An intelligent parsing method for manufacturing big data health information

A technology for health information and intelligent analysis, applied in manufacturing computing systems, data processing applications, and pattern recognition in signals.

Inactive Publication Date: 2019-01-04
FOSHAN UNIVERSITY
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The improvement method of traditional equipment is to improve product performance and reduce cost, but as time goes

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0015] An intelligent analysis method for manufacturing big data health information of the present invention comprises the following steps

[0016] 101. Multi-source signal resampling: receiving multiple time-interleaved input signals from the industrial electromechanical equipment to be monitored; performing parallel filtering on each of the interleaved input signals by using multiple time-interleaved filter coefficients to generate multiple filtering signals; and adding the plurality of filtered signals of a plurality of packets into a plurality of signal streams; wherein each packet in the plurality of packets includes a plurality of filtered signal members, each filtered signal member from the different ones of the plurality of time-interleaved input signals;

[0017] 102. Time-frequency joint analysis: obtain the respective concentrated frequency bands of the target filter signal and non-target filter signal; according to the concentrated frequency band, filter the analog...

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 an intelligent analysis method for manufacturing big data health information. Aiming at fragmentization of historical manufacturing big data, through resampling of multisourcesignals, frequency joint analysis, variable granularity analysis and dimension conversion are used to establish the quality evaluation index, data purification algorithm and deconvolution network of big data in equipment monitoring, so as to realize the purification of big data and the adaptive extraction of complex fault features, in order to realize the intelligent analysis and characterizationtechnology of manufacturing big data health information. Combined with the Deep Learning Theory, a causal relationship between a plurality of health states of a manufacturing process and a monitoringsignal is explored, in order to overcome the congenital defects such as low diagnostic rate and poor robustness of the traditional shallow identification model, the depth identification model of the on-orbit manufacturing process health status is established to describe the health status of the mechanical and electrical equipment in the manufacturing process comprehensively and realize the intelligent identification of multi-mark faults, so as to realize the depth learning and intelligent identification technology of the manufacturing process health status.

Description

technical field [0001] The invention relates to the field of industrial manufacturing big data processing, in particular to an intelligent analysis method for manufacturing big data health information. Background technique [0002] As the market competition continues to intensify, how to improve the competitiveness of industrial electromechanical equipment is the key to the survival of enterprises. The way to improve traditional equipment is to improve product performance and reduce costs. However, as time goes by, the limitations of improving performance and reducing costs become more and more obvious, and innovation is weak. Therefore, how to maintain more mature performance and longer-lasting vitality of existing electromechanical equipment is the direction of future development. Therefore, monitoring the health information of electromechanical equipment is particularly important, and how to intelligently analyze and represent health information requires machine learning...

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
IPC IPC(8): G06Q10/06G06Q50/04G06K9/00
CPCG06Q10/06393G06Q50/04G06F2218/02Y02P90/30
Inventor 张彩霞王向东王新东
Owner FOSHAN UNIVERSITY
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