CN218949200U

CN218949200U - Intelligent flaw judging system for rail head nuclear flaws of steel rail and flaw detection vehicle

Info

Publication number: CN218949200U
Application number: CN202223229861.6U
Authority: CN
Inventors: 彭召斌; 李帅源; 桑华; 杨培俊; 刘润林; 翟升
Original assignee: Beijing Xinke Qiyuan Technology Co ltd
Current assignee: Beijing Xinke Qiyuan Technology Co ltd
Priority date: 2022-12-02
Filing date: 2022-12-02
Publication date: 2023-05-02
Anticipated expiration: 2032-12-02

Abstract

The utility model relates to the technical field of rail flaw detection, in particular to an intelligent flaw detection system for rail head nuclear flaws of a steel rail and a flaw detection vehicle. The intelligent flaw detection system for the rail head nuclear flaw of the steel rail comprises a mounting frame, a flaw detection wheel and a machine vision recognition system, wherein the flaw detection wheel is rotatably assembled at the lower end of the mounting frame through a wheel frame, a plurality of flaw detection probes are arranged in the flaw detection wheel, the machine vision recognition system is provided with two camera devices, the two camera devices are respectively arranged on the mounting frame and distributed at the front side and the rear side of the running direction of the flaw detection wheel, and the intelligent flaw detection system further comprises an alarm, and the machine vision recognition system is connected with the alarm. The advantages are that: the structure design is reasonable, the false alarm rate of rail head nuclear injury of the steel rail can be effectively reduced, the rail flaw detection efficiency is improved, the on-site injury discrimination accuracy is improved, the on-site injury leakage probability is reduced, and the practical problem of difficulty in injury discrimination of fish scale injury sections is effectively solved.

Description

Intelligent flaw judging system for rail head nuclear flaws of steel rail and flaw detection vehicle

Technical Field

The utility model relates to the technical field of rail flaw detection, in particular to an intelligent flaw detection system for rail head nuclear flaws of a steel rail and a flaw detection vehicle.

Background

In the existing rail flaw detection operation, the detection speed of novel rail flaw detection equipment, such as a double-rail flaw detector, is about 15km/h, and because the speed is high, on-site operators can hardly find the suspected flaw of the rail in the rail B-scanning image in real time;

the most common of the parent metal injuries of the high-speed seamless railway is rail head nuclear injuries, the misjudgment rate of the conventional intelligent rail head nuclear injury recognition system is high, particularly, aiming at rail nuclear injuries, the rail head nuclear injuries and rail tread injuries cannot be accurately distinguished, the light injuries of rail surfaces are frequently misjudged as rail head nuclear injuries, and the conventional fish scale injury judgment system frequently misjudges fish scale injuries as nuclear injuries when fish scale injury sections are encountered; when the false alarm rate is high, the system can send out an alarm to remind, and the working efficiency and the injury judging accuracy rate of on-site operators can not be effectively improved.

Disclosure of Invention

The utility model aims to solve the technical problem of providing an intelligent flaw detection system for rail head nuclear flaws of a steel rail and a flaw detection vehicle, and effectively overcomes the defects of the prior art.

The technical scheme for solving the technical problems is as follows:

the intelligent flaw judging system for rail head nuclear flaw of steel rail comprises a mounting frame, a flaw detection wheel and a machine vision recognition system, wherein the flaw detection wheel is rotatably assembled at the lower end of the mounting frame through a wheel frame, a plurality of flaw detection probes are arranged in the flaw detection wheel, the machine vision recognition system is provided with two camera devices, the two camera devices are respectively arranged on the mounting frame and distributed at the front side and the rear side of the travelling direction of the flaw detection wheel, and the intelligent flaw judging system further comprises an alarm, and the machine vision recognition system is connected with the alarm.

On the basis of the technical scheme, the utility model can be improved as follows.

Further, transparent length scales are respectively arranged below the two image pickup devices, and the length scales are respectively arranged below the mounting frame through brackets.

Further, the camera also comprises two groups of light sources, wherein the two groups of light sources are respectively arranged on the mounting frame and are respectively and correspondingly positioned near the camera equipment one by one.

Further, the machine vision recognition system also comprises an alarm, and the machine vision recognition system is connected with the alarm.

Further, 9 flaw detection probes are provided.

The beneficial effects of the utility model are as follows: the structure design is reasonable, the false alarm rate of rail head nuclear injury of the steel rail can be effectively reduced, the rail flaw detection efficiency is improved, the on-site injury discrimination accuracy is improved, the on-site injury leakage probability is reduced, and the practical problem of difficulty in injury discrimination of fish scale injury sections is effectively solved.

The flaw detection vehicle further comprises a vehicle body and two intelligent rail head nuclear injury judging systems, wherein the two intelligent rail head nuclear injury judging systems are respectively arranged on two sides of the vehicle body, and the machine vision recognition system is arranged on the vehicle body.

Drawings

Fig. 1 is a schematic structural diagram of the intelligent judging system for rail head nuclear damage of the steel rail.

In the drawings, the list of components represented by the various numbers is as follows:

1. flaw detection wheel; 2. a flaw detection probe; 3. an image pickup apparatus; 4. length scale.

Detailed Description

The principles and features of the present utility model are described below with reference to the drawings, the examples are illustrated for the purpose of illustrating the utility model and are not to be construed as limiting the scope of the utility model.

Example 1

As shown in fig. 1, the intelligent flaw detection system for rail head nuclear flaws of the present embodiment includes a mounting frame, a flaw detection wheel 1 and a machine vision recognition system, wherein the flaw detection wheel 1 is rotatably assembled at the lower end of the mounting frame through the wheel frame, a plurality of flaw detection probes 2 are arranged in the flaw detection wheel 1, the machine vision recognition system has two image pickup devices 3, the two image pickup devices 3 are respectively installed on the mounting frame and distributed at the front side and the rear side of the travelling direction of the flaw detection wheel 1, and the intelligent flaw detection system further includes an alarm, and the machine vision recognition system is connected with the alarm.

It should be noted that: machine vision systems (machine vision recognition systems) are known in the art, which means that a machine is used to make measurements and decisions instead of the human eye. The vision system is used for converting the shot target into an image signal through a machine vision product (namely an image shooting device, namely CMOS and CCD, respectively), transmitting the image signal to a special image processing system, and converting the image signal into a digital signal according to the information of pixel distribution, brightness, color and the like; the image system performs various operations on these signals to extract characteristics of the object, and further controls the operation of the on-site device according to the result of the discrimination. In the present embodiment, the two image pickup apparatuses 3 correspond to image pickup devices in which machine vision is a system.

In this embodiment, the flaw detection probe 2 may be a conventional ultrasonic probe.

In the present embodiment, the imaging apparatus 3 is installed at the front and rear positions of the inspection wheel 1, and when the ultrasonic wave of a certain probe in the inspection wheel 1 detects a suspected rail head nuclear injury, the imaging apparatus 3 at the corresponding position is controlled to take a picture. The position of the corresponding reflector along the steel rail direction can be calculated according to the ultrasonic echo of the flaw detection probe 2, and the corresponding region in the photo can be intercepted according to the position information of the flaw detection probe 2, the camera equipment 3 and the echo. In the detection process, the machine vision recognition system recognizes the feature classification of the intercepted area: the movable joint, the falling block, the fish scale, the surface without abnormality and the like; if the block is dropped, the size is identified, the size exceeds the severe injury standard, the severe injury is judged, and a suspected severe injury reminding alarm is sent out. If the fish scales are detected, the machine vision recognition system controls the alarm to alarm according to the detection result. If the joint is a movable joint, the alarm is not given. If the surface is not abnormal, judging that the rail head is nuclear damaged.

As a preferred embodiment, transparent length scales 4 are respectively provided below the two image pickup apparatuses 3, and the length scales 4 (the length direction of the length scales 4 is along the length direction of the rail) are respectively mounted below the mounting frame via brackets.

In the above embodiment, a transparent length scale 4 is installed between the lens of the image capturing device 3 and the rail, near the rail position, for assisting in identifying the actual size in the photograph, and the machine vision recognition system can calculate the position of the corresponding reflector along the rail direction according to the ultrasonic echo of the probe, and intercept the corresponding region in the photograph according to the position information of the probe, the camera and the echo, and in combination with the scale data in the photograph.

As a preferred embodiment, two sets of light sources (denoted by a in the figure) are also included, and the two sets of light sources are respectively mounted on the mounting frame and are respectively located near the image pickup apparatus 3 in one-to-one correspondence.

In the above embodiment, the light source is used for supplementing light to the track below the image pickup apparatus 3, so that the situation that the image pickup of the image pickup apparatus 3 is unclear due to light is avoided, and the detection result is inaccurate.

In this embodiment, the flaw detection probes 2 are provided with 9 probes (the arrows in fig. 1 indicate the directions of the emitted waves of the probes), one probe is a probe with an emission angle of 0 ° and vertically downward, and two probes with front and lower and rear lower emission (the refraction angles of the emitted waves of the two probes are respectively 37 °); two probes which emit forward and downward and backward and downward (the refraction angles of the emitted waves of the two probes are 70 degrees respectively); a probe with a transmitting wave facing the front side and the inner side of the track pedal, and a probe with a transmitting wave facing the front side and the outer side of the track pedal (the refraction angles of the transmitting waves of the two probes are respectively 70 °); one probe with the emission wave facing the rear side and the inner side of the track tread and one probe with the emission wave facing the rear side and the outer side of the track tread (the refraction angles of the emission waves of the two probes are 70 degrees), and the wave detected by the flaw detection probe 2 after the emission returns to the original path and is received by the flaw detection probe 2.

Of particular emphasis is the fact that: taking echo detection of a probe that emits a wave downward toward the rear side in the flaw detection wheel 1 as an example, when the probe detects a flaw, the machine vision recognition system controls the image pickup apparatus 3 located behind the flaw detection wheel 1 to take a picture (the image pickup apparatus 3 is an apparatus corresponding to a plurality of probes that emit flaw detection waves toward the rear side).

Example 2

The embodiment provides a flaw detection vehicle, which comprises a vehicle body and two intelligent flaw detection systems for rail head nuclear flaws of the steel rail in embodiment 1, wherein the two intelligent flaw detection systems for rail head nuclear flaws of the steel rail are respectively arranged on two sides of the vehicle body, and the machine vision recognition system is arranged on the vehicle body. Specifically, the mounting frames of the intelligent flaw judging system for the rail head and the rail head of the two steel rails are respectively detachably arranged on two sides of the vehicle body, walking wheels are respectively arranged on two sides of the vehicle body along the length direction of the rail, and the flaw detection wheels 1 are respectively supported on the two rail treads in a rolling way during flaw detection.

It should be noted that: the flaw detection vehicle is provided with a power supply, and all electric elements are connected with the power supply for power supply.

In the description of the present utility model, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings are merely for convenience in describing the present utility model and simplifying the description, and do not indicate or imply that the device or element being referred to must have a specific orientation, be configured and operated in a specific orientation, and therefore should not be construed as limiting the present utility model.

In the present utility model, unless explicitly specified and limited otherwise, the terms "mounted," "connected," "secured," and the like are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; either directly or indirectly, through intermediaries, or both, may be in communication with each other or in interaction with each other, unless expressly defined otherwise. The specific meaning of the above terms in the present utility model can be understood by those of ordinary skill in the art according to the specific circumstances.

In the present utility model, unless expressly stated or limited otherwise, a first feature "up" or "down" a second feature may be the first and second features in direct contact, or the first and second features in indirect contact via an intervening medium. Moreover, a first feature being "above," "over" and "on" a second feature may be a first feature being directly above or obliquely above the second feature, or simply indicating that the first feature is level higher than the second feature. The first feature being "under", "below" and "beneath" the second feature may be the first feature being directly under or obliquely below the second feature, or simply indicating that the first feature is less level than the second feature.

While embodiments of the present utility model have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the utility model, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the utility model.

Claims

1. An intelligent steel rail head nuclear injury judging system is characterized in that: including mounting bracket, wheel (1) and machine vision recognition system of detecting a flaw, detect a flaw wheel (1) through the rotatable assembly of wheel carrier in the lower extreme of mounting bracket, be equipped with a plurality of probes (2) of detecting a flaw in wheel (1) of detecting a flaw, machine vision recognition system has two camera equipment (3), and two camera equipment (3) are installed respectively on the mounting bracket, and distribute the front and back side of the walking direction of wheel (1) of detecting a flaw still includes the alarm, machine vision recognition system connects the alarm.

2. The intelligent steel rail head nuclear damage judging system according to claim 1, wherein: transparent length scales (4) are respectively arranged below the two image pickup devices (3), and the length scales (4) are respectively arranged below the mounting frame through brackets.

3. The intelligent steel rail head nuclear damage judging system according to claim 1, wherein: the camera also comprises two groups of light sources, wherein the two groups of light sources are respectively arranged on the mounting frame and are respectively positioned near the camera equipment (3) in a one-to-one correspondence manner.

4. The intelligent steel rail head nuclear damage judging system according to claim 1, wherein: the number of the flaw detection probes (2) is 9.

5. The utility model provides a flaw detection car which characterized in that: the intelligent flaw judging system for the rail head nuclear flaw of the steel rail comprises a vehicle body and two intelligent flaw judging systems for the rail head nuclear flaw of the steel rail according to any one of claims 1 to 4, wherein the two intelligent flaw judging systems for the rail head nuclear flaw of the steel rail are respectively arranged on two sides of the vehicle body, and the machine vision identifying system is arranged on the vehicle body.