Mechanical multidimensional big data processing method based on tensor decomposition

A technology of big data processing and tensor decomposition, applied in the field of big data processing, can solve problems such as differences in data processing methods, failure to achieve expected results, failure to run, etc., and achieve the effect of reducing the dimensionality of data

Inactive Publication Date: 2018-07-10
BEIJING UNIV OF CIVIL ENG & ARCHITECTURE
View PDF9 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The sparsity of high-dimensional data leads to significant differences in data processing methods in high-dimensional space and low-dimensional space
Many mature algorithms in the traditional low-dimensional space cannot achieve the expected results or even run in the high-dimensional space

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
  • Mechanical multidimensional big data processing method based on tensor decomposition
  • Mechanical multidimensional big data processing method based on tensor decomposition
  • Mechanical multidimensional big data processing method based on tensor decomposition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] The present invention will be described in detail below by taking the vibration signal collected in the gearbox as an example to reduce the noise of the signal by constructing a multi-dimensional tensor model. The complete flowchart of the invention is as follows figure 1 As shown, the specific process is:

[0029] 1. Signal acquisition. The acceleration vibration sensor is used to collect the time domain vibration signal of the gearbox. In this embodiment, the equipment is driven by a 3HP motor, the experimental gear is installed on the input shaft connected to the motor, and the VQ data acquisition system (including computer, data acquisition instrument and NI acquisition card) is used to install it on the 2-level parallel shaft. A piezoelectric accelerometer on the gearbox collects vibration data inside the gearbox. The experimental gear used in the experiment is a root cracked gear. The input shaft rotation frequency is 49.78Hz when the vibration signal is collec...

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 a mechanical multidimensional big data processing method based on tensor decomposition. The method comprises the steps of signal acquisition, frequency domain information construction, tensor model construction, truncation parameter selection, target tensor reconstruction and the like. According to the invention, a signal is modeled into a tensor form, the big data problem in a high dimensional space can be solved by a tensor tool, and multidimensional signal processing is perform efficiently and reliably by using the processing method based on tensor decomposition through simple vibration signal measurement.

Description

technical field [0001] The invention relates to the field of big data processing, in particular to a mechanical multi-dimensional big data processing method based on tensor decomposition. Background technique [0002] In recent years, with the expansion of the scope of human exploration, the scope of data recording has rapidly expanded, and a large amount of data has been accumulated. In the field of mechanical fault diagnosis, due to the wide distribution of mechanical equipment, numerous measuring points, high data sampling frequency, and long service life, a large amount of multi-dimensional diagnostic data has been obtained. Mining useful information components from big data is the key to fault diagnosis. [0003] With the continuous and rapid development of multi-dimensional data, it is inevitable that a large amount of data will be processed in high-dimensional space in the future. This patent proposes to model the collected multi-channel vibration signals into a ten...

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): G01M13/02
CPCG01M13/028
Inventor 王衍学胡超凡杨建伟姚德臣
Owner BEIJING UNIV OF CIVIL ENG & ARCHITECTURE
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