Non-Gaussian process monitoring method based on distributed ICR model

A process monitoring, decentralized technology used in program control, electrical testing/monitoring, test/monitoring control systems, etc.

Active Publication Date: 2018-08-24
NINGBO UNIV
View PDF6 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, implementing similar error generation schemes in data-driven fault detection models is open to further discussion.

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
  • Non-Gaussian process monitoring method based on distributed ICR model
  • Non-Gaussian process monitoring method based on distributed ICR model
  • Non-Gaussian process monitoring method based on distributed ICR model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0067] The method of the present invention will be described in detail below in conjunction with the accompanying drawings and specific examples of implementation.

[0068] Such as figure 1 As shown, a fault detection method based on a decentralized principal component regression model. The specific implementation process of the method of the present invention and its superiority over existing methods will be described below in conjunction with an example of a specific industrial process.

[0069] The application object is from Tennessee-Eastman (TE) chemical process experiment, and the prototype is an actual process flow of Eastman chemical production workshop. Currently, the TE process has been widely used in fault detection research as a standard experimental platform due to its complexity. The whole TE process includes 22 measured variables, 12 manipulated variables, and 19 component measured variables. The collected data are divided into 22 groups, including 1 group 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 non-Gaussian process monitoring method based on distributed ICR (Independent Component Regression) models, aiming at solving the problem of how to use a non-Gaussian data modeling algorithm to convert sampling data into errors through a data model and the problem of implementing non-Gaussian process monitoring by taking errors as monitored objects. Specifically, the method of the invention includes the following steps: firstly, establishing a soft sensing model between each variable and other variables using an independent component regression (ICR) algorithm for eachmeasured variable; and secondly, establishing a process monitoring model based on independent component analysis (ICA) to implement non-Gaussian process monitoring using estimation errors of a soft sensor model as monitored objects. It can be seen that the method of the invention utilizes the advantages of distributed modeling and adopts an implementation mode combined with a plurality of non-Gaussian data analysis algorithms, so the method is a more preferred data-driven process monitoring method suitable for a non-Gaussian process.

Description

technical field [0001] The invention relates to a data-driven process monitoring method, in particular to a non-Gaussian process monitoring method based on a distributed ICR model. Background technique [0002] Real-time monitoring of the operating status of the production process is a direct way to ensure safe production and maintain stable product quality. The research on process monitoring has always existed in the development of the entire industry, and its purpose is to find faults in a timely and accurate manner. At present, the mainstream technical means of fault detection is the data-driven process monitoring method. With the large-scale construction of modern chemical processes and the wide application of advanced instrumentation and computer technology, massive amounts of data can be collected in the production process, which provides a solid data foundation for data-driven process monitoring research. The traditional fault detection method based on the mechanism ...

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): G05B23/02
CPCG05B23/0243G05B2219/24065
Inventor 童楚东俞海珍朱莹
Owner NINGBO UNIV
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