Check patentability & draft patents in minutes with Patsnap Eureka AI!

Chemical process fault detection method comprising missing data

A chemical process and fault detection technology, which is applied in complex mathematical operations, instruments, character and pattern recognition, etc., can solve problems such as non-Gaussian information modeling, poor stability, and lack of consideration of missing data.

Active Publication Date: 2018-12-07
ZHEJIANG UNIVERSITY OF SCIENCE AND TECHNOLOGY
View PDF5 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The current iterative autoregressive dynamic hidden variable model based on the probability generation model only extracts the Gaussian information of the sampled data set, but does not model the non-Gaussian information in the data.
Moreover, the problem of missing data is not considered, the detection efficiency is low, and the stability is poor

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
  • Chemical process fault detection method comprising missing data
  • Chemical process fault detection method comprising missing data
  • Chemical process fault detection method comprising missing data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0132] refer to figure 1 , this method is a chemical process fault detection method that includes missing data. This method is aimed at the problem of chemical process fault detection. Regression dynamic hidden variable model, namely: independent component analysis - recursive autoregressive dynamic hidden variable model (or independent component analysis - iterative autoregressive dynamic hidden variable model). The model structure is estimated by the expectation maximization algorithm. On this basis, based on this model, three monitoring statistics I 2 , T 2 , SPE and their corresponding statistical limits and SPE limit . To monitor the newly sampled process data, the existing model structure can be used to estimate the corresponding characteristic variables of the test samples, and the corresponding statistics can be calculated, and the final fault detection results can be obtained.

[0133] A kind of chemical process fault detection method comprising missing data of...

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 chemical process fault detection method comprising missing data. The chemical process fault detection method utilizes an iterative learning method based on independent component analysis and autoregressive dynamic hidden variables, establishes an effective chemical dynamic process fault detection model, overcomes the problem of missing values existing in measured data inactual industrial processes, and improves the online monitoring efficiency and performance of the chemical process, thereby making the industrial chemical process more stable and the product quality monitoring more reliable.

Description

technical field [0001] The invention belongs to the field of chemical production process control, in particular to a chemical process fault detection method including missing data. Background technique [0002] In modern industry, with the increasing popularity of machine learning and big data, these theories have made some progress in industrial control, and the widespread use of distributed control systems has made multivariate statistical process monitoring (MSPM) a An integral part of the control system. For a modern chemical industrial process, measured variables such as temperature, pressure, and flow are sampled based on time intervals, so they have strong autocorrelation, so dynamic process modeling is required. [0003] In order to extract the autocorrelation of measured variables, the traditional dynamic model has dynamic principal component analysis (DPCA) using the extended matrix method. After this innovative work, the extended matrix has become a common metho...

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): G06K9/62G06F17/16
CPCG06F17/16G06F18/2134G06F18/214
Inventor 周乐余家鑫介婧张淼郑慧
Owner ZHEJIANG UNIVERSITY OF SCIENCE AND TECHNOLOGY
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com