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

Steel rail defect width detection method based on magnetic flux leakage detection device and neural network

A technology of magnetic flux leakage detection and neural network, which is applied in the field of measurement technology and instruments, can solve the problems affecting the grinding and replacement of workpieces, and achieve the effect of precise damage and accurate judgment

Inactive Publication Date: 2018-12-21
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The measurement of defect length is also crucial to the evaluation of the damage of the measured workpiece, and different defect widths may affect the grinding and replacement of the workpiece

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
  • Steel rail defect width detection method based on magnetic flux leakage detection device and neural network
  • Steel rail defect width detection method based on magnetic flux leakage detection device and neural network
  • Steel rail defect width detection method based on magnetic flux leakage detection device and neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] The invention discloses a rail defect width detection method based on a magnetic flux leakage detection device and a neural network, such as figure 1 As shown, the magnetic flux leakage detection device includes a housing, a yoke, an excitation coil, a Hall sensor array, a first caster and a second caster;

[0034] Both the first caster and the second caster are wide wheels, which are respectively arranged on the lower end surface of the housing, so that the housing can roll on the rail to be detected;

[0035] The yoke, the excitation coil, and the Hall sensor array are all arranged in the housing, wherein the yoke is in an inverted U shape, the excitation coil is wound on it, and the excitation coil is connected to an external power supply. The yoke is used to send a magnetic signal toward the rail to be detected when the excitation coil is energized; the Hall sensor array is arranged in the yoke and parallel to the rail to collect magnetic flux leakage signals;

[0...

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 steel rail defect width detection method based on a magnetic flux leakage detection device and a neural network. The method comprises the following steps: firstly, placing the magnetic flux leakage detection device on a steel rail to be detected to measure magnetic flux leakage signals of the steel rail to be detected on an X direction and a Y direction, and obtaining a signal time domain distribution diagram of the X direction and the signal time domain distribution diagram of the Y direction after bandpass filtering and amplification processing; then, extracting signal peak characteristic values and signal spacing characteristic values of the X direction and the Y direction, and inputting the signal peak characteristic values, the signal spacing characteristic values and extraction separation values to a neural network toolbox to obtain coefficients of defects of the X direction and the Y direction; and finally, obtaining defect widths of the X direction andthe Y direction by calculation. By adoption of the steel rail defect width detection method disclosed by the invention, quantitative analysis can be performed on defect signals of different lengths on the basis that the magnetic flux leakage signals can only be detected, and the damage severity situation can be judged more accurately.

Description

technical field [0001] The invention relates to the field of measurement technology and instruments, in particular to a method for detecting the width of rail defects based on a magnetic flux leakage detection device and a neural network. Background technique [0002] At present, non-destructive magnetic flux leakage testing has become one of the main methods for detecting the width of rail defects. The basic principle of magnetic flux leakage detection in non-destructive testing refers to that after the ferromagnetic material is partially magnetized, if the material has cracks or pits in the local magnetized area, the magnetic field distribution at the damage will change suddenly, and some magnetic fields will It will leak out to form a leakage magnetic field. By detecting the change of the magnetic field in this part of the ferromagnetic material, it can be judged whether there is damage in this part of the material. [0003] The leakage magnetic field intensity at the de...

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): G01N27/83G01B7/02G06N3/04G06N3/08
CPCG06N3/08G01B7/02G01N27/83G06N3/048
Inventor 熊师洵王平冀凯伦朱雨微刘骕骐姚恒宇
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
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