Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Non-stationary dynamic process anomaly monitoring method based on dynamic stationary subspace analysis

A dynamic stationary sub and dynamic process technology, applied in complex mathematical operations and other directions, can solve the problem of non-stationary variables being unequal or greater than first-class

Pending Publication Date: 2020-12-11
SHANDONG UNIV OF SCI & TECH
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the actual process, the order of cointegration of non-stationary variables may be unequal or greater than one, which poses some challenges to existing methods

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-stationary dynamic process anomaly monitoring method based on dynamic stationary subspace analysis
  • Non-stationary dynamic process anomaly monitoring method based on dynamic stationary subspace analysis
  • Non-stationary dynamic process anomaly monitoring method based on dynamic stationary subspace analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0076] The specific embodiment of the present invention will be further described below in conjunction with accompanying drawing and specific embodiment:

[0077] Such as figure 1 As described above, a non-stationary dynamic process anomaly monitoring method based on dynamic stationary subspace analysis includes an offline training phase and an online monitoring phase.

[0078] In the offline training phase, according to the operation history data of the non-stationary dynamic process under normal working conditions, an optimization problem is established, and the alternating direction multiplier method is used to solve it and obtain a stable projection matrix, and then construct monitoring statistics, and use the kernel density estimation method to determine the control limit;

[0079] In the online monitoring stage, according to the real-time operation data of the non-stationary dynamic process, the real-time monitoring statistics are calculated, and the real-time monitorin...

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-stationary dynamic process anomaly monitoring method based on dynamic stationary subspace analysis, and particularly relates to the field of industrial process anomaly monitoring. On the basis of a stationary subspace analysis method, the dynamic relationship of process data is modeled by introducing a time shifting technology, and the dynamic stationary subspace analysis method suitable for monitoring a non-stationary dynamic process is provided. An estimation problem of a stable projection matrix is described as an optimization problem, and the problem is solvedby using an alternating method multiplier method. A Mahalanobis distance is used as monitoring statistics to monitor stable components of augmented data. The dynamic characteristics of the process data can be effectively modeled, so that the monitoring performance of the non-stationary dynamic process is improved. Compared with a method based on co-integration analysis, the method can be suitablefor the condition that the co-integration orders of non-stationary variables are unequal or larger than one, and therefore the method has a wider application range.

Description

technical field [0001] The invention belongs to the field of industrial process abnormality monitoring, in particular to a non-stationary dynamic process abnormality monitoring method based on dynamic stationary subspace analysis. Background technique [0002] With the increasing demand for system safety and production efficiency, process monitoring techniques have attracted extensive attention from both academia and industry in the past few decades. Among all monitoring methods, data-driven process monitoring technology is one of the most important branches. The data-driven method extracts key features from process data, and then constructs monitoring statistics to realize the task of process monitoring. With the rise of smart manufacturing and industrial Internet of Things, modern industry is entering the era of big data, which greatly promotes the development and application of data-driven methods. [0003] Traditional monitoring algorithms usually have an inherent assu...

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): G06F17/16G06F17/15
CPCG06F17/16G06F17/15Y02P90/02
Inventor 周东华吴德浩陈茂银纪洪泉高明
Owner SHANDONG UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com