A Batch Process Fault Monitoring Method Based on Fourth Moment Singular Value Decomposition

A singular value decomposition and fault monitoring technology, applied in the field of fourth-order moment singular value decomposition technology, can solve problems such as the destruction of structural information between data and the influence of fault diagnosis.

Active Publication Date: 2021-07-02
BEIJING UNIV OF TECH
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The kernel can map data to high dimensions, but at the same time, the structural information between data will be destroyed, which will have a certain impact on fault diagnosis

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 Batch Process Fault Monitoring Method Based on Fourth Moment Singular Value Decomposition
  • A Batch Process Fault Monitoring Method Based on Fourth Moment Singular Value Decomposition
  • A Batch Process Fault Monitoring Method Based on Fourth Moment Singular Value Decomposition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0061] The algorithm proposed in this paper can monitor the faults that occur in the production of industrial batch processes. By processing the fourth moment of variables, performing singular value decomposition, constructing statistics and corresponding control lines to complete the monitoring. Finally, satisfactory monitoring results can be obtained to ensure the safety of production.

[0062] In order to verify the accuracy of the algorithm proposed in this paper, a test was carried out using TE process data. TE (TenesseeEastman) simulation platform is a simulation platform based on the actual chemical reaction process. The data generated by it has time-varying, strong coupling and nonlinear characteristics, and is widely used to test the control and fault diagnosis models of complex industrial processes.

[0063] There are 21 kinds of faults in the TE process, the specific description is shown in Table 1

[0064] Table 1 TE process failure list

[0065] fault...

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 an intermittent process fault monitoring method based on fourth-order moment singular value decomposition, which is used to solve the nonlinearity of data in the intermittent process and the non-Gaussian property brought by the nonlinearity. The present invention includes two stages: "offline modeling stage" and "online monitoring stage". The "offline modeling stage" includes: first, standardize the data, perform fourth-order moment processing, and combine the fourth-order moment matrix; then perform singular value decomposition, simplify the obtained matrix, and prepare for monitoring. The "online monitoring stage" includes: standardizing the online data, performing fourth-order moment processing, and combining fourth-order moment matrices; then calculating statistics, residuals, and corresponding control lines; finally, using statistics to monitor the generation process, when it is found that An alarm is generated when a fault occurs. The present invention fully considers the nonlinear and non-Gaussian nature of intermittent process data, reduces the false alarm rate in the normal stage, reduces the false alarm rate in the fault stage, and accelerates the response speed, and has high practical value.

Description

technical field [0001] The invention belongs to the field of industrial process fault monitoring, and in particular relates to a fourth-order moment singular value decomposition technology. The method for fault monitoring based on the fourth-order moment singular value decomposition of the present invention is a specific application in the TE (Tenessee Eastman) process. Background technique [0002] There are a large number of batch processes in modern industrial processes. Common batch processes include microbial pharmaceuticals, sewage treatment, beer preparation, yogurt preparation, etc. The production batch size of the batch process is relatively flexible, and the process change is relatively easy. At the same time, it has certain compatibility for product switching, and can produce a small amount of different varieties, and can quickly adapt to changes in raw materials or operating conditions. [0003] Most industrial process data has strong nonlinearity. Due to the no...

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): G05B19/418G06F17/16
CPCG05B19/41885G05B19/41875G06F30/20Y02P90/02
Inventor 常鹏卢瑞炜张祥宇王普
Owner BEIJING UNIV OF TECH
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