Nonlinear chemical process fault detection method

A chemical process and fault detection technology, which is applied in the direction of program control, comprehensive factory control, and comprehensive factory control, can solve the problems of high computational complexity and low fault detection sensitivity, so as to reduce computational complexity, improve detection performance, and improve Calculating time-consuming effects

Active Publication Date: 2021-08-13
CHINA UNIV OF PETROLEUM (EAST CHINA)
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the above-mentioned problems of high computational complexity and low fault detection sensitivity in the prior art, the present invention provides a non-linear chemical process fault detection method based on stochastic slow feature analysis (SFA for short), which can improve the calculation cost of traditional kernel matrix. When the problem, improve the fault detection sensitivity

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
  • Nonlinear chemical process fault detection method
  • Nonlinear chemical process fault detection method
  • Nonlinear chemical process fault detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0114] Example: see figure 2, take the continuous stirring reactor (hereinafter referred to as CSTR) as an example to illustrate.

[0115] CSTR is a widely used equipment in the chemical industry, where an irreversible exothermic reaction occurs in the reactor to generate new substances. The reaction process involves a total of 4 state variables [C a ,T,T c ,h] and 6 input variables [Q,Q f ,C af ,T f ,Q c ,T cf ], see Table 1 for details. A total of 1000 fault-free data were collected as training data in the simulation, and 6 faults were generated, as shown in Table 1. Each fault contains 1000 samples, and the fault is introduced into the system at the 161st sample.

[0116] Table 1

[0117] Fault describe Amplitude F1 A step change in the flow rate of feed A +3L / min F2 The concentration of the reactor feed A is ramped +3×0(-4)(mol / L) / min F3 The activity of the catalyst is deactivated with a ramp change +3K / min F4 Heat tran...

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 nonlinear chemical process fault detection method which comprises the following specific steps: in an offline modeling stage, firstly performing normalization processing on training data, then constructing M random slow feature analysis models, and solving corresponding dominant subspace statistics and residual space statistics control limits; in the online detection stage, test data are collected and normalized, then the test data are mapped to M random slow feature analysis models, M groups of dominant subspace statistics and residual space statistics are obtained, an integrated monitoring statistic and a statistic BICQ are obtained through a weighted probability index fusion mechanism and are respectively compared with 1-alpha to judge whether a fault occurs or not, wherein alpha is a confidence level. According to the method, the data characteristics of the random Fourier mapping deep excavation nonlinear process are utilized, a nonlinear slow characteristic analysis model can be established more efficiently, and the fault detection effect is improved.

Description

technical field [0001] The invention belongs to the technical field of industrial process detection, and relates to a nonlinear chemical process fault detection technology, in particular to a nonlinear chemical process fault detection method based on random slow feature analysis. Background technique [0002] In the process of modern industrial production, real-time fault detection technology has become an important support for ensuring safe production and improving product quality. Due to various faults such as instrument failure, valve sticking, material leakage, etc. may occur in the production process, these faults may cause measurement deviations and product quality degradation, or even lead to dangerous safety accidents, resulting in equipment damage and casualties. directly affect the normal operation of the enterprise. Therefore, researchers and engineers have been working on advanced process monitoring and fault detection techniques. Among them, data-driven method...

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): G05B19/418
CPCG05B19/41875G05B2219/32252Y02P90/02
Inventor 邓晓刚杜昆玉王晓慧王延江曹玉苹王平
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