Industrial process fault diagnosis system and method based on wavelet analysis

A fault diagnosis system and industrial production technology, applied in the direction of total factory control, total factory control, electrical program control, etc., can solve the problems that fault diagnosis is difficult to obtain better diagnostic results, and does not take into account the multi-scale characteristics of the process, etc.

Inactive Publication Date: 2007-07-11
ZHEJIANG UNIV
View PDF0 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the current fault diagnosis methods often only consider the multicollinearity and nonlinear characteristics of industrial processes, but do not consider the multi-scale characteristics of the process. It is often difficult to obtain better fault diagnosis methods for complex industrial processes that are seriously affected by multi-scale characteristics. Diagnostic effect

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
  • Industrial process fault diagnosis system and method based on wavelet analysis
  • Industrial process fault diagnosis system and method based on wavelet analysis
  • Industrial process fault diagnosis system and method based on wavelet analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0086] With reference to Fig. 1, Fig. 2, Fig. 3 and Fig. 4, a kind of industrial production process fault diagnosis system based on wavelet analysis, comprises field intelligent instrument 2, DCS system and host computer 6 connected with industrial process object 1, described DCS The system consists of a data interface 3, a control station 4, and a database 5; the smart instrument 2, the DCS system, and the host computer 6 are sequentially connected through a field bus, and the host computer 6 includes:

[0087] The standardization processing module 7 is used to standardize the data. The mean value of each variable is 0 and the variance is 1 to obtain the input matrix X. The following process is used to complete:

[0088] 1) Calculate the mean: TX ‾ = 1 N Σ i = 1 N TX i ...

Embodiment 2

[0177] With reference to Fig. 1, Fig. 2, Fig. 3 and Fig. 4, a kind of industrial production process fault diagnosis method based on wavelet analysis, described fault diagnosis method comprises the following steps:

[0178] (1), determine the used key variable of fault diagnosis, collect the data of described variable when system is normal and fault respectively from the history database of DCS database as training sample TX;

[0179] (2), in wavelet decomposition module 8, principal component analysis module 9 and support vector machine classifier module 11, set respectively the parameters such as wavelet decomposition layer number, principal component analysis variance extraction rate, support vector machine kernel parameter and confidence probability, Set the sampling period in DCS;

[0180] (3), the training sample TX is in the upper computer 6, and the data is standardized, so that the mean value of each variable is 0, and the variance is 1, and the input matrix X is obtai...

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

An industrial production process diagnostic system based on small wave analysis comprises industrial process object connected on site intelligent meter, DCS system and its upper position control machine with the DCS system made of data interface, control station, data base, the intelligent meter, DCS system and the upper position control machine connected sequentially, with the said upper position control machine composed of standardized handling module, small wave dissolving module, pivot element analysis function module, small wave restructuring module, support vector machine classifier module and diagnostic judging module. It also puts forward a failure diagnostic method. It provides an industrial production process failure diagnostic system and method with good diagnostic effect based on small wave analysis.

Description

(1) Technical field [0001] The invention relates to the field of industrial process fault diagnosis, in particular to a wavelet analysis-based industrial production process fault diagnosis system and method. (2) Background technology [0002] Due to the requirements of product quality, economic benefits, safety and environmental protection, industrial processes and related control systems have become very complex. In order to ensure the normal operation of industrial systems, fault diagnosis and detection play a very important role in industrial processes. In recent years, the application of statistical analysis to process monitoring and fault diagnosis has been extensively studied. [0003] Using industrial measured data, using statistical methods for fault diagnosis, avoiding complex mechanism analysis, and relatively convenient solution. Since the industrial process has multi-scale characteristics in nature, such as the spatial multi-scale characteristics of micro- and m...

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
CPCY02P90/02
Inventor 刘兴高阎正兵
Owner ZHEJIANG UNIV
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