Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Induction motor rotor broken bar fault diagnosis method based on wavelet packet support vector machine

A support vector machine and rotor broken bar technology, applied in the direction of motor generator testing, etc., can solve problems such as small component amplitude, difficulty in identifying faults, small slip rate, etc., achieve reliable and practical significance, realize predictive diagnosis, and avoid signal The effect of sampling too long

Inactive Publication Date: 2019-05-21
XI AN JIAOTONG UNIV
View PDF7 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when the induction motor is running, the slip s is generally very small, so at the initial stage of the rotor broken bar fault, (1±2s)f 1 The component amplitude is also very small, it is difficult to judge whether the fault occurs or not

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
  • Induction motor rotor broken bar fault diagnosis method based on wavelet packet support vector machine
  • Induction motor rotor broken bar fault diagnosis method based on wavelet packet support vector machine
  • Induction motor rotor broken bar fault diagnosis method based on wavelet packet support vector machine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The present invention will be described in further detail below in conjunction with the accompanying drawings.

[0027] see figure 1 , the present invention is based on the wavelet packet support vector machine induction motor rotor broken bar fault diagnosis method, the steps are as follows:

[0028] The first step: preprocessing of the fault current signal, denoising the original fault current of the stator winding. Preprocess the stator current data of the detected broken rotor bar fault of the induction motor, and filter out the power frequency stator current component and high frequency noise component in the stator current fault signal through SVD filtering technology based on singular value decomposition, and only retain the fault component , and store the data.

[0029] In the second step, the fifth-order wavelet packet decomposition is performed on the fault current signal to obtain the fault current signal components of each sub-band. The five-layer wavelet...

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

An induction motor rotor broken bar fault diagnosis method based on a wavelet packet support vector machine, and the method comprises the steps of preprocessing detected induction motor rotor broken bar fault stator current, and filtering out the noise component included in the fault stator current; performing wavelet packet decomposition on the de-noised current signal to obtain a fault current signal component of each sub-band; reconstructing a wavelet packet decomposition coefficient and calculating the sum of signal energy in each frequency band; performing normalization processing on thesignal energy in each frequency band and constructing a feature vector; constructing a support vector machine model; dividing the feature vector into a training sample and a prediction sample, training the support vector machine model by using the training sample, testing the trained model by using the prediction sample, judging a fault type to which the signal corresponding to the feature vectorbelongs, and obtaining the diagnosis accuracy of the test set as a verification result of the model. According to the invention, the limitation that signal sampling time is too long, load fluctuationinterference is caused, and slight faults cannot be detected is avoided.

Description

technical field [0001] The invention belongs to the field of fault diagnosis of induction motors, and relates to a method for diagnosing a broken bar of an induction motor rotor based on a wavelet packet support vector machine, which solves the problem of extraction and discrimination of fault signals, and decomposes the fault signal of a broken bar of an induction motor rotor based on a correlation algorithm The extraction method is combined with the support vector machine to realize the diagnosis of the broken bar fault of the induction motor rotor. Background technique [0002] Induction motors have the advantages of durability, low price, and easy maintenance, and have been widely used in electric power, mining, shipbuilding, and metallurgy industries. Due to the complex working environment of induction motors, they usually face long-term continuous operation, frequent Braking and starting and complex working environment and other harsh tests are prone to various failure...

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): G01R31/34
Inventor 徐浩东刘凌司杰文
Owner XI AN JIAOTONG UNIV
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
Eureka Blog
Learn More
PatSnap group products