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

Equipment fault early warning method and system based on multi-modal sensitive feature selection fusion

A technology for sensitive features and equipment failures, applied in nuclear methods, alarms, character and pattern recognition, etc., can solve problems such as low accuracy rate and narrow application range, so as to improve accuracy rate, solve feature failure, and realize early detection and early detection The effect of maintenance

Active Publication Date: 2021-08-13
ZHENGZHOU UNIVERSITY OF LIGHT INDUSTRY
View PDF13 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005]Aiming at the deficiencies in the above-mentioned background technology, the present invention proposes an equipment failure early warning method and system based on multimodal sensitive feature selection and fusion, which solves the existing The early warning system based on single-mode features has technical problems of low accuracy and narrow application range

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
  • Equipment fault early warning method and system based on multi-modal sensitive feature selection fusion
  • Equipment fault early warning method and system based on multi-modal sensitive feature selection fusion
  • Equipment fault early warning method and system based on multi-modal sensitive feature selection fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0076] Example 1, such as figure 1 As shown, a method for early warning of equipment failure based on multi-modal sensitive feature selection and fusion, the specific steps are as follows:

[0077] Step 1: Collect the parameter operation data of the normal state of the equipment under different working conditions, where the parameter operation data includes vibration data, acoustic emission data, temperature data, video monitoring data, electrical signal data and thermal imaging data; during the long-term operation of the equipment In the process, historical sample data is accumulated, including vibration data, acoustic emission data, electrical signal data, video surveillance data, and thermal imaging data. Through data regularization, data cleaning and denoising, removal of outliers and missing values, etc., high-quality structured data is formed, and a multi-modal database that can be retrieved at any time is established. The multimodal database constructed such as figur...

Embodiment 2

[0127] Example 2, such as Figure 5 As shown, a device failure early warning system based on multimodal sensitive feature selection and fusion, including multimodal data acquisition module, industrial Internet of things data transmission module, database module, data format standardization and data statistics information visualization module, multimodal State feature extraction module, feature visualization module and early warning module; the multimodal data acquisition module is connected with the industrial Internet of Things data transmission module, the industrial Internet of Things data transmission module is connected with the database module, and the database module is respectively connected with the data format standardization and The data statistical information visualization module is connected with the multimodal feature extraction module, the multimodal feature extraction module is connected with the feature visualization module, and the feature visualization modul...

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 provides an equipment fault early warning method and system based on multi-modal sensitive feature selection fusion, which are used for solving the technical problems of low accuracy and narrow application range of an early warning system based on single-modal features. The method comprises the following steps: firstly, extracting a feature vector of collected parameter operation data of a normal state of historical equipment, and standardizing the feature vector; secondly, obtaining sensitive features of the standardized feature data by using kernel PCA based on a Mercer kernel, and training a GMM according to the sensitive features; then obtaining real-time state data of the equipment during operation on line, and selecting multi-mode sensitive features according to the steps; and finally, inputting the multi-modal sensitive features into a trained GMM model, and determining whether to give an alarm according to whether the obtained probability value is smaller than a preset threshold value. According to the invention, through selection and fusion of the multi-modal features of the equipment, the accuracy of an equipment fault early warning system is improved, and off-line early warning model construction and on-line real-time fault early warning are realized.

Description

technical field [0001] The invention relates to the technical field of equipment failure early warning, in particular to an equipment failure early warning method and system based on selection and fusion of multi-modal sensitive features. Background technique [0002] Equipment maintenance costs account for a large proportion of equipment output income. Traditional equipment maintenance methods use regular maintenance and after-the-fact maintenance: the former will increase unnecessary maintenance costs, and the latter will cause long-term equipment downtime and affect product quality and delivery time. The condition-based maintenance method based on big data can issue early warnings in the early stages of fault formation, provide sufficient buffer time for early maintenance measures, avoid catastrophic major accidents, and change passive to active, thereby reducing the maintenance cost of enterprise equipment. [0003] Conventional big data-based condition-based maintenance...

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): G06K9/62G06N3/04G06N20/10G06Q10/00G06Q10/06G08B21/18
CPCG06N20/10G06Q10/20G06Q10/0639G08B21/185G06N3/045G06F18/2135G06F18/253G06F18/214
Inventor 张玉彦文笑雨李浩王昊琪孙春亚乔东平
Owner ZHENGZHOU UNIVERSITY OF LIGHT INDUSTRY
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