CN113804755B - Automatic rail weld joint recognition system and method - Google Patents
Automatic rail weld joint recognition system and method Download PDFInfo
- Publication number
- CN113804755B CN113804755B CN202010530223.4A CN202010530223A CN113804755B CN 113804755 B CN113804755 B CN 113804755B CN 202010530223 A CN202010530223 A CN 202010530223A CN 113804755 B CN113804755 B CN 113804755B
- Authority
- CN
- China
- Prior art keywords
- rail
- weld
- acoustic wave
- wave sensor
- steel rail
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 14
- 238000003466 welding Methods 0.000 claims abstract description 56
- 229910000831 Steel Inorganic materials 0.000 claims abstract description 53
- 239000010959 steel Substances 0.000 claims abstract description 53
- 238000012937 correction Methods 0.000 claims abstract description 31
- 238000001514 detection method Methods 0.000 claims abstract description 28
- 230000008878 coupling Effects 0.000 claims abstract description 15
- 238000010168 coupling process Methods 0.000 claims abstract description 15
- 238000005859 coupling reaction Methods 0.000 claims abstract description 15
- 238000012545 processing Methods 0.000 claims abstract description 13
- 230000005540 biological transmission Effects 0.000 claims abstract description 11
- 238000002592 echocardiography Methods 0.000 claims abstract description 7
- 238000005096 rolling process Methods 0.000 claims abstract description 6
- 238000012423 maintenance Methods 0.000 claims description 10
- 238000012790 confirmation Methods 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims 1
- 230000007547 defect Effects 0.000 abstract description 9
- 238000012544 monitoring process Methods 0.000 description 9
- 238000007689 inspection Methods 0.000 description 6
- 230000006378 damage Effects 0.000 description 5
- 238000007405 data analysis Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 230000035945 sensitivity Effects 0.000 description 4
- 230000001960 triggered effect Effects 0.000 description 4
- 208000027418 Wounds and injury Diseases 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 208000014674 injury Diseases 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000000523 sample Substances 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 239000010985 leather Substances 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000001028 reflection method Methods 0.000 description 1
- 210000002435 tendon Anatomy 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000004148 unit process Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/04—Analysing solids
- G01N29/048—Marking the faulty objects
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
Landscapes
- Physics & Mathematics (AREA)
- Biochemistry (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Acoustics & Sound (AREA)
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Investigating Or Analyzing Materials By The Use Of Ultrasonic Waves (AREA)
Abstract
Provided is a rail weld automatic identification system, comprising: an acoustic wave sensor configured to transmit acoustic waves to the rail and to receive echoes from the rail; a coupling medium; the rubber wheel is internally fixedly provided with the acoustic wave sensor and filled with the coupling medium, and can be in rolling press connection with the steel rail tread to form an acoustic wave transmission channel among the acoustic wave sensor, the coupling medium, the rubber wheel and the steel rail; the welding line identification unit is used for processing the echo received by the acoustic wave sensor to identify a welding line; the positioning unit is used for determining the coordinate position of the identified welding line on the steel rail; a storage unit for storing correction data; and the correction unit is used for correcting the identified welding line data according to the correction data. Also provides a rail welding seam automatic identification method and a rail defect detection system.
Description
Technical Field
The invention relates to an automatic identification system and method for a steel rail welding seam, which can be applied to steel rail flaw detection equipment and belongs to the technical field of steel rail flaw detection.
Background
Chinese patent CN201811503525 proposes a method for identifying welds by means of rail surface image identification. The method is used for shooting the surface image of the steel rail in real time, the data volume is large, and a large amount of information redundancy is caused in the non-welded joint area of the steel rail. Meanwhile, the image recognition calculation and marking process in the patent has larger time delay, and the position of the weld mark is easy to generate errors. Meanwhile, the difference of the gray values of the images is utilized to distinguish the welding line from the normal steel rail, the welding line is required to be established on the extraction and the training of massive standard welding line photos, the implementation conditions and the difficulty are very large, the road condition state is complex in the actual flaw detection, and the identification accuracy is difficult to ensure.
In addition, the detection of the weld joint data and the rail defects relates to the safety of railway operation, and the rapid and effective detection of the weld joint is beneficial to improving the safety of railway operation and is a long-standing problem.
Therefore, it is necessary to research an automatic rail weld recognition system and a method thereof to solve the above-mentioned technical problems.
Disclosure of Invention
The research shows that when the sound wave is adopted to detect the defects or the injuries of the steel rail, a certain interference exists on the detection result when a large number of welding seams exist in the steel rail in active service in China at present. Specifically, the welding rib wave of the welding seam is very similar to the rail head nuclear damage wave of the steel rail parent metal, so that the welding seam or the damage is not easy to distinguish when flaw detection data analysis is carried out. That is, for example, when a rail flaw detection vehicle is used for detecting a rail flaw, although the running speed is high, erroneous judgment or missed judgment is easily caused because a later data analysis person cannot distinguish between a welding tendon and a rail head nuclear flaw. The false judgment of the injury can cause unnecessary on-site rechecking by the staff, which is time-consuming and labor-consuming, and the serious accidents such as rail breakage and the like are easy to cause if the judgment is missed due to nuclear injury.
The invention provides an automatic rail welding seam identification system based on the research findings, which is characterized by comprising:
an acoustic wave sensor configured to transmit acoustic waves to the rail and to receive echoes from the rail;
a coupling medium;
the rubber wheel is internally fixedly provided with the acoustic wave sensor and filled with the coupling medium, and can be in rolling press connection with the steel rail tread to form an acoustic wave transmission channel among the acoustic wave sensor, the coupling medium, the rubber wheel and the steel rail;
the welding line identification unit is used for processing the echo received by the acoustic wave sensor to identify a welding line;
the positioning unit is used for determining the coordinate position of the identified welding line on the steel rail;
a storage unit for storing correction data;
and the correction unit is used for correcting the identified welding line data according to the correction data.
According to another aspect of the invention, the correction data may include weld data and its corresponding coordinate position after field confirmation from the railway maintenance department, and may also include, for example, relevant data that are each a weld through multiple identifications of the weld identification unit, or a combination thereof.
According to another aspect of the invention, the wheels are arranged on rail flaw detection equipment capable of moving along the rail and roll on the rail tread along with the movement of the flaw detection equipment on the rail so as to realize continuous identification of the rail weld joints.
According to another aspect of the invention, the acoustic wave sensor is arranged so that the distance between the incidence point of the steel rail tread and the center line of the steel rail tread is 0.14-0.4L, a refraction angle of 35-50 degrees is formed at the steel rail tread, and an included angle of 8-15 degrees is formed between the longitudinal section of the steel rail and the side surface of the steel rail, wherein L is the distance between the side surface of the steel rail and the center line of the steel rail tread.
According to another aspect of the invention, the acoustic wave sensor comprises a first acoustic wave sensor and a second acoustic wave sensor which are respectively arranged on the inner side and the outer side of a steel rail, and the first acoustic wave sensor and the second acoustic wave sensor only identify the welding line when detecting the welding line at the same position of the steel rail.
According to another aspect of the present invention, the weld recognition unit may include first and second weld recognition units corresponding to the first and second acoustic sensors, respectively, for processing according to echoes received by the first and second acoustic sensors, respectively, to independently recognize welds.
According to another aspect of the invention, the automatic rail weld identification system further comprises an encoder unit for sending a trigger signal to the sonic sensor to trigger the sonic sensor to operate periodically and which follows the rotation of the wheels of the inspection apparatus synchronously to determine the coordinate position of the detected weld on the rail.
According to another aspect of the invention, the echo comprises dihedral reflections from the butt-jaw strap-like projections at the weld.
According to another aspect of the invention, the weld recognition unit further comprises an echo time gain compensation unit in which a corresponding coefficient table of sound wave transmission time and gain values is stored.
According to another aspect of the present invention, when one of the first acoustic wave sensor and the second acoustic wave sensor provided at the same position of the rail detects the weld and the other does not detect the weld, it is determined that the rail is cracked, preferably, a maintenance person may be notified to confirm.
According to another aspect of the present invention, correction data is generated based on the confirmation result and stored in the storage unit.
According to another aspect of the present invention, when one of the first acoustic sensor and the second acoustic sensor provided at the same position of the rail detects the weld and the other does not detect the weld, the correction unit performs correction processing, and if the correction processing is not successful, it is determined that the rail crack is detected, and maintenance personnel is preferably notified to perform confirmation.
According to another aspect of the invention, the invention also provides an automatic rail weld joint identification method which is characterized in that the rail weld joint is identified by adopting the automatic rail weld joint identification system.
According to another aspect of the invention, the invention also provides a steel rail defect detection system, which is characterized in that the steel rail defect detection result is corrected by adopting the steel rail welding seam automatic identification system.
Compared with the prior art, the invention has the following technical effects: 1) The welding seam real-time automatic identification and/or marking are realized, the monitoring and the data analysis of flaw detection personnel are greatly facilitated, and the working flaw detection efficiency is improved; 2) The weld joint recognition result can be corrected, and the accuracy and the efficiency are improved; 3) The safety of railway operation is improved.
Drawings
FIG. 1 is a schematic structural view of an automatic rail weld identification system in accordance with a preferred embodiment of the present invention;
FIG. 2 is a schematic diagram of identifying welds by acoustic reflection in accordance with a preferred embodiment of the present invention;
fig. 3 is a schematic diagram of the workflow of an echo time gain compensation unit based on an FPGA and a programmable gain amplifier according to a preferred embodiment of the present invention.
Detailed Description
The present invention is described in its best mode by the following preferred embodiments with reference to the accompanying drawings, and the detailed description herein is to be construed as limiting the invention, since various changes and modifications can be made without departing from the spirit and scope of the invention.
Example 1
Referring to fig. 1-2, the invention provides an automatic rail weld joint identification system, which is characterized by comprising:
an acoustic wave sensor 2 configured to transmit acoustic waves to the rail and to receive echoes from the rail;
a coupling medium;
the rubber wheel 1 is internally fixedly provided with the acoustic wave sensor 2 and filled with the coupling medium, and is in rolling press connection with the steel rail tread 3 to form an acoustic wave transmission channel among the acoustic wave sensor, the coupling medium, the rubber wheel and the steel rail;
the welding line identification unit is used for processing the echo received by the acoustic wave sensor to identify a welding line;
the positioning unit is used for determining the coordinate position of the identified welding line on the steel rail;
a storage unit for storing correction data;
and the correction unit is used for correcting the identified welding line data according to the correction data.
It will be appreciated that the pulley 1 can roll on the rail tread, whereas the acoustic wave sensor 2 does not roll with the rolling of the pulley 1, its distance, angle and the position of the point of incidence of the acoustic wave on the rail tread are relatively fixed with respect to the rail tread. That is, during the rolling of the pulley 1, the acoustic wave sensor 2 is simply moved forward parallel to the rail tread, the position relative to the rail tread 3 preferably remaining substantially fixed during operation. It will be appreciated that the parallel movement of the sonic sensor 2 is to continuously identify defects at different locations in the rail. The acoustic wave may be, for example, an ultrasonic wave.
Further, the correction data may include the weld data and the corresponding coordinate positions thereof after the on-site confirmation from the railway maintenance department, or may include, for example, related data that are each identified as a weld by the weld identification unit a plurality of times (for example, 10 times or more), or a combination thereof. It will be appreciated that over time accumulation and machine learning, enriched correction data can be obtained.
The pulley 1 is preferably arranged on a rail inspection device that is movable along the rail and rolls on the rail tread 3 as the inspection device moves on the rail to achieve continuous identification of the rail weld 4.
Preferably, the acoustic wave sensor 2 is arranged such that the distance between the incidence point of the emitted acoustic wave on the rail tread and the rail tread center line is 0.14 to 0.4L, and a refraction angle of 35 to 50 degrees is formed at the rail tread, and an included angle of 8 to 15 degrees is formed with the rail longitudinal section, wherein L is the distance between the rail side face and the rail tread center line. It has been found that by a specific setting of the relative position of the acoustic wave sensor 2, a reliable detection of the rail weld can be achieved.
Preferably, the acoustic wave sensor comprises a first acoustic wave sensor and a second acoustic wave sensor which are respectively arranged on the inner side and the outer side of the steel rail, and the existence of the welding seam is determined only when the first acoustic wave sensor and the second acoustic wave sensor detect the welding seam at the same coordinate position (the same position of the steel rail). It will be appreciated that the interference is eliminated by two sets of sonic sensors for detecting the rail weld, for example, by locating the rail weld on both the inner and outer sides of a rail. Therefore, when one of the acoustic wave sensors fails or is detected by mistake, potential crack defects are removed as welding seams, and no later maintenance is performed, so that the running safety of the train can be ensured to the greatest extent.
Preferably, the weld recognition unit may include a first weld recognition unit and a second weld recognition unit corresponding to the first acoustic wave sensor and the second acoustic wave sensor, respectively, for processing according to echoes received by the first acoustic wave sensor and the second acoustic wave sensor, respectively, to independently recognize the weld.
Preferably, the automatic rail weld identification system further comprises an encoder unit for sending a trigger signal to the sonic sensor 2 to trigger the sonic sensor 2 to operate periodically and which follows the wheel rotation of the rail inspection device synchronously to determine the coordinate position of the detected weld 4 on the rail.
Preferably, the echoes include dihedral reflections from the butt-jaw strap-like projections at the weld. Advantageously, by the detection of this dihedral angle, a reliable detection of the weld can be achieved efficiently. It will be appreciated that the invention is not so limited and that other locations of the weld may be selected to reflect sound waves, for example, although the detection may not be optimal.
Preferably, the weld recognition unit further includes an echo time gain compensation unit in which a corresponding coefficient table of sound wave transmission time and gain values is stored to increase sensitivity of an echo from the dihedral angle and suppress interference waves other than the echo.
Preferably, when one of the first acoustic wave sensor and the second acoustic wave sensor detects the weld and the other does not detect the weld at the same coordinate position (the same position of the rail), it is determined that the rail is cracked, and a maintenance person is notified to confirm.
Preferably, the correction data is generated from the confirmation result and stored in the storage unit by, for example, a maintenance person. For example, the correction data may be a weld and its coordinate position, or may be a non-weld and its coordinate position.
Preferably, when one of the first acoustic sensor and the second acoustic sensor detects the weld and the other does not detect the weld at the same coordinate position (the same position of the rail), the correction processing is performed by the correction data, and if the correction processing is successful (that is, if the correction data does not exist in the correction data, the correction data is not related to the coordinate position), the rail crack is determined, and the maintenance personnel is notified to confirm.
Preferably, the invention also provides a rail welding seam automatic identification method, which is characterized in that the rail welding seam automatic identification system is adopted to identify the rail welding seam.
Preferably, the invention also provides a steel rail defect detection system, which is characterized in that the steel rail defect detection result is corrected by adopting the automatic steel rail welding seam recognition system.
Example 2
Preferably, the invention also provides an automatic rail weld joint identification system, which comprises a weld joint monitoring probe and a weld joint identification unit.
Preferably, referring to fig. 2, the weld monitoring probe includes an acoustic wave sensor 2, a coupling medium, and a pulley 1. The acoustic wave sensor realizes the transmission and the reception of acoustic waves. The acoustic wave sensor emits acoustic waves under the triggering of the external encoder, the acoustic waves are reflected in the steel rail, and the reflected acoustic waves are received by the acoustic wave sensor. Preferably, the acoustic wave sensor 2 has a frequency of 2MHz to 5MHz.
Preferably, the weld recognition unit processes the acoustic wave sensor echo information. Specifically, the unit sets a gate (threshold value) in the time span of reflection at the weld joint of the jaw part of the steel rail, when the gate is triggered by monitoring the echo of the acoustic wave sensor, the weld joint exists, and otherwise, the unit is a normal steel rail. The gate is set with an amplitude threshold value in a certain period of time of the echo, and when the amplitude of the echo signal exceeds the threshold value in the period of time, the gate is triggered. And after the weld joint is identified, sending the result to an information summarizing unit.
Preferably, the encoder adopts an incremental photoelectric encoder which is driven by a running wheel of the steel rail flaw detection equipment. The wheel of the flaw detection device walks one circle, and the encoder rotates 360 degrees. Every 360 degrees of rotation of the encoder, a fixed number of pulse trigger signals are outwards given as external triggers for starting one-time transmitting and receiving and information processing of the acoustic wave sensor. Since the output pulse signals of the encoder are uniform in rotation, i.e. the pulse signals output by the unit distance or angle of rotation are fixed, the number of rotation turns of the encoder is calculated by counting triggered outwards, and the number of rotation turns and the driving distance of the wheels can be obtained. Therefore, when the encoder is triggered each time, the corresponding relation between the flaw detection data and/or the welding seam information and a unique encoder position can be known exactly.
Preferably, the encoder triggers the resolution, i.e. how far the inspection apparatus travels, to perform an acoustic inspection. To meet different pulse trigger resolutions, each pulse may be set to trigger or trigger after receiving several consecutive pulses. The encoder triggering unit realizes high-resolution step scanning, so that the pulse emission interval of each acoustic wave sensor 2 is less than or equal to 3mm.
Preferably, the position of each encoder can accurately obtain the information of whether the welding line exists or not, the welding line identification and marking have no delay, the real-time performance is high, and the marking position is ensured to be timely and accurate. .
Preferably, it has been found that the rail weld joint has a band-like bulge at both the rail jaw and the web, which has a large difference in sound transmission characteristics from the rail base material. Specifically, the invention adopts the device shown in fig. 2 to realize the weld monitoring by adopting an acoustic wave reflection method. The acoustic wave sensor 2 is arranged in the pulley 1, the pulley 1 is tightly attached to the rail tread 3, and the pulley 1 is filled with liquid as a coupling medium for transmitting acoustic waves between the acoustic wave sensor 2 and the rail. And 4 is a welding line, and 5 is a dihedral angle formed by the welding line at the jaw part of the rail.
Preferably, the acoustic wave sensor 2 emits acoustic waves under the triggering of the encoder, the acoustic waves are refracted on the tread into the rail, and refraction occurs. If the acoustic wave is positioned at the welding seam position, the refraction acoustic wave in the steel rail can be reflected at the welding seam jaw dihedral angle 5, and the reflected acoustic wave is received by the acoustic wave sensor 2 through the leather wheel and the coupling medium. The gate is set according to the occurrence time of the reflected wave of the weld jaw dihedral 5. The reflected sound wave will appear in the sluice provided with the sound wave sensor 2, which is monitored by the weld recognition unit. If the welding seam is positioned at other rail jaw positions, the dihedral reflected waves of the welding seam jaw parts cannot appear, and the welding seam recognition unit cannot judge that the welding seam is the welding seam. The invention utilizes dihedral angle reflection brought by band-shaped bulges of the jaw of the rail head at the welding seam to distinguish normal steel rail and the welding seam, thereby realizing the monitoring of the welding seam.
Preferably, the steel rail grains at the weld joint are coarser, the clutter is large, and meanwhile, the reflection of sound waves at the tread is strong, so that the echo signals received by the sound wave sensor 2 are large in clutter, the interference to the dihedral angles of the jaw parts of the weld joint is obvious, and the false triggering of the gate is easy to cause. If the clutter amplitude is reduced by reducing the sensitivity setting, the weld seam jaw dihedral angle echo monitoring is affected, and the weld seam is missed. In order to solve the problems, the invention designs a time gain compensation (Time Gain Compensation, TGC) method based on an FPGA and a programmable gain amplifier, which can obviously inhibit interference waves nearby a weld joint jaw dihedral angle echo sensitivity and improve the weld joint recognition accuracy.
Preferably, the logic design block diagram of the echo time gain compensation method of the present invention is shown in fig. 3. And transmitting two groups of coefficients with one-to-one correspondence of the sound wave transmission time and the gain value to the FPGA, wherein the FPGA adopts an on-chip cache unit for storage. The time-gain coefficient table is set in such a way that a high gain is set for the weld seam jaw dihedral angle wave-out position and a low gain is set for the clutter position.
Preferably, the TGC function may be on or off. The TGC coefficient is a table designed a priori, setting different gain values at different echo times, which can be obtained by research and empirical summary. In the on state, when the trigger of the encoder comes, the FPGA reads a group of distance D0 and gain value G0 in TGC coefficient, on the premise that sound velocity of sound waves in the steel rail is known (sound wave longitudinal wave is 5.92 mm/mu s, transverse wave is 3.23 mm/mu s), the FPGA calculates the propagation distance D of the sound waves by recording sound wave transmission time, and when d=D0, the G0 is configured to the programmable gain amplifier by adopting a serial configuration interface. And then the FPGA reads a second group of distance gain coefficients D1 and G1, and when D is clocked to D1, the G0 is configured to the programmable gain amplifier by adopting a serial configuration interface until the FPGA finishes configuring the last group of distance gain values. The logic will wait for the next encoder trigger to come.
Preferably, the operator may also manually modify the gain while the TGC function is off.
Preferably, the invention adopts the FPGA to carry out time gain compensation of the weld jaw dihedral angle echo, improves the sensitivity and monitoring accuracy of the weld jaw dihedral angle echo, has higher real-time performance than data processing, has more accurate result, reduces calculation pressure and improves the operation efficiency of the system.
Compared with the prior art, the invention has the following technical effects: 1) The welding seam real-time automatic identification and/or marking are realized, the monitoring and the data analysis of flaw detection personnel are greatly facilitated, and the working flaw detection efficiency is improved; 2) The weld joint recognition result can be corrected, and the accuracy and the efficiency are improved; 3) The safety of railway operation is improved.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.
Claims (8)
1. An automatic rail weld identification system, comprising:
an acoustic wave sensor configured to emit an acoustic wave to the rail and which itself receives an echo from the rail jaw weld;
a coupling medium;
the rubber wheel is internally fixedly provided with the acoustic wave sensor and filled with the coupling medium, and can be in rolling press connection with the steel rail tread to form an acoustic wave transmission channel among the acoustic wave sensor, the coupling medium, the rubber wheel and the steel rail;
the welding line identification unit is used for processing the echo received by the acoustic wave sensor to identify a welding line, and the welding line exists when the amplitude of the echo triggers a set amplitude threshold value;
the positioning unit is used for determining the coordinate position of the identified welding line on the steel rail;
a storage unit for storing correction data;
a correction unit configured to correct the identified weld data based on the correction data;
the method comprises the steps of arranging an acoustic wave sensor so that the distance between an incidence point of a steel rail tread and a central line of the steel rail tread is 0.14-0.4L, forming a refraction angle of 35-50 degrees at the steel rail tread, and forming an included angle of 8-15 degrees with a longitudinal section of the steel rail, wherein L is the distance between a side surface of the steel rail and the central line of the steel rail tread;
the sound wave sensor comprises a first sound wave sensor and a second sound wave sensor which are respectively arranged at the inner side and the outer side of a steel rail, and the existence of a welding line is determined when the first sound wave sensor and the second sound wave sensor detect the welding line at the same coordinate position;
the echoes come from dihedral reflections caused by the jaw band-shaped projections of the rail head at the weld joint.
2. The automatic rail weld joint recognition system according to claim 1, wherein the pulley is provided on a rail flaw detection device movable along a rail, and rolls on a rail tread as the flaw detection device moves on the rail to realize continuous recognition of the rail weld joint.
3. The automatic rail weld identification system of claim 1, further comprising an encoder unit for sending a trigger signal to the sonic sensor to trigger the sonic sensor to operate periodically and which synchronizes the rotation of the wheels of the follower vehicle to determine the coordinate location of the detected weld on the rail.
4. The automatic rail weld identification system of claim 1, wherein the weld identification unit further comprises an echo time gain compensation unit in which a table of corresponding coefficients of sonic transmission time and gain values is stored.
5. The automatic rail weld recognition system according to claim 1, wherein when one of the first acoustic sensor and the second acoustic sensor at the same position of the rail detects a weld and the other does not detect a weld, it is determined that the rail is cracked, and a maintenance person is notified to confirm.
6. The automatic rail weld recognition system according to claim 5, wherein the correction data is generated based on the result of the verification and stored in the storage unit.
7. The automatic rail weld joint recognition system according to claim 1, wherein the correction unit performs correction processing when one of the first acoustic sensor and the second acoustic sensor detects a weld joint and the other does not detect a weld joint at the same position of the rail, determines that the rail is cracked if the correction processing is successful, and notifies maintenance personnel of confirmation.
8. An automatic rail weld recognition method characterized in that the rail weld is recognized by adopting the automatic rail weld recognition system according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010530223.4A CN113804755B (en) | 2020-06-11 | 2020-06-11 | Automatic rail weld joint recognition system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010530223.4A CN113804755B (en) | 2020-06-11 | 2020-06-11 | Automatic rail weld joint recognition system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113804755A CN113804755A (en) | 2021-12-17 |
| CN113804755B true CN113804755B (en) | 2024-01-12 |
Family
ID=78891943
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010530223.4A Active CN113804755B (en) | 2020-06-11 | 2020-06-11 | Automatic rail weld joint recognition system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113804755B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114561871A (en) * | 2022-03-31 | 2022-05-31 | 江苏润扬大桥发展有限责任公司 | Be used for steel bridge deck pavement deep level disease infrared detection equipment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101398411A (en) * | 2008-11-07 | 2009-04-01 | 哈尔滨工业大学 | Rail tread defect rapid scanning and detecting method and device thereof |
| CN104713952A (en) * | 2013-12-16 | 2015-06-17 | 中国铁道科学研究院 | Double-wave wheel type probe for steel rail flaw detection |
| CN105259254A (en) * | 2015-11-12 | 2016-01-20 | 湖南高速铁路职业技术学院 | Scanning device for steel rail bottom transverse cracks |
| CN106053611A (en) * | 2016-05-25 | 2016-10-26 | 中国铁道科学研究院 | Wheel type probe capable of detecting rail bottoms |
| CN205941463U (en) * | 2016-08-11 | 2017-02-08 | 合肥超科电子有限公司 | Wheel type probe support and wheel type probe are visited to jam -proof rail ultrasonic wave |
| CN106896157A (en) * | 2017-03-16 | 2017-06-27 | 华南理工大学 | Based on the 3D ultrasonic rail examination method and devices of splicing visualization apart from self adaptation |
| CN210427453U (en) * | 2019-06-04 | 2020-04-28 | 北京云率数据科技有限公司 | Automatic aligning system of steel rail flaw detection device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11067539B2 (en) * | 2014-12-24 | 2021-07-20 | Technological Resources Pty Ltd | System for detecting a break in a rail |
-
2020
- 2020-06-11 CN CN202010530223.4A patent/CN113804755B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101398411A (en) * | 2008-11-07 | 2009-04-01 | 哈尔滨工业大学 | Rail tread defect rapid scanning and detecting method and device thereof |
| CN104713952A (en) * | 2013-12-16 | 2015-06-17 | 中国铁道科学研究院 | Double-wave wheel type probe for steel rail flaw detection |
| CN105259254A (en) * | 2015-11-12 | 2016-01-20 | 湖南高速铁路职业技术学院 | Scanning device for steel rail bottom transverse cracks |
| CN106053611A (en) * | 2016-05-25 | 2016-10-26 | 中国铁道科学研究院 | Wheel type probe capable of detecting rail bottoms |
| CN205941463U (en) * | 2016-08-11 | 2017-02-08 | 合肥超科电子有限公司 | Wheel type probe support and wheel type probe are visited to jam -proof rail ultrasonic wave |
| CN106896157A (en) * | 2017-03-16 | 2017-06-27 | 华南理工大学 | Based on the 3D ultrasonic rail examination method and devices of splicing visualization apart from self adaptation |
| CN210427453U (en) * | 2019-06-04 | 2020-04-28 | 北京云率数据科技有限公司 | Automatic aligning system of steel rail flaw detection device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113804755A (en) | 2021-12-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102084245B (en) | The method and apparatus of on-the-spot ultrasonic examination railway track | |
| CA2732971C (en) | Apparatus for and method of detecting defects in a rail joint bar | |
| US10422773B2 (en) | Mobile ultrasonic rail inspection system and method | |
| CN101424664B (en) | Rail tread crack ultrasonic detection device and detecting method | |
| WO2003016897A2 (en) | A method and apparatus for inspecting a product with ultrasound | |
| JPH02225702A (en) | Method and device for positioning transversing direction of member moving along railroad rail | |
| JPH0332021B2 (en) | ||
| CN113804755B (en) | Automatic rail weld joint recognition system and method | |
| CN115656343B (en) | Steel rail weld defect positioning method based on serial matrix scanning | |
| CN105510441A (en) | Linkage detection method adopting multi-channel combined probes | |
| CA1075805A (en) | Ultrasonic testing of seams | |
| US11035827B2 (en) | Methods and instrumentation for detection of transverse rolling contact fatigue rail defects within head-hardened rail | |
| CN105510442A (en) | Dynamic linkage focus detection method adopting multiple phased array probes | |
| KR100975330B1 (en) | Multi Channel Ultrasonic Welding Inspection System and Control Method | |
| CN106404909A (en) | Quality detecting device of laser welding system | |
| CN113804756B (en) | Rail defect real-time correction system and method | |
| JP2009058238A (en) | Method and device for defect inspection | |
| RU2621216C1 (en) | Intra tube method of ultrasonic testing of welds | |
| CN112014464A (en) | Automatic steel rail welding seam identification system and method | |
| CN113804757B (en) | Automatic flaw detector | |
| CN112014463A (en) | Steel rail acoustic flaw detection system and flaw detection method | |
| CN218601221U (en) | Automatic change rail equipment of detecting a flaw | |
| RU2801895C1 (en) | Ultrasonic testing method | |
| RU2231783C2 (en) | Ultrasonic flaw detector | |
| RU2764571C1 (en) | Ultrasonic method for detecting and evaluating rail welded joints in high-speed inspection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |