Quality-related fault online monitoring method for efficiently updating model under time-varying system

A quality-related, time-varying system technology, applied in general control systems, control/regulation systems, program control, etc., can solve problems such as inability to monitor quality-related faults, high computational complexity of model update, and low update efficiency

Active Publication Date: 2020-03-27
ROCKET FORCE UNIV OF ENG
View PDF4 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the existing two types of model update methods have been widely used, the method based on data expansion has the disadvantages of high computational complexity and low update efficiency; the method based on recursive structure cannot effectively detect quality-related faults. Disadvantages of Process Monitoring

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
  • Quality-related fault online monitoring method for efficiently updating model under time-varying system
  • Quality-related fault online monitoring method for efficiently updating model under time-varying system
  • Quality-related fault online monitoring method for efficiently updating model under time-varying system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0129] The method proposed by the present invention will be verified below through the data collected in the Tennessee-Eastman (TEP) experiment. TEP is a small-scale industrial process developed by Eastman Chemical Company Downs and Vogel in 1993. The entire process consists of five operating units, including chemical reactors, condensers, compressors, vapor / liquid separators, and separators.

[0130] TEP contains eight components: A, B, C, D, E, F, G and H, where gaseous substances A, C, D and E and inert substance B are reactants, G and H are reaction products, and F is reaction by-products. In the reactor, 4 reactions are carried out simultaneously with the assistance of the catalyst:

[0131]

[0132] Table 1 is 12 control variables (XMV), Table 2 is 41 measurement variables (XMEAS); Table 3 is 15 known faults (IDV). Table 1-Table 3 are as follows:

[0133] Table 1 12 control variables (XMV)

[0134]

[0135] Table 2 41 measurement variables (XMEAS)

[0136] ...

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 quality-related fault online monitoring method for efficiently updating a model under a time-varying system. The method comprises the steps of obtaining a training data sample; determining discrete training model parameters according to the training data sample; determining a fault threshold value according to the discrete training model parameters; acquiring online testdata; carrying out deorthogonalization processing on the online test data to obtain online test data after orthogonalization processing; determining a current sample statistic according to the onlinetest data after orthogonal processing; and determining a fault type according to the current sample statistics and the fault threshold. According to the method, parameters can be used for replacing original historical data, the model updating calculation amount is effectively reduced, the model updating efficiency is improved, parameter changes of the system are effectively tracked, and effectivequality-related fault monitoring is achieved.

Description

technical field [0001] The invention relates to the field of reliability engineering, in particular to an online monitoring method for quality-related faults of an efficient model update under a time-varying system. Background technique [0002] In the actual industrial production process, the time-varying system usually causes the slow drift of the working point due to equipment aging and small changes in the working environment. The static process monitoring model based on traditional batch processing is difficult to describe this process, which will lead to serious false alarms. and a leak alarm occurs. For time-varying systems, the common method is to track system changes by regularly updating the model. The common methods are mainly divided into two categories: 1. Traditional model update methods based on data augmentation. This method is a commonly used model update method in process monitoring. The historical input data is added to the input data matrix, a large amou...

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): G05B19/418
CPCG05B19/41885G05B2219/32339Y02P90/02
Inventor 孔祥玉胡昌华罗家宇李强司小胜
Owner ROCKET FORCE UNIV OF ENG
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