State recognition method based on time-varying data and multi-scale microscopic vibration data analysis

A technology of time-varying data and vibration data, applied in character and pattern recognition, instruments, calculations, etc., can solve the problems of reciprocating mechanical fault identification and diagnosis, and achieve the goal of avoiding excessive dependence, accurate identification, and improving state identification accuracy. Effect

Pending Publication Date: 2022-03-01
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] At present, most of the fault diagnosis is based on the research object of rotary machinery. Reciprocating machinery also plays an irreplaceable role in daily life. However, there are very few identification and diagnosis of reciprocating machinery faults.

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
  • State recognition method based on time-varying data and multi-scale microscopic vibration data analysis
  • State recognition method based on time-varying data and multi-scale microscopic vibration data analysis
  • State recognition method based on time-varying data and multi-scale microscopic vibration data analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0155] Below in conjunction with accompanying drawing and embodiment the present invention will be further described:

[0156] The state identification method based on time-varying data analysis includes the following steps:

[0157] Step 1. Measurement of working process data

[0158] According to the working mechanism and failure mode analysis of the anti-recoil device, the working process data is collected through multiple sensors. The anti-recoil device is composed of a retreating machine and a re-entrying machine. The common failure modes in the reciprocating motion are too long recoil, too short recoil, insufficient re-entry, and excessive re-entry. Move data, velocity data, and acceleration data back and forth.

[0159] Step 2. Anti-recoil device fault feature recognition method based on time-varying data

[0160] 2-1 Abnormal data removal

[0161] Remove abnormal data: Abnormal data refers to monitoring values ​​that do not conform to the trend of the entire time s...

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 relates to a state recognition method based on time-varying data and multi-scale microscopic vibration data analysis, and belongs to the field of complex mechanical fault diagnosis. The objective of the invention is to solve the problem of fault identification of a linear reciprocating machine with small data volume. According to the method, displacement, speed and vibration signals in a movement process are analyzed according to a working mechanism and a typical fault mode of a to-be-recognized device, and then the working state of the system is recognized. The fault of the to-be-recognized device shows that the maximum recoil displacement exceeds or is smaller than a normal value, the recoil time exceeds or is smaller than a normal value, the counter-recoil forward rushing exceeds or does not reach the original position, and the vibration signal of the buffer is abnormal in terms of displacement and speed data. Therefore, the state recognition of the device to be recognized is to process and analyze the displacement, the speed, the acceleration and the vibration signal in the movement process.

Description

technical field [0001] The invention relates to a state recognition method based on analysis of time-varying data and multi-scale microscopic vibration data, which belongs to the field of complex mechanical fault diagnosis. Background technique [0002] At present, most of the fault diagnosis is based on the research object of rotary machinery. Reciprocating machinery also plays an irreplaceable role in daily life. However, there are very few identification and diagnosis of reciprocating machinery faults. Reciprocating machinery includes two processes of recoil and recoil, reciprocating along the central axis, and has the characteristics of high wear rate, high failure rate, and large displacement reciprocation. [0003] The fault diagnosis method of rotary machinery is not effective in the fault diagnosis of reciprocating machinery, and the analysis of microscopic vibration signals of reciprocating machinery is one-sided, because the microscopic vibration signals of rotary ...

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): G06K9/00G06K9/62
CPCG06F2218/06G06F2218/08G06F2218/12G06F18/2433
Inventor 张发平杨向飞魏剑峰
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
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