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

A method and system for monitoring industrial system conditions based on static and dynamic joint analysis

A technology of joint analysis and working conditions, applied in neural learning methods, character and pattern recognition, instruments, etc., can solve problems such as inapplicability, and achieve the effect of improving accuracy and enhancing robustness

Active Publication Date: 2022-05-06
CENT SOUTH UNIV
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Dobos et al. proposed a dynamic PCA-based multivariate process condition division method, but it needs to set the number of conditions and the value of the maximum segmentation error, which is not applicable in practice

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
  • A method and system for monitoring industrial system conditions based on static and dynamic joint analysis
  • A method and system for monitoring industrial system conditions based on static and dynamic joint analysis
  • A method and system for monitoring industrial system conditions based on static and dynamic joint analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] With the increasing complexity of industrial systems, the correct working conditions cannot be accurately distinguished from the static or dynamic characteristics alone. Only by including both into the analysis can the characteristics of the changing working conditions be more truly reflected. On the other hand, with the continuous operation of industrial processes, a lot of new unknown working condition information will appear. Because the traditional division method cannot update the model, a wrong division result may be obtained for unknown working conditions, which will affect the follow-up monitoring and control effect.

[0044] Inspired by the needs of the above-mentioned actual industrial process, this patent proposes an incremental working condition division method based on static and dynamic joint analysis. First, the method of the present invention comprehensively considers the static and dynamic characteristics of the industrial process, and can effectively g...

Embodiment 2

[0101] This embodiment provides an industrial system working condition monitoring system based on static and dynamic joint analysis, including a feature extraction module, a SOM network training module, a control limit calculation module and a working condition change time point judgment module;

[0102] The feature extraction module is used to: obtain an industrial process data sequence of a stable working condition i=A before the current industrial process, the industrial process data of each sampling point is used as a training data sample, and the training data is extracted using the slow feature analysis method The static eigenvector s and dynamic eigenvector of the sample

[0103] The SOM network training module is used to: use the static feature vector s of all training data samples to train 1 SOM network, obtain the static SOM network corresponding to the stable working condition i=A, and add it to the static SOM network group SOM sta ;Remember the static SOM network...

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 method and system for monitoring working conditions of an industrial system based on static and dynamic combined analysis. The method is as follows: aiming at an industrial process data sequence of a stable working condition, using slow feature analysis method to extract the static and dynamic features of samples; Use static and dynamic features to train initial static and dynamic SOM networks respectively; use static and dynamic SOM network weights and inputs to calculate sample quantization errors, and calculate static and dynamic control limits for current working conditions; obtain industrial process data online and extract its static and dynamic features, respectively calculate the quantization error with the static / dynamic SOM network, compare with the static and dynamic feature discrimination control limits, and judge whether the working condition changes at the current time point of the industrial process. If there is a change, use the new data to train the new static With the dynamic SOM network, if there is no change, the sample is used to update the existing SOM network weights. The present invention can more truly and accurately judge the change time point of the working condition of the industrial process.

Description

technical field [0001] The invention belongs to the technical field of working condition classification, and in particular relates to an industrial system working condition monitoring method and system based on static and dynamic combined analysis. Background technique [0002] Nowadays, industrial field equipment is becoming more and more complex, affected by the internal mechanism and external environment, it will be in different working modes during its operation. Under different working conditions, the corresponding monitoring indicators and control strategies will be completely different. For example, for a motor system, when the load changes, its normal operating current and set speed will inevitably change accordingly, which requires the monitoring model and controller to complete the switching of the working mode according to the change of the motor working condition. If the corresponding working conditions cannot be clarified in time, false positives and false posi...

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 Patents(China)
IPC IPC(8): G06K9/62G06N3/04G06N3/08
CPCG06N3/04G06N3/08G06F18/213G06F18/214
Inventor 黄科科韦可阳春华李繁飙李勇刚朱红求
Owner CENT SOUTH 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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com