Supercharge Your Innovation With Domain-Expert AI Agents!

Bearing abrasion early warning method and system based on frequency spectrum

An early warning system, bearing technology, applied in complex mathematical operations, instruments, character and pattern recognition, etc., can solve the problem of bearing loss early warning and other problems

Pending Publication Date: 2021-04-06
SHANGHAI MININGLAMP ARTIFICIAL INTELLIGENCE GRP CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the above-mentioned technical problem that the bearing loss cannot be early-warned, the present invention proposes a bearing wear early-warning method and system based on frequency spectrum

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
  • Bearing abrasion early warning method and system based on frequency spectrum
  • Bearing abrasion early warning method and system based on frequency spectrum
  • Bearing abrasion early warning method and system based on frequency spectrum

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0074] refer to figure 1 as shown, figure 1 It is a schematic diagram of the steps of a spectrum-based bearing wear early warning method provided by the present invention. Such as figure 1 As shown, this embodiment discloses a specific implementation of a spectrum-based bearing wear early warning method (hereinafter referred to as "method").

[0075] The vibration caused by the bearing is called bearing pitch, and all rolling bearings produce pitch to a certain degree, the more severely worn the bearing, the higher the degree of pitch of the bearing. Therefore, the remaining vibration signal obtained by removing the low-frequency vibration component can be used to judge the degree of bearing wear.

[0076] Specifically, the method disclosed in this embodiment mainly includes the following steps:

[0077] refer to figure 2 , performing step S1: using a sensor to acquire raw data of device vibration, processing the raw data, and converting the processed raw data into a fir...

Embodiment 2

[0135] In combination with the spectrum-based bearing wear early warning method disclosed in Embodiment 1, this embodiment discloses a specific implementation example of a spectrum-based bearing wear early warning system (hereinafter referred to as "system").

[0136] refer to Figure 10 As shown, the system includes:

[0137] Data conversion module 1: using a sensor to acquire raw data of device vibration, processing the raw data, and converting the processed raw data into a first spectrogram;

[0138] Spectrum image segment acquisition module 2: set the step size, and perform a sliding window on the first spectral image according to the time sequence according to the step size, to obtain several first spectral image segments;

[0139] Training sample acquisition module 3: label the first spectrum picture segment according to the original data, if there is a fault, the label is 1, if there is no fault, the label is 0, and the first language of the label is The spectrogram 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 discloses a bearing abrasion early warning method and system based on a frequency spectrum, and the method comprises the steps: obtaining equipment vibration data, processing the data, and converting the data into a first spectrogram; setting a step length, and performing window sliding on the first spectrogram according to the step length to obtain a plurality of first spectrogram picture segments; labeling the first spectrogram picture segment according to the original data, and taking the labeled first spectrogram picture segment as a training sample; using triplet loss as a loss function, using resnet50 as a feature extraction network, and training the feature extraction network to obtain reference features; processing the test data into a second spectrogram to obtain a second spectrogram picture segment, and using the trained feature extraction network to obtain vibration features in the time period; calculating the Euclidean distance between the vibration characteristic and the reference characteristic in each period of time, and judging whether the vibration is abnormal or not according to a threshold value.

Description

technical field [0001] The invention relates to the technical field of early warning, in particular to a bearing wear early warning method and system based on frequency spectrum. Background technique [0002] Vibration is an important characteristic of rotating machinery. Use the data collector to collect the vibration information of the operating state of mechanical equipment (such as bearings), and then analyze the vibration spectrum to quickly and accurately diagnose faults such as rotor imbalance, shaft bending, bearing damage and looseness, and shaft misalignment The reasons for the existence, so as to achieve the purpose of early detection of faults, rapid and timely diagnosis, fixed-point and quantitative conclusions, and clear and clear mechanisms. [0003] However, this solution can only judge whether there is a fault in the traditional rotating machinery inspection process, and cannot quantitatively analyze the loss and give an early warning. Contents of the inv...

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): G06K9/00G06K9/62G06F17/14
CPCG06F17/14G06F2218/08G06F18/217G06F18/214
Inventor 安达
Owner SHANGHAI MININGLAMP ARTIFICIAL INTELLIGENCE GRP CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More