Multi-block fault monitoring method based on fault sensitive slow characteristics

A fault monitoring and slow feature technology, applied in electrical testing/monitoring, testing/monitoring control systems, instruments, etc., to solve the problems that fault monitoring methods cannot be dynamic and large-scale process monitoring.

Active Publication Date: 2020-10-02
JIANGNAN UNIV
View PDF5 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In view of the fact that the above-mentioned existing fault monitoring methods cannot effectively monitor dynamic and large-scale processes, the present invention is proposed

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
  • Multi-block fault monitoring method based on fault sensitive slow characteristics
  • Multi-block fault monitoring method based on fault sensitive slow characteristics
  • Multi-block fault monitoring method based on fault sensitive slow characteristics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0068] refer to figure 1 , provides a schematic diagram of the overall structure of a multi-block fault monitoring method based on fault-sensitive slow features, such as figure 1 , a multi-block fault monitoring method based on fault-sensitive slow features includes steps,

[0069] S1: collect data in the industrial production system, and divide the obtained data into training set and test set;

[0070] S2: Perform slow feature analysis on the training set, and calculate the slow feature transformation matrix;

[0071] S3: Define the fault sensitivity coefficient, and obtain the sensitivity of each slow feature to fault from the coefficient in the slow feature transformation matrix;

[0072] S4: Define the fault sensitivity threshold, select the fault-sensitive slow feature for each dimension variable of the training set, and use it as a training sub-block;

[0073] S5: Calculate the fault statistics for each training sub-block separately, and use the support vector data de...

Embodiment 2

[0150] In order to verify the effectiveness and feasibility of the proposed method, five main units were built on the Tennessee-Eastman (TE) software platform: reactor, condenser, compressor, separator and stripper ,Such as figure 1 As shown, the simulation model contains 22 process measurement variables, 19 component measurement variables, and 12 operation variables. It should be noted that the TE process model is a realistic industrial process created by Eastman Chemical Company and used to evaluate process control and monitoring methods ;A total of 21 different types of faults were preset in the TE process, the types of faults include step change, random change, slow drift, and valve stickiness, of which 16 are known faults and 5 are unknown faults; normal The 960 samples under working conditions are used as the training data set, and the 960 samples under the fault condition are used as the fault test set. The faults are all introduced from the 161st sample point. Table...

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 multi-block fault monitoring method based on fault sensitive slow features, and the method comprises the steps: collecting data in an industrial production system, and dividing the obtained data into a training set and a test set; performing slow feature analysis on the training set, and calculating a slow feature transformation matrix; defining a fault sensitivity degreecoefficient, and obtaining the sensitivity degree of each slow feature to the fault according to the coefficient in the slow feature transformation matrix; defining a fault sensitivity degree threshold value, selecting fault sensitivity slow characteristics of each dimensional variable of the training set, and taking the fault sensitivity slow characteristics as training sub-blocks. According tothe invention, through the analysis of the statistical magnitude calculation formula, the fault sensitivity degree coefficient is defined, the slow features are reordered, the slow feature most sensitive to the fault in the variable direction is selected, the sensitive slow feature of each dimension variable is selected, parallel monitoring is carried out, and effective monitoring in the multi-dimension dynamic and large-scale process can be effectively achieved.

Description

technical field [0001] The technical field of industrial production process fault monitoring and diagnosis that the present invention relates to, in particular to a multi-block fault monitoring method based on fault-sensitive slow features. Background technique [0002] Modern industrial production processes have increasingly high requirements for product quality and safety. If a complex industrial process fails, it will cause huge losses. Therefore, it is very important to effectively monitor the process. With the rapid development of sensing and detection technology, the degree of informatization of industrial production has been continuously improved, and a large amount of production process data has been generated, so the method of multivariate statistical process monitoring (MSPM) has been widely used. Among them, Principal Component Analysis (PCA), Partial Least Squares (PLS) and Independent Component Analysis (ICA) are relatively classic multivariate statistical monit...

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
CPCG05B23/024
Inventor 熊伟丽翟超马君霞
Owner JIANGNAN 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