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

Rectifying tower abnormal state identification method based on brief kernel principal component analysis

A technology of nuclear principal component analysis and abnormal state, which is applied in character and pattern recognition, instruments, computer parts, etc.

Pending Publication Date: 2020-11-10
NINGBO UNIV
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

If the sampling interval is short, using KPCA to implement online identification of the abnormal state of the distillation column will face serious real-time efficiency problems

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
  • Rectifying tower abnormal state identification method based on brief kernel principal component analysis
  • Rectifying tower abnormal state identification method based on brief kernel principal component analysis
  • Rectifying tower abnormal state identification method based on brief kernel principal component analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0057] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0058] Such as figure 1 As shown, the present invention discloses a rectification column abnormal state identification method based on simple nuclear principal component analysis. The specific implementation of the method of the present invention will be described below in conjunction with a specific application example.

[0059] from figure 2 It can be seen from the real picture of the rectification tower in the figure that the rectification tower equipment is not only a single rectification equipment, but also has a supporting reboiler at the bottom and a condenser at the top. from figure 2 It can be seen from the structural diagram in the figure that the measuring instruments of the rectification tower equipment include: flow meter, temperature meter, and liquid level meter. There are 17 variables corresponding to the measurement, incl...

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 rectifying tower abnormal state identification method based on brief kernel principal component analysis, and aims to improve the efficiency of detecting the abnormal state of rectifying tower equipment in real time by using a KPCA method. Specifically, it is better for training a KPCA model by using typical representative sample data rather than by using as many sample data as possible. The method has the advantages and characteristics that part of representative data is screened out through edge point indexes to train the KPCA model, so that the online calculation amount of a kernel vector is greatly reduced. Besides, although part of data is screened, the unselected data is not denied completely, and the data is considered in online monitoring in a detection index construction mode. Finally, through a specific embodiment, it is verified that the calculation efficiency of the method is improved, and meanwhile, the identification capability for the abnormal state is not reduced.

Description

technical field [0001] The invention relates to a method for monitoring the running state of a chemical process, in particular to a method for identifying an abnormal state of a rectifying tower based on simple nuclear principal component analysis. Background technique [0002] Since computer technology and advanced measuring instrument technology are widely used in chemical production, the temperature, pressure, flow and other data information in the chemical production process can be measured and stored in real time. These massive sample data provide a solid data foundation for the current chemical intelligent manufacturing . In the past ten years, the use of sampling data to detect abnormal states in the operation of chemical processes has received more and more attention in the field of safe chemical production. After more than ten years of development, a set of multivariate analysis algorithms such as Principal Component Analysis (abbreviation: PCA) and partial least s...

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
IPC IPC(8): G06K9/62
CPCG06F18/2135G06F18/22G06F18/24
Inventor 蓝艇其他发明人请求不公开姓名
Owner NINGBO UNIV
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