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

Equipment degeneration multi-source data fusion method based on improved variational automatic coding

A multi-source data, automatic coding technology, applied in electrical digital data processing, special data processing applications, complex mathematical operations, etc., can solve the problem of large uncertainty in the early stage, loss of prior information of fusion results, and small uncertainty in the final stage. and other problems, to achieve the effect of low volatility, guaranteed robustness, and low uncertainty

Active Publication Date: 2018-11-27
XI AN JIAOTONG UNIV
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the degradation features used for remaining life prediction often have a heteroscedastic data structure with relatively large uncertainty in the early stage and relatively small uncertainty in the end stage
The above methods often lose the prior information of the heteroscedasticity of the fusion results

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 degeneration multi-source data fusion method based on improved variational automatic coding
  • Equipment degeneration multi-source data fusion method based on improved variational automatic coding
  • Equipment degeneration multi-source data fusion method based on improved variational automatic coding

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The present invention is described in further detail below:

[0036] A multi-source data fusion method for equipment degradation based on improved variational auto-encoding. When the prior fusion results of non-linear and degraded multi-source data of equipment are obviously right-biased, the lognormal distribution is used to replace the original standard normal distribution. , construct the corresponding cost function regularization expression, combine data normalization and model batch training and other processes to obtain the fusion result of degenerated multi-source data, this method ensures the right-biasedness of the data.

[0037] Specifically include the following steps:

[0038] Step 1: Construct a lognormal distribution variational autoencoder network model including "encoding-resampling-decoding" three-layer network structure, "encoding-resampling-decoding" three-layer network structure, and its encoding layer contains "mean" network and the "variance" vari...

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 equipment degeneration multi-source data fusion method based on improved variational automatic coding. The logarithmic normal distribution is used as the prior distributionof hidden variables of a variational automatic encoder to construct a corresponding cost function regularization expression, and data normalization and model batch processing training are combined toobtain fusion results of degenerated multi-source data. The equipment degeneration multi-source data fusion method based on improved variational automatic coding uses the logarithmic normal distribution as the prior distribution of the hidden variables of a variational automatic encoder and constructs the corresponding normalization express so as to retain heteroscedasticity prior information of adegenerate state.

Description

technical field [0001] The invention relates to the field of degradation modeling and remaining life prediction, in particular to a multi-source data fusion method for equipment degradation based on improved variational automatic coding. Background technique [0002] With the continuous development of science and technology and industrial level, the structure of mechanical equipment is becoming more and more complex, the working environment is increasingly demanding, and users have higher and higher requirements for the reliability and safety of mechanical equipment. Therefore, it is of great significance to effectively extract the degradation state of mechanical equipment and timely discover the abnormal state information of equipment operation to ensure the safe and reliable operation of mechanical equipment. [0003] The degradation information of mechanical equipment is often contained in the equipment status information obtained by multi-source and multi-physical sensor...

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): G06F17/50G06F17/18
CPCG06F17/18G06F30/20G06F2119/04
Inventor 陈景龙平根訾艳阳
Owner XI AN JIAOTONG 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