Supercharge Your Innovation With Domain-Expert AI Agents!

Motor mechanical fault diagnosis method adopting current signal based on data driving

A current signal, data-driven technology, applied in the recognition of patterns in signals, neural learning methods, machine learning and other directions, can solve the problems of inability to add vibration sensors, limited application of small and medium-sized motors, and high prices of vibration sensors. Improve the efficiency of diagnosis, the difficulty of modeling, and the effect of low accuracy

Pending Publication Date: 2020-09-18
HUNAN UNIV
View PDF13 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the price of the vibration sensor is high, and its application in small and medium-sized motors is limited
In addition, the vibration sensor needs to be in direct contact with the motor, so there are problems with installation and placement. Some equipment that has already been put into production cannot be equipped with a vibration sensor
Therefore, the existing vibration-based sensors have the problem of limited scope of application

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
  • Motor mechanical fault diagnosis method adopting current signal based on data driving
  • Motor mechanical fault diagnosis method adopting current signal based on data driving
  • Motor mechanical fault diagnosis method adopting current signal based on data driving

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The principle of the motor mechanical fault diagnosis method based on the data-driven current signal of the present invention is as follows:

[0033] When the motor has a typical mechanical fault (broken rotor bar, eccentric fault, bearing fault), the motor will generate periodic torque ripples during operation, which will affect the current. Each fault will have a specific frequency on the current spectrum, that is, the fault characteristic frequency, as follows:

[0034] Rotor broken bar fault characteristic frequency f brb1 and f brb2 for:

[0035] f brb1 =(1±2k 1 s)·f s ,k1 =1,2,3,... (1)

[0036] f brb2 =[(k 2 / p)(1-s)±s] f s ,k 2 / p=1,2,3,... (2)

[0037] Eccentric fault characteristic frequency f ecc1 for:

[0038] f ecc1 =[(k·R±n d )·(1-s) / P p ±v]·f s ,k=1,2,3,... v=1,3,5,... (3)

[0039] no d = 0, it is a static eccentric fault, n d = 1, 2, 3, ... is a dynamic eccentric fault.

[0040] Bearing fault characteristic frequency:

[0041] Chara...

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 data driving-based motor mechanical fault diagnosis method adopting a current signal. The method comprises the steps: obtaining a stator current signal which is D in length and comprises N samples; carrying out noise signal reconstruction on the stator current signal to obtain a reconstructed signal; subtracting the reconstruction signal from the original stator current signal to obtain a residual current; converting the signal of the residual current into a frequency domain to obtain a frequency domain signal; and inputting the frequency domain signal of the residualcurrent into a pre-trained machine learning feature extraction and fault classification model to obtain a motor state. According to the invention, motor fault diagnosis is carried out by using current signals; the method can be used for diagnosing mechanical faults, a vibration sensor and a current sensor do not need to be additionally installed, data can be collected through a current transformer installed in a protection system or a control system, the method is a non-invasive low-cost mode, and the method has the advantages of being high in diagnosis efficiency, high in diagnosis accuracyand low in false alarm rate.

Description

technical field [0001] The invention relates to a motor mechanical fault diagnosis technology, in particular to a data-driven motor mechanical fault diagnosis method using current signals. Background technique [0002] Motor faults can be divided into mechanical faults and electrical faults. For mechanical faults, vibration signals are often used for diagnosis in the prior art. However, the price of the vibration sensor is high, and its application in small and medium-sized motors is limited. Moreover, the vibration sensor needs to be in direct contact with the motor, so there is a problem of installation and placement, and some equipment that has already been put into production cannot be equipped with a vibration sensor. Therefore, the existing vibration-based sensors have the problem of limited application range. Contents of the invention [0003] The technical problem to be solved by the present invention: Aiming at the above-mentioned problems of the prior art, a da...

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): G06K9/00G06K9/62G06N3/08G06N20/00
CPCG06N3/084G06N20/00G06F2218/04G06F2218/08G06F2218/12G06F18/214G06F18/24Y04S10/52
Inventor 王辉孙梅迪黄守道刘平龙卓
Owner HUNAN UNIV
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com