CN116519787A - Third rail power receiving boot detection system and method - Google Patents
Third rail power receiving boot detection system and method Download PDFInfo
- Publication number
- CN116519787A CN116519787A CN202310815634.1A CN202310815634A CN116519787A CN 116519787 A CN116519787 A CN 116519787A CN 202310815634 A CN202310815634 A CN 202310815634A CN 116519787 A CN116519787 A CN 116519787A
- Authority
- CN
- China
- Prior art keywords
- power receiving
- image
- receiving boot
- area
- boot
- 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.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 59
- 238000000034 method Methods 0.000 title claims abstract description 16
- 230000007547 defect Effects 0.000 claims abstract description 21
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 claims description 49
- 229910052799 carbon Inorganic materials 0.000 claims description 49
- 230000001960 triggered effect Effects 0.000 claims description 8
- 238000012937 correction Methods 0.000 claims description 7
- 229910000831 Steel Inorganic materials 0.000 claims description 5
- 238000005259 measurement Methods 0.000 claims description 5
- 239000010959 steel Substances 0.000 claims description 5
- 230000001502 supplementing effect Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 description 6
- 230000006872 improvement Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 238000005299 abrasion Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 2
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000000712 assembly Effects 0.000 description 1
- 238000000429 assembly Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N27/00—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means
- G01N27/72—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating magnetic variables
- G01N27/82—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating magnetic variables for investigating the presence of flaws
- G01N27/90—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating magnetic variables for investigating the presence of flaws using eddy currents
- G01N27/904—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating magnetic variables for investigating the presence of flaws using eddy currents with two or more sensors
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B7/00—Measuring arrangements characterised by the use of electric or magnetic techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/0008—Industrial image inspection checking presence/absence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Chemical & Material Sciences (AREA)
- Health & Medical Sciences (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Analytical Chemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Electrochemistry (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Train Traffic Observation, Control, And Security (AREA)
Abstract
The invention discloses a third rail power receiving boot detection system and a method, wherein the system comprises an image acquisition module, a third rail power receiving boot detection module and a third rail power receiving boot detection module, wherein the image acquisition module is used for acquiring a 2D area array image, a 2D linear array image and a 3D image of the power receiving boot; the triggering module is used for controlling the opening and closing of the image acquisition module; the speed measuring shaft module is used for measuring the shaft and the speed of the railway vehicle to be measured; the analysis module is used for analyzing the 2D linear array image and the 3D image acquired by the image acquisition module to judge whether the power receiving boot has a size defect, and analyzing the 2D area array image acquired by the image acquisition module to judge whether the power receiving boot has a surface defect. The invention can realize automatic detection, remove the influence of artificial subjective factors, reduce the inefficiency in the traditional operation mode and reduce the labor cost and difficulty. And when the train is in normal operation, automatic online non-contact detection is provided. The geometrical parameters and the surface defect condition of the power receiving boots can be monitored in time, and faults of various power receiving boots can be early warned in time. Ensuring the safe operation of the train.
Description
Technical Field
The invention belongs to the technical field of rail vehicle detection, and particularly relates to a system and a method for detecting a third rail power receiving boot of a rail vehicle.
Background
The current-receiving boot current-receiving device is mainly applied to a circuit of a third rail power supply mode, and the current-receiving boot is arranged at the positions, close to the middle part outside the vehicle, of two sides of the vehicle bogie frame. It is put down when in use and is retracted when not in use, just like the landing gear of an airplane. All the bogie frames of the motor car are provided with two sets of current collectors, and only one bogie of the trailer is provided with two sets of current collectors. The mounting bracket of each current collector is fixed under the side beams of the bogie frame with 4 bolts.
The contact rail is used as a common power supply mode of a subway, and different from a state train which gets electricity through a contact net, the subway train obtains electric energy through the contact of the power receiving boots and the contact rail. The state of the power receiving boot is critical to the subway traction power supply system. Once the mechanical fault or the geometrical parameter overrun occurs to the related parts of the power receiving boot, the normal current taking of the power receiving boot is affected, the operation vehicle can not normally run, and even the safety quality accident occurs. Therefore, the geometric parameters of the third rail power receiving shoe of the subway and whether surface defect detection is in place are important.
The existing power receiving boot detection is to measure the thickness of a carbon slide plate of the power receiving boot by utilizing a steel ruler, and visually check whether the appearance of the carbon slide plate is normal or not, and whether a damaged surface or a fracture crack exists or not. The manual detection is finished by human eyes, so that the measurement error is large, the measurement efficiency is low, the labor intensity is high, and the detection omission is easy to cause. And the state of the power receiving boot cannot be detected in the warehouse-in and warehouse-out or operation process.
Disclosure of Invention
In view of the above, the present invention provides a third rail power receiving shoe detection system and method, which can automatically detect the power receiving shoe on line.
In order to solve the technical problems, the technical scheme of the invention is to adopt a third rail power receiving boot detection system, comprising:
the image acquisition module is used for acquiring a 2D area array image, a 2D linear array image and a 3D image of the power receiving boot;
the triggering module is used for controlling the opening and closing of the image acquisition module;
the speed measuring shaft module is used for measuring the shaft and the speed of the railway vehicle to be measured;
the analysis module is used for analyzing the 2D linear array image and the 3D image acquired by the image acquisition module to judge whether the power receiving boot has a size defect, and analyzing the 2D area array image acquired by the image acquisition module to judge whether the power receiving boot has a surface defect.
As an improvement, the image acquisition module comprises a linear scanning 3D camera for acquiring a 3D image and a 2D linear array image of the power receiving boot and an area array camera for acquiring a 2D area array image of the power receiving boot.
As a further improvement, the image acquisition module further comprises a light supplementing light source.
As a further development, the triggering module comprises a start sensor and an end sensor arranged at both ends of the detection area on the track; a trigger sensor for triggering the image acquisition module to acquire images is arranged in the detection area; the trigger sensor is turned on when the start sensor is triggered and turned off when the end sensor is triggered.
As an improvement, the 2D trigger sensor and the 3D trigger sensor are eddy current sensors.
As an improvement, the tachometer shaft module is a magnetic steel sensor.
The invention also provides a third rail power receiving boot detection method which is applied to the third rail power receiving boot detection system and comprises the following steps:
the method comprises the steps of collecting 2D area array images, 2D linear array images and 3D images of the railway vehicle to be tested, and performing axle counting and speed measurement on the railway vehicle to be tested; the 2D linear array image and the 3D image are combined;
judging, namely judging whether the number of axes is an integer multiple of 4, if so, acquiring a power receiving boot area from the acquired 3D image according to the template file; judging whether the power receiving boot area contains the power receiving boot or not according to the mark on the template file, and if not, considering that the power receiving boot is lost;
correcting the acquired 2D linear array image and 3D image to the actual width by utilizing the speed of the railway vehicle to be detected;
further comprising a detection step comprising:
dividing the carbon slide plate image from the power receiving boot area in the 2D linear array image, so that the carbon slide plate point cloud in the 3D image is divided, and if no carbon slide plate exists, the power receiving boot is considered to be lost;
measuring the inclination angle of the carbon slide plate in the segmented carbon slide plate image;
correcting the carbon slide plate image to be horizontal, so that the carbon slide plate point cloud is also horizontal, and measuring the thickness of the carbon slide plate point cloud;
positioning a power receiving boot area from the 2D area array image;
and carrying out feature recognition on the power receiving boot area, and judging whether the power receiving boot has surface defects or not.
As an improvement, if the number of axes is not an integer multiple of 4, dividing the 3D image to obtain a power receiving boot area, comparing the number of divided power receiving boots with the number of power receiving boots on the template file, ending the detection if the number of divided power receiving boots is not equal, and entering the correction step and the detection step if the number of divided power receiving boots is equal.
As an improvement, the method for obtaining the power receiving boot area by segmenting the 3D image comprises the following steps:
setting a depth threshold;
and taking the point cloud with the depth value smaller than the depth threshold value as the point cloud of the power receiving boot area.
The invention has the advantages that:
the invention detects the state of the power receiving boot in the process of entering and exiting the subway train or running the subway train, and performs non-contact online detection by using a machine vision and intelligent image recognition method. The system can automatically calculate abnormal conditions of visual parts such as abrasion, inclination, loss, surface foreign matters, cracks, scratches, burns and the like of the carbon slide plate of the power receiving boot and alarm. Therefore, the detection efficiency and the detection accuracy are improved, and the safety of the detection process and the detection personnel is guaranteed to a certain extent.
Compared with the prior art, the invention has the beneficial effects that:
1. the automatic detection is realized, the influence of artificial subjective factors is removed, the inefficiency in the traditional operation mode is reduced, and the labor cost and difficulty can be reduced.
2. And when the train is in normal operation, automatic online non-contact detection is provided. The geometrical parameters and the surface defect condition of the power receiving boots can be monitored in time, and faults of various power receiving boots can be early warned in time. Ensuring the safe operation of the train.
3. And the data platform carries out grading alarm processing and early warning on the service life of the power receiving boot on the detection value.
Drawings
Fig. 1 is a schematic diagram of the structure of the present invention.
FIG. 2 is a flow chart of the detection in the present invention.
Detailed Description
In order to make the technical scheme of the present invention better understood by those skilled in the art, the present invention will be further described in detail with reference to the following specific embodiments.
As shown in fig. 1, the present invention provides a third rail power receiving shoe detection system, including:
the image acquisition module is used for acquiring a 2D area array image, a 2D linear array image and a 3D image of the power receiving boot;
the triggering module is used for controlling the opening and closing of the image acquisition module;
the speed measuring shaft module is used for measuring the shaft and the speed of the railway vehicle to be measured;
the analysis module is used for analyzing the 2D linear array image and the 3D image acquired by the image acquisition module to judge whether the power receiving boot has a size defect, and analyzing the 2D area array image acquired by the image acquisition module to judge whether the power receiving boot has a surface defect;
and the alarm module is used for alarming when the size defect and the surface defect exceed the threshold value.
Specifically, the image acquisition module comprises a line scanning 3D camera for acquiring a 3D image and a 2D linear array image of the power receiving boot and an area array camera for acquiring a 2D area array image of the power receiving boot. It is envisioned that the image acquisition module further includes a light supplementing light source in order to enhance brightness to make the acquired 2D image clearer.
According to the position design installation fixed knot of area array camera and line sweep 3D camera constructs, adopts the stand to support installation camera. The center of the upright post structure is at a distance of 2300mm from the center of the track, and the acquisition assemblies are symmetrically arranged on the vehicle side and used for acquiring the power receiving boots on the two sides. The main purpose of the area array camera is to shoot a 2D area array image of the top surface of the carbon slide plate of the power receiving boot, and the main purpose of the line scanning 3D camera is to acquire a 3D point cloud and a 2D line array image of the carbon slide plate of the power receiving boot, so that the arrangement of the area array camera and the line scanning 3D camera can be adjusted according to the purpose.
The triggering module comprises a start sensor and an end sensor which are arranged at two ends of a detection area on the track; a trigger sensor for triggering the image acquisition module to acquire images is arranged in the detection area; the trigger sensor is turned on when the start sensor is triggered and turned off when the end sensor is triggered. In this embodiment, the 2D trigger sensor and the 3D trigger sensor are both eddy current sensors.
The speed of the railway vehicle passing through the image acquisition module is generally changed, and the third rail power receiving boot detection device uses a 3D linear array camera to acquire images at a fixed frame rate, so that the images acquired by the railway vehicle at a high speed show a compression effect, and the images acquired by the railway vehicle at a low speed show a stretching effect. In order to improve the visual viewing effect and the accuracy of automatic defect detection of the algorithm, it is necessary to correct all compressed or stretched images to the same resolution, so that the speed correction algorithm is required to correct the speed of the passing data so that all images are corrected to the same resolution.
The speed correction needs to acquire the speed of the train, and the speed measuring module is used for measuring the axle and measuring the speed of the railway vehicle to be measured. The tachometer shaft module adopted in the embodiment is a magnetic steel sensor.
The triggering principle of the area array camera is as follows:
(1) when a train enters a detection area, a start sensor is triggered first and used as a train receiving signal of the whole system, and an area array camera is opened to prepare for acquisition.
(2) When each wheel pair is pressed to the 2D sensor, the area array camera can take a picture, and images possibly existing in the power-on boot are collected.
(3) When the first wheel set of the head car presses to the end sensor, indicating that the rail car has completely passed the acquisition module, the system is on standby and the area camera is off.
The triggering principle of the line scanning 3D camera is as follows:
(1) when a train enters a detection area, a start sensor is triggered first and used as a train receiving signal of the whole system, and a line scanning 3D camera is opened to prepare for acquisition.
(2) When the first wheel set is pressed against the 3D sensor, the line scan 3D camera starts to take pictures at a fixed frame rate.
(3) Thereafter each wheel set is pressed to a tachometer shaft module, which records the shaft number and records the speed of each shaft.
(4) The first wheel set of the head car presses to the end sensor, indicating that the rail car has passed completely through the acquisition module, at which time the system is on standby and the line scan 3D camera is also off.
In addition, in order to further provide an industrial personal computer, a server, a UPS uninterrupted power supply, a PDU power distribution unit, a KVM cabinet rack type display, a switch and the like in the system, the devices can be arranged in the electric control cabinet. The image collected by the collecting unit is transmitted to a server (an analyzing module), and defects of the power receiving boot in the image are analyzed through an algorithm.
In order to detect and analyze the state of the power receiving shoe, different algorithm functions need to be developed in a targeted manner on the 3D and 2D images. Detecting abrasion, inclination angle and loss of the carbon slide plate on an image acquired by the online scanning 3D camera; and detecting foreign matters, cracks, scratches and burning on the surface of the carbon slide plate on the image acquired by the area array camera. Therefore, as shown in fig. 2, the present invention further provides a third rail power receiving shoe detection method, which is applied to the third rail power receiving shoe detection system, and includes:
s1, acquiring a 2D area array image, a 2D linear array image and a 3D image of a railway vehicle to be tested, and performing axle counting and speed measurement on the railway vehicle to be tested; the 2D linear array image and the 3D image are combined.
In the invention, 2D area array images are acquired by an area array camera, and 2D linear array images and 3D images are acquired by a linear scanning 3D camera. The axle counting and speed measuring of the railway vehicle to be measured are carried out by a magnetic steel sensor.
In addition, since both the 2D linear array image and the 3D image are acquired by the linear scanning 3D camera, the two images are automatically combined after being acquired, so that the operation on one image can be mapped to the other image. For example, the 2D line image is cut, and accordingly, the point cloud of the corresponding region in the 3D image is also cut.
S2, judging whether the number of axes is an integer multiple of 4, if so, acquiring a power receiving boot area from the acquired 3D image according to the template file; judging whether the power receiving boot area contains the power receiving boot or not according to the mark on the template file, and if not, considering that the power receiving boot is lost.
If the number of axes is not an integer multiple of 4, dividing the 3D image to obtain a power receiving boot area, comparing the number of the divided power receiving boots with the number of the power receiving boots on the template file, ending the detection if the number of the divided power receiving boots is not equal, and jumping to the correction step and the detection step below if the number of the divided power receiving boots is equal. In the invention, the method for obtaining the power receiving boot area by dividing the 3D image comprises the following steps: setting a depth threshold; and taking the point cloud with the depth value smaller than the depth threshold value as the point cloud of the power receiving boot area.
Before acquiring the power receiving boot area, a template file and axle counting information which are set for each type of vehicle type in advance are required to be read, and a bogie image containing the power receiving boot is acquired through the template file and the axle counting information. The 3D image of each bogie can be obtained from the collected 3D images through the triggering time information of each shaft, and all the bogies which should contain the power receiving boots can be finally obtained through the information of each bogie recorded in the template file.
There are 4 axles per car, so the total axle count should be a multiple of 4. If this condition is not satisfied, it is indicated that the axle is not being picked. At this time, the power receiving boot areas can only be obtained on the 3D point cloud image through image calculation, and the subsequent algorithm analysis can be performed only when the number of the power receiving boot areas is the same as that in the template file. If the power receiving boot areas are inconsistent, the power receiving boot areas cannot be judged to belong to which bogie, and 3D image algorithm analysis can only be finished in advance.
The power receiving boot is a device which extends outwards on the bogie to take power, and in the 3D point cloud image acquired by the camera, the power receiving boot area is closer to the line scanning 3D camera relative to other parts of the bogie, so that the depth value of the power receiving boot area is far smaller than that of other structures on the bogie. Therefore, the accurate region of the power receiving boot can be obtained by dividing the 3D image set with the threshold value, and when a large enough power receiving boot region cannot be obtained within the set depth threshold value range, the power receiving boot is considered to be lost.
And S3, correcting the acquired 2D linear array image and 3D image to the actual width by using the speed of the railway vehicle to be tested.
Because the speed of the vehicle is different during each acquisition, the power-receiving boot images acquired by the 3D linear array camera are stretched to different degrees in the passing direction, the images acquired by the train with high speed show a compression effect, and the images acquired by the train with low speed show a stretching effect. In order to improve the visual watching effect and the accuracy of automatic defect detection of the algorithm, the image of the power receiving boot needs to be corrected before the algorithm analysis, and then the algorithm analysis is carried out, so that all the images are corrected to the same resolution.
S4, detecting, namely, specifically comprising the following steps:
s411 is used for dividing the carbon slide plate image from the power receiving boot area in the 2D linear array image, so that the carbon slide plate point cloud in the 3D image is divided, and the power receiving boot is considered to be lost if the carbon slide plate is not used.
Before detecting the thickness and tilt angle of the carbon sled of the power receiving shoe, it is necessary to accurately acquire the carbon sled area in the power receiving shoe image. In the 2D linear array image, the region characteristics of the carbon slide plate are obvious, the segmentation difficulty is low, and the carbon slide plate can be segmented in the 2D linear array image acquired by the 3D camera by using deep learning. Because the 2D linear array image and the 3D image are combined, the carbon slide plate point cloud in the 3D image is naturally segmented. If the carbon slide plate is directly segmented from the 3D image, the difficulty is high and the accuracy is low.
S412, measuring the inclination angle of the carbon slide plate in the segmented carbon slide plate image.
In the segmented carbon sled image, the smallest bounding rectangle that can obtain the carbon sled area provided by the OpenCV library, through which the tilt angle of the carbon sled area relative to the entire image can be obtained, which is equal to the actual tilt angle of the power receiving shoe.
S413 corrects the carbon sled image to be horizontal so that the carbon sled point cloud is also horizontal, and measures the thickness of the carbon sled point cloud.
When the thickness is detected, the thickness value between the upper edge and the lower edge of the carbon slide plate needs to be calculated, and because the carbon slide plate may be inclined, the inclination correction needs to be carried out on the carbon slide plate before the thickness of the power receiving boot is detected. The carbon slide plate can be reversely rotated according to the inclination angle detection result, and the carbon slide plate is corrected to a state of no inclination. After the angle correction, the maximum thickness of the carbon slide plate is calculated by taking the upper edge and the lower edge of the carbon slide plate on an image in the x direction (namely, perpendicular to the driving direction) of the 3D point cloud image according to the segmentation result of the power receiving boot.
In the invention, an area-array camera is used for collecting a 2D area-array image of the surface of the carbon slide plate on the power receiving boot, and then the damage of the surface of the carbon slide plate, including foreign matters, cracks, scratches and burning, is analyzed through an algorithm. The 2D image is acquired by an area-array camera, compared with the image acquired by a line-scan 3D camera, the 2D image does not need to be corrected, and the method comprises the following specific steps:
s421, positioning a power receiving boot area from the 2D area array image.
In order to analyze the defects of the surface of the power receiving boot more accurately, an image only containing the power receiving boot area needs to be acquired from the 2D area array camera through a depth positioning model, and the positioning model needs to have high accuracy and high processing speed in an analysis flow. In the embodiment, a YOLO series deep learning positioning model with both positioning speed and positioning precision is adopted to obtain the power receiving boot area.
S422, carrying out feature recognition on the power receiving boot area, and judging whether surface defects exist on the power receiving boot.
The characteristics of the power receiving boot are identified by foreign matters, cracks, scratches and burning, and the characteristics are identified on the positioned power receiving boot area. The present embodiment uses the YOLO detection model for feature recognition of foreign substances and defects.
The foregoing is merely a preferred embodiment of the present invention, and it should be noted that the above-mentioned preferred embodiment should not be construed as limiting the invention, and the scope of the invention should be defined by the appended claims. It will be apparent to those skilled in the art that various modifications and adaptations can be made without departing from the spirit and scope of the invention, and such modifications and adaptations are intended to be comprehended within the scope of the invention.
Claims (10)
1. A third rail powered shoe detection system, comprising:
the image acquisition module is used for acquiring a 2D area array image, a 2D linear array image and a 3D image of the power receiving boot;
the triggering module is used for controlling the opening and closing of the image acquisition module;
the speed measuring shaft module is used for measuring the shaft and the speed of the railway vehicle to be measured;
the analysis module is used for analyzing the 2D linear array image and the 3D image acquired by the image acquisition module to judge whether the power receiving boot has a size defect, and analyzing the 2D area array image acquired by the image acquisition module to judge whether the power receiving boot has a surface defect.
2. A third rail powered shoe detection system according to claim 1, comprising: the image acquisition module comprises a line scanning 3D camera for acquiring a 3D image and a 2D linear array image of the power receiving boot and an area array camera for acquiring a 2D area array image of the power receiving boot.
3. A third rail powered shoe detection system according to claim 2, comprising: the image acquisition module further comprises a light supplementing light source.
4. A third rail powered shoe detection system according to claim 1, comprising: the triggering module comprises a start sensor and an end sensor which are arranged at two ends of a detection area on the track; a trigger sensor for triggering the image acquisition module to acquire images is arranged in the detection area; the trigger sensor is turned on when the start sensor is triggered and turned off when the end sensor is triggered.
5. A third rail powered shoe detection system as claimed in claim 4, comprising: the trigger sensor comprises a 3D trigger sensor used for triggering 2D linear array images and 3D image acquisition and a 2D trigger sensor used for triggering 2D linear array image acquisition.
6. A third rail powered shoe detection system as claimed in claim 5, comprising: the 2D trigger sensor and the 3D trigger sensor are eddy current sensors.
7. A third rail powered shoe detection system according to claim 1, comprising: the tachometer shaft module is a magnetic steel sensor.
8. A third rail power receiving shoe detection method applied to the third rail power receiving shoe detection system according to any one of claims 1 to 7, characterized by comprising:
the method comprises the steps of collecting 2D area array images, 2D linear array images and 3D images of the railway vehicle to be tested, and performing axle counting and speed measurement on the railway vehicle to be tested; the 2D linear array image and the 3D image are combined;
judging, namely judging whether the number of axes is an integer multiple of 4, if so, acquiring a power receiving boot area from the acquired 3D image according to the template file; judging whether the power receiving boot area contains the power receiving boot or not according to the mark on the template file, and if not, considering that the power receiving boot is lost;
correcting the acquired 2D linear array image and 3D image to the actual width by utilizing the speed of the railway vehicle to be detected;
further comprising a detection step comprising:
dividing the carbon slide plate image from the power receiving boot area in the 2D linear array image, so that the carbon slide plate point cloud in the 3D image is divided, and if no carbon slide plate exists, the power receiving boot is considered to be lost;
measuring the inclination angle of the carbon slide plate in the segmented carbon slide plate image;
correcting the carbon slide plate image to be horizontal, so that the carbon slide plate point cloud is also horizontal, and measuring the thickness of the carbon slide plate point cloud;
positioning a power receiving boot area from the 2D area array image;
and carrying out feature recognition on the power receiving boot area, and judging whether the power receiving boot has surface defects or not.
9. The third rail power receiving shoe detection method according to claim 8, wherein: if the number of axes is not an integer multiple of 4, dividing the 3D image to obtain a power receiving boot area, comparing the number of the divided power receiving boots with the number of the power receiving boots on the template file, ending the detection if the number of the divided power receiving boots is not equal, and entering a correction step and a detection step if the number of the divided power receiving boots is equal.
10. The third rail power receiving shoe detecting method as claimed in claim 9, wherein the method for obtaining the power receiving shoe region by dividing the 3D image comprises:
setting a depth threshold;
and taking the point cloud with the depth value smaller than the depth threshold value as the point cloud of the power receiving boot area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310815634.1A CN116519787A (en) | 2023-07-05 | 2023-07-05 | Third rail power receiving boot detection system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310815634.1A CN116519787A (en) | 2023-07-05 | 2023-07-05 | Third rail power receiving boot detection system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116519787A true CN116519787A (en) | 2023-08-01 |
Family
ID=87390759
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310815634.1A Pending CN116519787A (en) | 2023-07-05 | 2023-07-05 | Third rail power receiving boot detection system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116519787A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117876368A (en) * | 2024-03-11 | 2024-04-12 | 成都唐源电气股份有限公司 | Method and system for detecting abrasion and crack of carbon slide plate of contact rail collector shoe |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN207882170U (en) * | 2018-02-28 | 2018-09-18 | 北京康拓红外技术股份有限公司 | A kind of EMU critical component installation condition image detection device |
| CN109374636A (en) * | 2018-11-29 | 2019-02-22 | 成都铁安科技有限责任公司 | Pantograph image acquisition system, detection system and detection method |
| CN110030960A (en) * | 2019-05-07 | 2019-07-19 | 中国铁道科学研究院集团有限公司 | Steel-aluminum conductor rail wear detecting system and method |
| CN111238393A (en) * | 2020-01-20 | 2020-06-05 | 成都铁安科技有限责任公司 | Pantograph carbon slide plate detecting system and its control method |
| CN111942434A (en) * | 2020-06-30 | 2020-11-17 | 北京康拓红外技术股份有限公司 | Intelligent fault image detection device for key parts of railway wagon |
| CN112208585A (en) * | 2020-09-30 | 2021-01-12 | 深圳市平方科技股份有限公司 | Train information detection system and method thereof |
| CN112964180A (en) * | 2021-02-08 | 2021-06-15 | 辽宁鼎汉奇辉电子系统工程有限公司 | Urban rail vehicle collector shoe detection system |
| CN113865490A (en) * | 2021-09-24 | 2021-12-31 | 东莞市诺丽电子科技有限公司 | Non-contact collector shoe carbon sliding plate abrasion detection device and abrasion detection method |
| CN114511519A (en) * | 2022-01-20 | 2022-05-17 | 南京理工大学 | Train bottom bolt loss detection method based on image processing |
| CN114543661A (en) * | 2020-11-27 | 2022-05-27 | 南京拓控信息科技股份有限公司 | Subway vehicle 360-degree image detection system and detection method thereof |
-
2023
- 2023-07-05 CN CN202310815634.1A patent/CN116519787A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN207882170U (en) * | 2018-02-28 | 2018-09-18 | 北京康拓红外技术股份有限公司 | A kind of EMU critical component installation condition image detection device |
| CN109374636A (en) * | 2018-11-29 | 2019-02-22 | 成都铁安科技有限责任公司 | Pantograph image acquisition system, detection system and detection method |
| CN110030960A (en) * | 2019-05-07 | 2019-07-19 | 中国铁道科学研究院集团有限公司 | Steel-aluminum conductor rail wear detecting system and method |
| CN111238393A (en) * | 2020-01-20 | 2020-06-05 | 成都铁安科技有限责任公司 | Pantograph carbon slide plate detecting system and its control method |
| CN111942434A (en) * | 2020-06-30 | 2020-11-17 | 北京康拓红外技术股份有限公司 | Intelligent fault image detection device for key parts of railway wagon |
| CN112208585A (en) * | 2020-09-30 | 2021-01-12 | 深圳市平方科技股份有限公司 | Train information detection system and method thereof |
| CN114543661A (en) * | 2020-11-27 | 2022-05-27 | 南京拓控信息科技股份有限公司 | Subway vehicle 360-degree image detection system and detection method thereof |
| CN112964180A (en) * | 2021-02-08 | 2021-06-15 | 辽宁鼎汉奇辉电子系统工程有限公司 | Urban rail vehicle collector shoe detection system |
| CN113865490A (en) * | 2021-09-24 | 2021-12-31 | 东莞市诺丽电子科技有限公司 | Non-contact collector shoe carbon sliding plate abrasion detection device and abrasion detection method |
| CN114511519A (en) * | 2022-01-20 | 2022-05-17 | 南京理工大学 | Train bottom bolt loss detection method based on image processing |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117876368A (en) * | 2024-03-11 | 2024-04-12 | 成都唐源电气股份有限公司 | Method and system for detecting abrasion and crack of carbon slide plate of contact rail collector shoe |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2018224073B2 (en) | Broken wheel detection system | |
| US10760898B2 (en) | Optical device and method for inspecting tires | |
| CN107678036B (en) | Vehicle-mounted non-contact type contact net geometric parameter dynamic detection system and method | |
| CN113112501B (en) | Vehicle-mounted track inspection device and method based on deep learning | |
| CN202793389U (en) | On-line routing inspection device for high-speed rail overhead line system | |
| KR101280243B1 (en) | Measuring system for height and stagger and wear of catenary using machine vision | |
| KR101602376B1 (en) | A train faulty monitoring system | |
| CN116519787A (en) | Third rail power receiving boot detection system and method | |
| CN109242035B (en) | Vehicle bottom fault detection device and method | |
| CN107187464A (en) | Track plates detection car, system and method | |
| CN110455214A (en) | A kind of abrasion of pantograph pan condition monitoring system and method | |
| CN113104063A (en) | Comprehensive detection system and method for network rail tunnel | |
| CN206954227U (en) | Track plates detect car and system | |
| CN113298059A (en) | Pantograph foreign matter intrusion detection method, device, computer equipment, system and storage medium | |
| CN111561967A (en) | Real-time online detection method and system for pantograph-catenary operation state | |
| CN205890903U (en) | Rail surface defect non -contact detection system | |
| ES2394902A1 (en) | System and method for measuring the thickness of collector shoes of a pantograph | |
| CN105564460A (en) | Accidental-pantograph-falling identifying and detecting method and system | |
| CN116519703A (en) | System and method for detecting carbon slide plate image of collector shoe based on line scanning 3D image | |
| CN111203389A (en) | Visual detection device and detection method | |
| CN116934680A (en) | Method and equipment for detecting track surface block drop of turnout rail piece | |
| CN112285111A (en) | Pantograph front carbon sliding plate defect detection method, device, system and medium | |
| CN213903347U (en) | Paster apparent on-line measuring equipment | |
| CN213121640U (en) | Detection apparatus for be used for track fastener not hard up | |
| CN203259116U (en) | Crack detecting device for train track |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230801 |
|
| RJ01 | Rejection of invention patent application after publication |