Step 1.1, first sample the non-faulty sensors of the industrial system, and at the same time the monitoring data collected by the normal sensors is represented by X={x 1 ,x 2 ,...,x N}∈R d×N where, X contains the data information of d non-faulty sensors, which is sampled once every 1s, and the number of samples is N, and the sampled data information at the tth time point is represented by x t means, and t=1,2,…,N, x t =[x t1 x t2 … x td ] T ;

[0043] Step 1.2, sampling the faulty sensors of...

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 recovery method for industrial system monitoring data based on online PCA. Firstly, the industrial system monitoring data is collected and sorted according to time sequence; secondly, a dimensionality reduction model is established based on the online PCA method, and the collected industrial system monitoring data is collected. Dimensionality reduction, which is to compress the collected data; finally, build a model based on the stack noise reduction sparse autoencoder network, and use the data after dimensionality reduction to restore the missing data. The present invention can accurately restore the highly correlated missing data in real time , and have some understanding of the state of the industrial system.

Description

technical field [0001] The invention belongs to the technical field of industrial system monitoring data recovery, and in particular relates to an online PCA-based industrial system monitoring data recovery method. Background technique [0002] As the proportion of industry in my country's national economy is increasing, its significance for improving people's quality of life is becoming more and more prominent. At the same time, security issues in industrial systems are getting more and more attention. For general industrial systems, it is the most effective monitoring method to reflect their status by extracting important information from monitoring data. Industrial systems generally transmit status information through installed sensors, and usually multiple sensors work in parallel to transmit data information. However, when one of the sensors or transmission equipment fails to transmit information, but does not affect the normal operation of the entire system, some dat...

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 Patents(China)
IPC IPC(8): G06F16/215G06F16/2458
Inventor 谢国张永艳穆凌霞黑新宏王文卿邱原金永泽孙澜澜
Owner BEIJING SGITG ACCENTURE INFORMATION TECH CO LTD