Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A method of converting motor current into grayscale image

A technology of motor current and grayscale image, applied in 2D image generation, motor, image coding and other directions, can solve problems such as long raw data and logical problems, and achieve the effect of improving timeliness and rigorous logic

Active Publication Date: 2022-08-09
GUIZHOU UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method is a big improvement for the human naked eye, but for the machine, this method still has the problem of mapping logic relationship in the coloring method
[0012] There are some deficiencies in the above three image conversion methods (requires too long original data; there are logic problems, etc.)

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
  • A method of converting motor current into grayscale image
  • A method of converting motor current into grayscale image
  • A method of converting motor current into grayscale image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0028] Example 1: as Figure 1-Figure 5 As shown, in order to adapt the motor data to the working mechanism of a Convolutional Neural Network (CNN), the present invention considers converting the IPMSM stator current signal into image data. An image data is a matrix composed of pixel values ​​from 0 to 255. Converting data to an image is essentially a process of converting a data sequence into a multi-dimensional matrix. A method for converting motor current into a grayscale image, the method is: obtaining an autocorrelation matrix through the motor current signal to obtain a two-dimensional matrix, and scattering the motor current signal data into the gray value range, so that the original data There is a complete mapping relationship with the image pixel value, and the mapping relationship function is set as a one-dimensional Gaussian distribution function:

[0029]

[0030] In the formula, x ij Represents the elements of the i-th row and j-th column in the autocorrelat...

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 for converting a motor current into a grayscale image. The method comprises the following steps: obtaining an autocorrelation matrix through the motor current signal to obtain a two-dimensional matrix, and scattering the motor current signal data into a grayscale value range , so that there is a complete mapping relationship between the original data and the image pixel value, and the mapping relationship function is set as a one-dimensional Gaussian distribution function. The invention converts the original data into a grayscale image with only one channel, so that the original data and the image maintain a strict mapping logical relationship, and the motor current signal is converted into a two-dimensional matrix to realize the data dimension uplift, and the high-dimensional features include With more data features, using the autocorrelation matrix of the data for image transformation will take up shorter raw data and require less raw data, which improves the timeliness of the diagnostic system, so that there is a complete relationship between raw data and image pixel values. The mapping relationship is more logically rigorous.

Description

technical field [0001] The invention belongs to the technical field of motor current signal processing methods, and relates to a method for converting motor current into grayscale images. Background technique [0002] The IPMSM fault diagnosis method realizes the fault monitoring of the IPMSM under the working condition of the electric vehicle. The intelligent diagnosis methods proposed in the existing technology are all based on the feature extraction of the vibration signal, and additional sensors need to be added to measure the vibration signal, and the detection results are affected by Influence of sensor installation location. In addition, the fault diagnosis method based on vibration signal cannot be applied to the working condition of multi-vibration system. During the driving process of electric vehicles, bumps and vibrations will occur, which will affect sensors that measure vibration signals such as acceleration sensors, thereby affecting the reliability of motor ...

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 Patents(China)
IPC IPC(8): G06T11/00G06T9/00G06N3/04G06N3/08
CPCG06T11/00G06T9/002G06N3/08G06N3/045Y02T10/64
Inventor 李志远吴钦木
Owner GUIZHOU UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com