Method and device for predicting life of mechanical component of electric drive assembly

A mechanical component and life prediction technology, applied in the testing of mechanical components, testing of machine/structural components, measuring devices, etc., can solve problems such as inability to replace and maintain mechanical components, wear and aging of mechanical components, easy judgment errors, etc., to achieve The effect of reducing the probability of instrument maintenance delays

Inactive Publication Date: 2019-09-13
UNIV OF ELECTRONICS SCI & TECH OF CHINA ZHONGSHAN INST
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] At present, with the development of technology, mechanical industrial production has been widely used and developed rapidly, replacing most of the labor force and improving production efficiency, but at the same time, long-term electric-driven mechanical production will cause problems such as wear and aging of mechanical parts, mechanical parts It has a certain service life. If the mechanical parts are not repaired in time, when the production equipment breaks down, the production efficiency will be affected if the production equipment is stopped for repair and replacement. The most common method at present is to carry out manual inspection, and the staff will carry out non-stop inspection during production , in order to detect faults and repairs in time, only rely on manual experience to judge whether there is a problem with mechanical parts, it is easy to make mistakes, and usually only after a fault occurs, it can be found, so it is impossible to replace and repair mechanical parts in time

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
  • Method and device for predicting life of mechanical component of electric drive assembly
  • Method and device for predicting life of mechanical component of electric drive assembly
  • Method and device for predicting life of mechanical component of electric drive assembly

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0063] By constructing the biorthogonal wavelet SVM (Support Vector Machine, SVM) kernel function based on the second-generation wavelet transform, the life prediction model of the second-generation wavelet SVM was established, and the obtained minimum quantization error index MQE was used as the prediction feature.

[0064] First, the vibration signals of mechanical components are collected to construct a sensitive feature set. For an original vibration signal X(t), the empirical mode decomposition is used to decompose X(t) to obtain the first m eigenmode components, m is 2, 3 or 4, and 14 time domain components are calculated for each decomposed signal Statistical feature Ftime and 13 frequency-domain statistical features Ffrequency, a total of m×27 features Ftotal=[FtimeFfrequency] are obtained; from the overall feature set Ftotal, select the feature corresponding to the feature evaluation index greater than a given threshold to form the most sensitive feature Set Fsensitiv...

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 method and a device for predicting the life of a mechanical component of an electric drive assembly. By collecting historical data and current characteristic parameter data of the mechanical component of the electric drive assembly, the modeling of a screening model and a life prediction model is completed, whether the mechanical component is in a failed state is judged according to the characteristic parameter data and the screening model, if the mechanical component is in the failed state, alarm information is sent in time to remind the staff to repair and replace the mechanical component, if the mechanical component is in a non-failed state, the remaining life of the mechanical component is accurately predicted via the life prediction model, the mechanical component which is about to be failed is monitored and detected in time, the working efficiency is improved, and the failure delay time of the mechanical component is shortened.

Description

technical field [0001] The invention relates to the technical field of mechanical failure prediction, and more specifically relates to a method and device for life prediction of mechanical components of an electric drive assembly. Background technique [0002] At present, with the development of technology, mechanical industrial production has been widely used and developed rapidly, replacing most of the labor force and improving production efficiency, but at the same time, long-term electric-driven mechanical production will cause problems such as wear and aging of mechanical parts, mechanical parts It has a certain service life. If the mechanical parts are not repaired in time, when the production equipment breaks down, the production efficiency will be affected if the production equipment is stopped for repair and replacement. The most common method at present is to carry out manual inspection, and the staff will carry out non-stop inspection during production , In order ...

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): G01M13/00G01M13/045
CPCG01M13/00G01M13/045
Inventor 夏百战杨亮戚远航
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA ZHONGSHAN INST
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