Linear-nonlinear industrial process fault detecting method based on linear evaluation factors

A technology for evaluating factors and fault detection, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve problems such as the inability to accurately describe the linear-nonlinear process information of complex systems

Active Publication Date: 2018-11-16
CHINA UNIV OF PETROLEUM (EAST CHINA)
View PDF5 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Aiming at the problem that the traditional industrial process monitoring method cannot accurately describe the linear-nonlinear process information contained in the complex system, the present invention provides a linear-nonlinear industrial process fault detection method based on linear evaluation factors

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
  • Linear-nonlinear industrial process fault detecting method based on linear evaluation factors
  • Linear-nonlinear industrial process fault detecting method based on linear evaluation factors
  • Linear-nonlinear industrial process fault detecting method based on linear evaluation factors

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0171] Embodiment one: at first, design the numerical system that contains 8 variables, its structure is as follows:

[0172] x 1 =u+e 1

[0173] x 2 =-2x 1 +1+e 2

[0174] x 3 = u 2 -3u+e 3

[0175]

[0176] x 6 =2x 5 +1+e 6

[0177] x 7 =sin(8πu)+e 7

[0178]

[0179] Among them, the data source signal u obeys the uniform distribution U(0, 2), e 1 ~e 8 8 independent noises with zero mean and 0.01 variance. Firstly, 500 sets of normal data are simulated as a training set for historical modeling. In addition, two sets of data containing faults are simulated as the test set, and each set of data contains 500 samples. Fault 1: variable x is given at the 201st moment 5 Add a step fault with an amplitude of 0.3.

[0180] The above-mentioned fault detection method of the present invention (hereinafter referred to as the LEF method) is used to detect the fault of the linear-nonlinear numerical system described in this embodiment. After the fault is detec...

Embodiment 2

[0188] Embodiment 2: Tennessee-Eastman (hereinafter referred to as: TE) process is an experimental platform established by Downs and Vogel of Eastman Chemical Company of the United States according to an actual chemical process, and is now widely used to verify control algorithms and process monitoring pros and cons of the method. see image 3 , the TE process is mainly composed of five units, including reactor, product condenser, gas-liquid separator, cycle compressor and stripper. There are 53 variables in the TE process, including 22 continuous measurement variables, 19 component variables and 12 operational variables. In this embodiment, referring to Table 3, 33 variables in the TE process are selected; referring to Table 4, there are 21 faults in total.

[0189] table 3

[0190] variable label

variable description

variable label

variable description

1

A feed (stream 1)

18

Stripper temperature

2

D feed (stream 2)

19

...

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 relates to a linear-nonlinear industrial process fault detecting method based on linear evaluation factors. The linear-nonlinear industrial process fault detecting method comprises the steps that firstly, normalization processing is conducted on training data and testing data; secondly, the linear evaluation factor LEF (xi, xj) is defined, different correlations of variables are measured through the linear evaluation factor LEF (xi, xj), linear and non-linear blocks in the industrial process are divided by the linear evaluation factor, the correlations of local variables can be described in more detail; on this basis, a PCA model and a KPCA model are respectively established in different sub-blocks, and the information of all blocks is fused; whether a fault occurs or not isjudged according to the statistical amount after fusion, thus fault detection results are improved, and the fault detection rate is improved.

Description

technical field [0001] The invention belongs to the technical field of complex industrial process fault detection, and relates to a linear-nonlinear mixed industrial process fault detection method based on a linear evaluating factor (LEF for short). Background technique [0002] Due to the increasing scale of modern industrial systems, fault diagnosis of industrial processes has become a key technology to ensure the safe and stable operation of modern industrial systems. With the development of modern computer control technology, a wealth of process data is collected and stored in industrial processes. Therefore, data-driven fault detection methods have gradually become a research hotspot in the field of industrial process monitoring. For online linear industrial process monitoring, the classic method is principal component analysis (PCA) method. Aiming at the problem of industrial process monitoring of nonlinear industrial systems, the researchers further proposed the Ker...

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): G06F17/50G06K9/62
CPCG06F30/20G06F18/2135G06F18/25
Inventor 邓晓刚邓佳伟王磊曹玉苹
Owner CHINA UNIV OF PETROLEUM (EAST CHINA)
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