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

Multi-loop performance diagnosis method based on sparsification variable contribution

A diagnostic method and sparse technology, applied in the direction of instruments, electrical testing/monitoring, control/regulation systems, etc., can solve problems such as unrealized diagnosis, and achieve the effect of reducing the possibility of misdiagnosis

Active Publication Date: 2019-10-25
ZHEJIANG UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method selects a certain period of historical data as the benchmark data, calculates its performance index, and compares it with the performance index of the current data. If the result shows that there is a performance difference, however, the disclosed patent has not realized the effective reason for the performance difference. diagnosis

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
  • Multi-loop performance diagnosis method based on sparsification variable contribution
  • Multi-loop performance diagnosis method based on sparsification variable contribution
  • Multi-loop performance diagnosis method based on sparsification variable contribution

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The present invention will be described in further detail below in conjunction with the accompanying drawings.

[0037] The present invention provides a multi-loop performance diagnosis method based on sparse variable contribution, comprising the following steps:

[0038] (1) Data preparation and preprocessing: first collect a piece of historical data with better performance x h (k), k=1,2,...,N, collect a piece of online data x(k) to be evaluated and diagnosed at the same time, and the length of both pieces of data is N; secondly, de-average the variables of the two pieces of data , the operations of de-averaging the two segments of data are respectively and In the absence of ambiguity, all variables in the subsequent steps refer to the de-averaged data, and x h (k) and x(k) to represent;

[0039] (2) Performance evaluation: first solve the generalized eigendecomposition problem where X = [x(1) x(2) ... x(N)] T ,X h =[x h (1)x h (2) … x h (N)] T , Σ h is...

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 multi-loop performance diagnosis method based on sparsification variable contribution. According to the method, sparsification is performed on a generalized feature vector corresponding to a performance degradation and performance enhancement subspace at first according to a generalized feature decomposition result of reference data and data to be evaluated and diagnosed,to obtain a sparse vector after sparsification. Then, each element in the sparse vector represents the contribution degree of a corresponding loop to the performance change. According to the magnitude of the contribution degree, the key loop causing the performance change can be determined. By means of the method based on the sparsification variable contribution, compared with other existing methods, the multi-loop performance diagnosis method disclosed by the invention has the advantages of being able to improve the accuracy of performance diagnosis in an industrial process, reduce the ambiguity of the diagnosis result, and being more conducive to the automatic implementation of the industrial process.

Description

technical field [0001] The invention relates to the field of process data analysis, in particular to a data-driven control performance diagnosis method, in particular to a multi-loop performance diagnosis method based on the contribution of sparse variables. Background technique [0002] With the development of distributed control systems and information sensing technologies, industrial processes have accumulated a large amount of process historical data. Using data analysis technology to extract effective information to assist decision-making can improve the operating efficiency of the process industry. In particular, as the process system continues to develop toward large-scale development, its accurate mechanism model has become difficult to obtain, and data analysis technology has become an important driving force to promote the development of large-scale industrial systems towards intelligence, digitalization and informationization. [0003] Using the data-driven 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): G05B23/02
CPCG05B23/0262G05B2219/24065
Inventor 王凯宋执环
Owner ZHEJIANG 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