Improved-Fisher-based chemical process fault diagnosis method

A chemical process and fault diagnosis technology, applied in the chemical process fault diagnosis, based on the improved nuclear Fisher's chemical process fault diagnosis field, can solve the problems of fuzzy, aliased data classification, etc., to improve the distribution, facilitate the classification, improve the classification The effect of accuracy

Active Publication Date: 2017-01-11
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF2 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to propose a chemical process fault diagnosis method based on improved Kernel Fisher in view of the problem that the m

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
  • Improved-Fisher-based chemical process fault diagnosis method
  • Improved-Fisher-based chemical process fault diagnosis method
  • Improved-Fisher-based chemical process fault diagnosis method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0034] A chemical process fault diagnosis method based on improved Kernel Fisher proposed by the present invention is based on the Kernel Fisher method, and is improved from the two aspects of inter-class dispersion and boundary data classification method, which improves the accuracy of fault diagnosis . figure 1 It is a chemical process fault diagnosis method based on the improved Kernel Fisher of the present invention, which also includes a flow chart of corresponding steps in this embodiment.

[0035] From figure 1 It can be seen that the present invention comprises the following steps:

[0036] Step A, input raw data;

[0037] Step B, normalize processing, and output training set and test set;

[0038] Step C, for different types of data output in step B, perform the following operations respectively:

[0039] C.1 Use the cross-validation method to select the kernel parameters for the data in the training set, and obtain the kernel Fisher method for improving the class...

Embodiment 2

[0073] In order to test the effectiveness of the fault diagnosis method proposed by the present invention and the detailed steps in Embodiment 1, this embodiment uses the Tennessee-Eastman (TE) process to verify the correctness of the present invention and Embodiment 1. As the data source of various statistical data analysis algorithms, TE process has been widely recognized and used. The TE process includes five main process units: reactor, condenser, compressor, separator, and stripper, as well as 12 controlled variables, 41 observed variables, and 20 types of typical faults. For a detailed introduction to the TE process, see the literature: In 2010, Wang Ting, titled "Research on Real-time Optimization Technology for TE Process".

[0074] In this embodiment, faults 4, 9, and 11 are selected for relevant experimental verification, and characteristic variables {51, 9} among 53 characteristic variables are selected to form each fault sample. For each type of fault type, two se...

Embodiment 3

[0083] TE process fault diagnosis, a total of 21 types of faults, these 21 types of faults are pre-set, of which the first 7 types of faults are all steps, and the 3rd, 4th, 5th, and 7th types of faults are selected as the research objects . For each fault type, two sets of data are taken, namely training data and test data, each set of data has 100 samples, and each sample is composed of all 52 feature variables. The training set and test set each contain 400 samples.

[0084] The kernel Fisher projection is used for the training set samples, and the obtained projection images on the first and second characteristic axes are as follows: Figure 4 As shown, the kernel parameter δ is set to 200. Figure 4 , the abscissa is the first characteristic axis, and the ordinate is the second characteristic axis; the circle represents fault 3, the five-pointed star represents fault 4, the triangle represents fault 5, and the square represents fault 7. In the same way, the kernel Fishe...

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 provides an improved-Fisher-based chemical process fault diagnosis method. The method comprises: step one, original chemical process fault diagnosis are collected and normalization processing is carried out on the data, wherein the data are classified into a training set and a testing set; step two, the training seat is inputted into an improved class-separation-distance kernel Fisher method, a threshold parameter is outputted, and a parameter of a Gaussian radial basis function is selected optimally by using a cross validation method; step three, the testing set outputted at the step one is inputted into the improved class-separation-distance kernel Fisher method to carry out projection; and step four, according to the threshold parameter outputted at the step two, whether the data are boundary points after projection at the step three is determined and a fault type is determined by combining an improved K-NN algorithm based on a mahalanobis distance. According to the method, distribution of sampling data in projection space is improved; and with introduction of a boundary threshold parameter and combination of the mahalanobis distance and the improved K-NN algorithm, the classification accuracy of the total samples is increased under the circumstance that the classification time is minimized.

Description

technical field [0001] The invention relates to a fault diagnosis method of a chemical process, in particular to a fault diagnosis method of a chemical process based on an improved Kernel Fisher, and belongs to the technical field of automatic detection. Background technique [0002] Modern chemical processes are characterized by large scale, high complexity, multiple variables and operating under closed-loop control. However, there are many unsafe factors in the chemical process, which are more dangerous than other productions. If some minor faults occur in the equipment of the chemical process and cannot be eliminated in time, it may cause the entire production process to not work normally and cause certain damage. loss of human and financial resources. Therefore, it is very important to ensure the safe and reliable operation of the chemical process, and fault diagnosis is the most important means. Fault diagnosis technology monitors the operating status of the productio...

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
CPCG06F18/2413
Inventor 徐发富马立玲王军政沈伟汪首坤李静
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
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