CN212628183U - Intelligent fault image acquisition and detection device for key parts of railway wagon - Google Patents
Intelligent fault image acquisition and detection device for key parts of railway wagon Download PDFInfo
- Publication number
- CN212628183U CN212628183U CN202021257467.1U CN202021257467U CN212628183U CN 212628183 U CN212628183 U CN 212628183U CN 202021257467 U CN202021257467 U CN 202021257467U CN 212628183 U CN212628183 U CN 212628183U
- Authority
- CN
- China
- Prior art keywords
- unit
- imaging unit
- image
- speed
- snapshot
- 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
Images
Landscapes
- Length Measuring Devices By Optical Means (AREA)
Abstract
The utility model relates to a railway freight car key part trouble image intelligent acquisition and detection device belongs to the automatic detection technology field of railway freight car. The utility model comprises a rail edge unit, an indoor unit and a train inspection center; the high-speed three-dimensional imaging unit is newly added at the rail edge unit, a plurality of positioning snapshot magnetic steels are arranged on the inner side of the rail along the direction of the coming vehicle, and when the wheels pass through the positioning snapshot magnetic steels, the positioning snapshot magnetic steels generate pulse signals to directly trigger the area array snapshot imaging unit to take a picture. The utility model discloses a multiple imaging equipment acquires the train image, and the three-dimensional information of train is gathered to the three-dimensional imaging unit that adds can compensate not enough that 2D image detected, directly triggers the camera through hardware design and shoots, improves the degree of accuracy of gathering the part image. The utility model discloses a to the higher diagnosis rate of accuracy of freight train part fault detection and lower misstatement rate.
Description
Technical Field
The utility model belongs to the technical field of the automatic detection of railway freight car, concretely relates to railway freight car key parts trouble image intelligent acquisition and detection device.
Background
A freight train fault rail edge image detection system (TFDS) is important guarantee equipment for the running safety of railway freight trains in China and is one of 5T systems of railway vehicles. According to the system, a set of TFDS device is installed beside a railway track, so that image data and vehicle information of railway wagon vehicles passing through equipment can be acquired in real time, the images are pushed to a railway wagon train inspection center through background data processing, and faults are detected in a manual image looking mode.
Although many faults are found in the manual detection mode, the following problems also exist: 1) the working strength is high, and the car inspection efficiency is low; 2) the phenomena of wrong detection and missed detection faults occur frequently under the influence of personnel quality, personal ability and the like, and the operation quality cannot be ensured; 3) a large amount of manual examination personnel need to be cultured, and the personnel cost is high.
At present, automatic image identification is also applied to TFDS image fault detection, for example, chinese patent application publication No. 102346844a discloses a device and method for identifying a truck center plate bolt loss fault in month 2 of 2012; chinese patent application publication No. 103034850a discloses an automatic TFDS key loss fault identification method in 2013, month 4. Therefore, integrating the image automatic recognition technology in the TFDS is an important application direction.
Disclosure of Invention
The utility model aims at providing a railway freight car key component trouble image intelligent acquisition and detection device for automatic acquisition railway freight car part image discerns railway freight car key component trouble.
The utility model discloses a railway freight car key part fault image intellectual detection system gathers and the device, examine the center including rail limit unit, indoor unit and row. The rail side unit comprises an area array snapshot imaging unit, a high-speed three-dimensional imaging unit, a high-speed linear array imaging unit, a first wheel sensor, a second wheel sensor and an AEI outdoor antenna. The indoor unit comprises a first image acquisition processing unit, a second image acquisition processing unit, a third image acquisition processing unit, an image storage unit, a vehicle information acquisition unit, a signal control unit, an AEI indoor unit and an image automatic identification unit.
The wheel sensors are arranged on the inner side of the rail, the first wheel sensor comprises starting magnetic steel, axle counting vehicle and speed measuring magnetic steel, and the second wheel sensor is positioning snapshot magnetic steel; wherein, AEI represents the automatic train number recognition device.
The high-speed linear array imaging unit and the high-speed three-dimensional imaging unit are arranged on two sides of the rail and below the rail, and the area array snapshot imaging unit is arranged on two sides of the rail. The high-speed linear array imaging unit is provided with a hardware trigger interface and a network port, the input end of the trigger interface is connected with the signal output end of the signal control unit, and the network port is connected with the network port of the first image acquisition processing unit. The high-speed three-dimensional imaging unit is provided with a hardware trigger interface and a network port, the input end of the trigger interface is connected with the signal output end of the signal control unit, and the network port is connected with the network port of the second image acquisition and processing unit. The area array snapshot imaging unit is provided with a hardware trigger interface and a net port, the input end of the trigger interface is connected with the positioning snapshot magnetic steel, and the net port is connected with the third image acquisition processing unit.
The positioning snapshot magnetic steel is distributed on the inner side of the rail along the direction of the coming vehicle, and when the wheels pass through the positioning snapshot magnetic steel, the positioning snapshot magnetic steel generates pulse signals to directly trigger the area array snapshot imaging unit to take a picture.
The signal control unit is connected with the signal output ends of the starting magnetic steel and the axle counting vehicle and speed measuring magnetic steel, connected with the signal output end of the AEI indoor unit, and connected with the signal input and output ends of the vehicle information acquisition unit.
The vehicle information acquisition unit is also connected with the three image acquisition processing units through a network.
The image storage unit is connected with the vehicle information acquisition unit and the first image acquisition processing unit through a network.
The image automatic identification unit is connected with the second image acquisition processing unit, the third image acquisition processing unit and the image storage unit through a network.
Compared with the prior art, the utility model, have following advantage:
(1) the utility model adopts a plurality of imaging devices to acquire the train image, the added three-dimensional imaging unit acquires the three-dimensional information of the train, the deficiency of 2D image detection can be compensated, and the accuracy of fault detection of truck parts is improved;
(2) the utility model is provided with the positioning snapshot magnetic steel, directly triggers the camera to shoot through hardware design, neglects the influence of image shifting caused by the change of the running speed of the vehicle, can accurately position and shoot the position pictures of the rolling bearing end bolt, the locking plate, the pillow spring and the like, can reduce the positioning process in the identification process, and improves the identification efficiency;
(3) proved by experiments, the utility model discloses the device has higher failure diagnosis rate of accuracy and lower misstatement rate.
Drawings
FIG. 1 is a schematic view of the overall connection structure of the device of the present invention;
fig. 2 is a schematic diagram of the installation of the rail edge unit part device of the present invention.
In the figure:
11-a high-speed linear array imaging unit; 12-a high-speed three-dimensional imaging unit; 13-area array snapshot imaging unit; 14-a first wheel sensor; 15-a second wheel sensor; 16-AEI outdoor antenna; 21-a first image acquisition processing unit; 22-a second image acquisition processing unit; 23-a third image acquisition processing unit; 24-a signal control unit; 25-a vehicle information acquisition unit; 26-an image storage unit; 27-AEI indoor unit; 28-an image automatic identification unit; 29-a switch; 31-an alarm terminal; 141-starting magnetic steel; 142-axle counting vehicle and speed measuring magnetic steel; 151-positioning and snapping magnetic steel.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples.
As shown in FIG. 1, the utility model provides a pair of railway freight car key component trouble image intelligent acquisition and detection device includes the triplex, is respectively rail limit unit, indoor unit and row's center of examining. Wherein the rail side unit and the indoor unit are installed at a detection station, and the detection station is generally positioned at the throat of the rail side 10km-20km before the train station of the truck is reached.
The rail side unit comprises a high-speed linear array imaging unit 11, a high-speed three-dimensional imaging unit 12, an area array snapshot imaging unit 13, a first wheel sensor 14, a second wheel sensor 15 and an outdoor antenna 16 of an automatic train number identification device (AEI).
The indoor unit includes a first image capture processing unit 21, a second image capture processing unit 22, a third image capture processing unit 23, a signal control unit 24, a vehicle information capture unit 25, an image storage unit 26, an AEI indoor unit 27, and an automatic image recognition unit 28. The indoor unit is installed in a rail-side machine room within 100m from the rail-side unit. The switch 29 provides a network signal forwarding service to the units of the indoor unit.
The train inspection center includes an alarm terminal 31.
The wheel sensors 14, 15, also called magnet steel, are installed inside the railway rails, as shown in fig. 2, and are divided into startup magnet steel, axle counting vehicle and speed measuring magnet steel, and positioning snapshot magnet steel, as shown in fig. 2. The first wheel sensor 14 and the second wheel sensor 15 in fig. 1 are only one illustration, wherein the second wheel sensor 15 is a positioning snapshot magnetic steel 151, and the first wheel sensor 14 includes a start magnetic steel 141 and an axle counting vehicle and speed measurement magnetic steel 142.
Adopt linear array imaging element or area array imaging element to gather train position image among the current TFDS, the utility model discloses in increased three-dimensional imaging's collection for the compensation passes through the not enough of 2D image detection. As shown in figure 1 and figure 2, the utility model discloses a multiple imaging unit obtains the image of train position, and high-speed linear array imaging unit 11 arranges in rail both sides and rail below together with high-speed three-dimensional imaging unit 12, and area battle array snapshot imaging unit 13 arranges in the both sides of rail. The three imaging units are respectively connected with an image acquisition and processing unit.
And the high-speed linear array imaging unit 11 consists of a linear array camera and a laser compensation light source and is used for imaging the running part of the running truck. The embodiment of the utility model provides an in, the laser compensation light source luminous wavelength of high-speed linear array imaging unit 11 is 808nm, installs 808nm band pass filter in the linear array camera lens simultaneously, can not lead to the image to expose excessively because of sunshine interference when the camera is imaged to influence image quality. Generally, the imaging frequency is higher than 50kHz and is high at the gigabit interface, and in this embodiment, the imaging frequency of the line camera is set to 80kHz, so that the line camera is called a high-speed line imaging unit. The high-speed linear array imaging unit 11 has a hardware trigger interface and a network port, the input end of the hardware trigger interface is connected with the signal output end of the signal control unit 24, and the network port is connected with the network port of the first image acquisition processing unit 21. When a truck passes through a detection station, the first image acquisition processing unit 21 informs the high-speed linear array imaging unit 11 to start scanning and photographing through a network, meanwhile, the vehicle information acquisition unit 25 controls the signal control unit 24 to send a trigger pulse signal to the high-speed linear array imaging unit 11, the high-speed linear array imaging unit 11 completes exposure and photographing, and meanwhile, a photographed linear array image is sent to the first image acquisition processing unit 21 through the network.
The high-speed three-dimensional imaging unit 12 is composed of a 3D camera and a laser light source and is used for shooting three-dimensional images of the parts of the running truck. The embodiment of the utility model provides an in, the laser source luminous wavelength of high-speed three-dimensional imaging unit 12 is 915nm, installs 915nm band pass filter in the 3D camera lens simultaneously, has anti sunlight interference function. Meanwhile, the high-speed three-dimensional imaging unit 12 and the high-speed linear array imaging unit 11 are relatively close in position, and in order to prevent optical interference, the wavelengths of laser light sources used by the two imaging units are designed to be different. The highest imaging frequency of the 3D camera is above 40 kHz. The high-speed three-dimensional imaging unit 12 also has a hardware trigger interface and a network port, and the image taking mode is similar to that of the high-speed linear array imaging unit 11. The input end of the trigger interface of the high-speed three-dimensional imaging unit 12 is connected with the signal output end of the signal control unit 24, and the network port is connected with the network port of the second image acquisition and processing unit 22. When the truck passes through the detection station, the second image acquisition processing unit 22 informs the high-speed three-dimensional imaging unit 12 to start photographing through the network, and meanwhile, the vehicle information acquisition unit 25 controls the signal control unit 24 to send a trigger pulse signal to the high-speed three-dimensional imaging unit 12, so that the high-speed three-dimensional imaging unit 12 photographs. The high-speed three-dimensional imaging unit 12 works on the principle that three-dimensional information data of key parts of a truck vehicle in operation is acquired through a triangulation method, and a three-dimensional image is sent to the second image acquisition and processing unit 22 through a network.
The area array snapshot imaging unit 13 is composed of an area array camera and an LED compensation light source, and is used for snapshot of images of truck wheels and nearby key parts in motion. In the embodiment, the light emitting wavelength of the LED compensation light source is 610nm, and meanwhile, a 610nm band-pass filter is installed in the lens of the area-array camera, so that the function of sunlight interference resistance is achieved. The area array snapshot imaging unit 13 is provided with a hardware trigger interface and a network port, the input end of the hardware trigger interface is connected with positioning snapshot magnetic steel, namely a second wheel sensor 15 in fig. 1, and the network port is connected with a third image acquisition processing unit 23. When a truck passes through a detection station, the third image acquisition and processing unit 23 informs the area array snapshot imaging unit 13 to start a shooting function through a network, when wheels pass through the upper part of the positioning snapshot magnetic steel, a pulse signal is generated to trigger a camera to shoot, the time delay can be reduced by the direct triggering mode of the hardware, key components near the wheels are accurately snapshot, such as a shaft end bolt, a locking plate, a bearing saddle, a sleeper spring and the like, and meanwhile, shot images are sent to the third image acquisition and processing unit 23 through the network.
The three image acquisition processing units 21, 22, and 23 are respectively connected to an imaging unit through a network cable, and are configured to configure parameters of the imaging unit, acquire an image of the imaging unit, process the image, and send processed image data to the image storage unit 26 and the image automatic identification unit 28 through a network. When a train passes through the detection station, the three image acquisition and processing units 21, 22 and 23 acquire images shot by the imaging unit, perform image transformation (rotation and mirror image), image enhancement, image compression, three-dimensional data space transformation and other processing on the images, meanwhile, perform distribution processing on different types of images, respectively transmit the compressed linear array images to the image storage unit 26 and the image automatic identification unit 28, and transmit the processed three-dimensional images and area array images to the image automatic identification unit 28. The hardware of image acquisition processing unit 21, 22, 23 and the realization of software function all can be directly realized through prior art, the utility model discloses no longer detailed description, if the utility model discloses an integrated circuit board of KTE04-IPC-CJ model comes as image acquisition processing unit.
The start-up magnet steel 141 and the axle counting vehicle and the speed measuring magnet steel 142 have been used in the prior art at present, the utility model discloses directly adopt prior art to realize. The utility model discloses a start magnet steel 141 and axle counting vehicle and speed measuring magnet steel 142's signal output part inserts at signal control unit 24, produces analog signal when the vehicle process to handle signal real-time transmission to signal control unit 24. The utility model discloses newly set up location snapshot magnet steel 151, the signal output part of location snapshot magnet steel 151 receives the signal input part of area array snapshot imaging unit 13 for trigger camera shoots. Start magnet steel 141 also is called 1, No. 2 magnet steel, appears in pairs, and 1, No. 2 magnet steel installation distance is 250mm 10mm, installs 80 meters positions before the arrival direction of distance detecting station, triggers when the train passes through start magnet steel 141 the utility model discloses the device gets into the operating condition that connects the car by standby state. The axle counting vehicles and speed measuring magnetic steels 142 are also called as No. 3 and No. 4 magnetic steels, and appear in pairs, the installation distance of the No. 3 and No. 4 magnetic steels is 250mm +/-10 mm, the magnetic steels are installed 4-5 meters in front of the direction of the coming vehicle at the detection station, and the magnetic steels are used for measuring the speed, counting the axles and judging the type of the train, for example, the train is normally picked up when a truck passes through the detection station, and the picking up is interrupted when a passenger car or a motor car passes through the detection station. When the wheel passes through the axle counting vehicle and the speed measuring magnetic steel 142, the magnetic steel 142 generates a pulse signal to the vehicle information acquisition unit 25. The location is taken a candid photograph magnet steel 151 and is distributed a plurality ofly along coming the car direction in the rail inboard, and the signal output part of location is taken a candid photograph magnet steel 151 directly links area array and takes a candid photograph imaging unit 13, when the wheel was taken a candid photograph magnet steel 151 through the location, generates pulse signal and directly triggers area array and take a candid photograph imaging unit 13 and shoot, reaches the purpose of accurate candid photograph.
An automatic train number identification (AEI) device is divided into an outdoor antenna 16 and an indoor unit 27. The outdoor antenna 16 and the indoor unit 27 are connected by a coaxial cable. When the radio frequency tag card at the bottom of the truck enters the working area of the outdoor antenna 16, the outdoor antenna 16 receives the carrier signal sent by the electronic tag, and transmits the carrier signal to the indoor unit 27 through the coaxial cable, and the indoor unit 27 demodulates and decodes the received carrier signal and sends the decoded electronic tag information to the signal control unit 24 through a serial port communication mode. The electronic tag information includes information such as station segment attribution, vehicle type, vehicle number and the like. The utility model discloses used AEI directly adopts existing equipment, like XCJP-3A1 series railway train number identification system.
The signal control unit 24 is connected with the signal output ends of the starting magnetic steel 141 and the axle counting vehicle and speed measuring magnetic steel 142, connected with the signal output end of the AEI indoor unit 27, and further connected with the signal input and output ends of the vehicle information acquisition unit 25. The signal control unit 24 receives the pulse signals of the wheel sensor 14, performs filtering and shaping processing, sends the shaped signals to the vehicle information acquisition unit 25 in real time, receives the output signals of the vehicle information acquisition unit 25, performs signal frequency division processing, sends the signals to the high-speed linear array imaging unit 11 and the high-speed three-dimensional imaging unit 12, and triggers the imaging unit to take a picture by a camera. The signal control unit 24 also receives the electronic tag information of the train collected from the AEI indoor unit 27, and forwards it to the vehicle information collection unit 24.
The vehicle information acquisition unit 25 is connected with the signal control unit 24 through a network, and receives the sensor pulse signal and the electronic tag information of the train. The vehicle information acquisition unit 25 calculates the current real-time speed of the wheels of the truck according to the sensor pulse signals, further calculates the distance between axles, obtains the axle distance information of the truck in a template matching mode, and simultaneously fuses the read vehicle electronic tag information to form complete vehicle information which is sent to the image storage unit 26. The vehicle information acquisition unit 25 is also connected to the three image acquisition processing units 21, 22, 23 via a network, and notifies the camera when to acquire an image or when to stop acquiring an image. The vehicle information acquisition unit 25 also updates the scanning frequency of the camera in real time according to the obtained current wheel speed, and outputs the scanning frequency to the high-speed linear array imaging unit 11 and the high-speed three-dimensional imaging unit 12 through the signal control unit 24.
The vehicle information acquisition unit 25 calculates the real-time speed of the truck wheels according to the sensor pulse signals, and further obtains the truck wheel base information. For example, when the train wheel passes through No. 3 and No. 4 magnetic steels, the obtained passing time is t1、t2And the distance between No. 3 and No. 4 magnetic steels is s, the speed of the current train wheel can be calculated
Simultaneously recording the time t when each shaft of the train passes through No. 4 magnetic steelnAnd then according to the formula that the distance is equal to the speed multiplied by the time, the wheelbase of each bogie of the train and the wheelbase between two front and rear bogies of each train can be calculated, and the wheelbase information of each train can be obtained by matching the wheelbase information with the standard wheelbase template, so that whether the train is a passenger car or a truck can be further judged, and meanwhile, the acquired images can be subjected to matching cutting and the like according to the information.
The utility model discloses in, the hardware of signal control unit 24 and vehicle information acquisition unit 25 can directly adopt the hardware equipment among the current TFDS, relate to the function of high-speed three-dimensional imaging unit 12, set up according to the mode with high-speed linear array imaging unit 11, the calculation that involves also has now realized, the utility model discloses can in the hardware equipment with corresponding function integration. If the utility model discloses a signal control unit is come as to the integrated circuit board of KTE03-XHCLX model, adopts the integrated circuit board of KT-IPC-KZ model as vehicle information acquisition unit.
The image storage unit 26 is connected with the vehicle information acquisition unit 25 and the first image acquisition processing unit 21 through a network, and is used for receiving the vehicle information and the train image data, associating the vehicle information and the image data, and storing the vehicle information and the image data locally. Meanwhile, the image storage unit 26 receives the alarm identification result of the image automatic identification unit 28, fuses and stores the identification result and data such as vehicle information, and pushes the identified alarm result to the train inspection center.
The automatic image identification unit 28 is connected with the second image acquisition processing unit 22, the third image acquisition processing unit 23 and the image storage unit 26 through a network, reads vehicle information and a shot high-definition image from the image storage unit, classifies truck vehicle image data according to the vehicle information, locates and identifies abnormalities in the image, and sends an identification result to the image storage unit 26. The image automatic identification unit 28 integrates the application programs of image automatic identification in the TFDS image fault detection in the prior art, such as fault identification of missing of a truck center bolt, fault automatic identification of missing of a TFDS stop key, and the like.
The image automatic recognition unit 28 also incorporates a technique for performing a fault supplementary detection using the acquired 3D image. For 2D images, it essentially records information of the intensity of the reflected light from the object surface; and the 3D image is descriptive of depth information. Thus, for water spots, dirt, etc. on the train surface, noise and interference may appear on the 2D image. If such an image is subjected to feature extraction, the interferences such as stains are also extracted as feature vectors to be included in the data set, which inevitably affects subsequent positioning and identification. The automatic image identification unit 28 extracts the gray features and gradient features of the 3D image acquired by the truck under the condition of no fault, stores the gray features and gradient features as standards, compares the gray features and gradient features of the 3D image acquired in real time with the standards, and judges whether the component has a fault. For 3D images, extracting gray features, wherein the gray features essentially represent the depth distribution information of an object relative to a camera lens; and extracting gradient characteristics, wherein the essential characteristics are information of height difference and roughness of the surface of the object. For equipment fixed on the edge of the rail, because the distance between the rails and all parts of the train are standard parts, under the condition of no fault, the depth information of the surfaces of the parts is very stable and cannot be influenced by factors such as surface stains, water stains, environmental illumination and the like. When each part has a fault, the change of the depth information is very obvious, so that the extraction of the features on the 3D image for detecting the fault discrimination is better than that of the 2D image. The automatic image recognition unit 28 extracts the gray scale features and the gradient features of the 3D image according to the prior art, and the feature comparison can be implemented by using the prior art.
Similarly, the image automatic recognition unit 28 of the present invention is implemented by a board card of model HPC-7242MB, and the physical structure thereof is described in the prior art and will not be described in detail.
The embodiment of the utility model discloses a freight train that utilizes south Beijing east vehicle section to attach has tested the detection station device of installing at south Beijing east vehicle section, through 5 many months's simulation fault and test result analysis, has accumulated a large amount of trouble samples, along with increasing gradually and a large amount of trouble sample training of trouble sample accumulation, verifies from 16 th time that the starting drive tends to stably, and fault identification misstatement rate reaches below 50% to realize zero and leak the newspaper. In the process of equipment trial, the outdoor camera is influenced by the environment, the quality of the shot image is reduced to some extent, the false alarm rate is increased to a certain extent, and in a controllable range, the quality of the shot image can be improved and the false alarm rate is reduced by regularly maintaining the clean imaging unit.
Claims (3)
1. An intelligent fault image acquisition and detection device for key parts of a railway wagon comprises a rail edge unit, an indoor unit and a train inspection center; the rail side unit comprises an area array snapshot imaging unit, a high-speed linear array imaging unit, a first wheel sensor and an AEI outdoor antenna, wherein the first wheel sensor comprises starting magnetic steel, axle counting vehicles and speed measuring magnetic steel; the indoor unit comprises a first image acquisition processing unit, a second image acquisition processing unit, a third image acquisition processing unit, an image storage unit, a vehicle information acquisition unit, a signal control unit, an AEI indoor unit and an image automatic identification unit; AEI represents a railway train number automatic identification device; the device is characterized in that the rail side unit further comprises a high-speed three-dimensional imaging unit and a second wheel sensor; the first wheel sensor and the second wheel sensor are arranged on the inner side of the rail, and the second wheel sensor is positioning snapshot magnetic steel;
the high-speed linear array imaging unit and the high-speed three-dimensional imaging unit are arranged on two sides of the rail and below the rail together, and the area array snapshot imaging unit is arranged on two sides of the rail; the high-speed linear array imaging unit is provided with a hardware trigger interface and a network port, the input end of the trigger interface of the high-speed linear array imaging unit is connected with the signal output end of the signal control unit, and the network port of the high-speed linear array imaging unit is connected with the network port of the first image acquisition processing unit; the high-speed three-dimensional imaging unit is provided with a hardware trigger interface and a network port, the input end of the trigger interface of the high-speed three-dimensional imaging unit is connected with the signal output end of the signal control unit, and the network port of the high-speed three-dimensional imaging unit is connected with the network port of the second image acquisition processing unit; the area array snapshot imaging unit is provided with a hardware trigger interface and a net port, the input end of the trigger interface of the area array snapshot imaging unit is connected with the positioning snapshot magnetic steel, and the net port of the area array snapshot imaging unit is connected with the third image acquisition processing unit;
a plurality of positioning snapshot magnetic steels are distributed on the inner side of the rail along the direction of the coming vehicle, and when the wheels pass through the positioning snapshot magnetic steels, the positioning snapshot magnetic steels generate pulse signals to directly trigger the area array snapshot imaging unit to take a picture;
the signal control unit is connected with the signal output ends of the starting magnetic steel and the axle counting vehicle and speed measuring magnetic steel, connected with the signal output end of the AEI indoor unit and connected with the signal input end and the signal output end of the vehicle information acquisition unit;
the vehicle information acquisition unit is also connected with the three image acquisition processing units through a network;
the image storage unit is connected with the vehicle information acquisition unit and the first image acquisition processing unit through a network;
the image automatic identification unit is connected with the second image acquisition processing unit, the third image acquisition processing unit and the image storage unit through a network.
2. The device as claimed in claim 1, wherein the high-speed line array imaging unit comprises a line array camera and a laser compensation light source, the light emitting wavelength of the laser compensation light source is set to 808nm, and a 808nm band-pass filter is installed in a lens of the line array camera.
3. The device according to claim 1, wherein the high-speed three-dimensional imaging unit comprises a 3D camera and a laser source, the light emitting wavelength of the laser source is 915nm, and a 915nm band-pass filter is arranged in a lens of the 3D camera.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202021257467.1U CN212628183U (en) | 2020-06-30 | 2020-06-30 | Intelligent fault image acquisition and detection device for key parts of railway wagon |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202021257467.1U CN212628183U (en) | 2020-06-30 | 2020-06-30 | Intelligent fault image acquisition and detection device for key parts of railway wagon |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN212628183U true CN212628183U (en) | 2021-02-26 |
Family
ID=74757033
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202021257467.1U Active CN212628183U (en) | 2020-06-30 | 2020-06-30 | Intelligent fault image acquisition and detection device for key parts of railway wagon |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN212628183U (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113965745A (en) * | 2021-11-18 | 2022-01-21 | 合肥富煌君达高科信息技术有限公司 | System and method for automatic high-speed monitoring of rail turnout |
-
2020
- 2020-06-30 CN CN202021257467.1U patent/CN212628183U/en active Active
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113965745A (en) * | 2021-11-18 | 2022-01-21 | 合肥富煌君达高科信息技术有限公司 | System and method for automatic high-speed monitoring of rail turnout |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111942434A (en) | Intelligent fault image detection device for key parts of railway wagon | |
| US8509969B2 (en) | Automatic identification method and system for train information | |
| CN102759347B (en) | Online in-process quality control device and method for high-speed rail contact networks and composed high-speed rail contact network detection system thereof | |
| CN107687953B (en) | A kind of lorry failure automatic checkout equipment | |
| CN107187464B (en) | Track slab detection vehicle, system and method | |
| CN109242035B (en) | Vehicle bottom fault detection device and method | |
| CN206446603U (en) | A kind of locomotive running part detection means being imaged based on linear array scanning and 3D | |
| CN109489724A (en) | A kind of tunnel safe train operation environment comprehensive detection device and detection method | |
| CN105115605A (en) | Track train infrared detection system and detection method | |
| CN109002045B (en) | A kind of the inspection localization method and inspection positioning system of intelligent inspection robot | |
| CN113947731B (en) | Foreign matter identification method and system based on contact net safety inspection | |
| CN212628183U (en) | Intelligent fault image acquisition and detection device for key parts of railway wagon | |
| CN111289261A (en) | Detection method for in-warehouse bottom car part | |
| CN109238756A (en) | Lorry operation troubles motion image detection equipment and detection method | |
| CN111605578A (en) | Railway track inspection method for carrying 3D equipment by using unmanned aerial vehicle | |
| CN110595804A (en) | Intelligent fault detection system for railway wagon running part | |
| CN108981565A (en) | A kind of municipal rail train pantograph disalignment monitoring device and method | |
| CN107144227A (en) | A kind of municipal rail train pantograph pan on-line thickness testing and method | |
| CN210954335U (en) | Detection device for wagon compartment | |
| KR102004909B1 (en) | Tongue rail inspection system for detecting the close contact | |
| CN113591643A (en) | Underground vehicle station entering and exiting detection system and method based on computer vision | |
| CN207725421U (en) | Vehicle wheel is to dynamic detection system | |
| CN112733709A (en) | Track inspection detection system and method | |
| CN111354190A (en) | Method and device for detecting vehicle by combining RSU and video stream | |
| CN203766824U (en) | On-line rail detecting device of electric locomotive electrified boot |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address |
Address after: 9th floor, No. 61 Zhichun Road, Haidian District, Beijing, 100190 Patentee after: Beijing Aerospace Shenzhou Intelligent Equipment Technology Co.,Ltd. Patentee after: BEIJING AEROSPACE CTROWELL INFORMATION TECHNOLOGY CO.,LTD. Address before: 100080 No. 61, Haidian District, Beijing, Zhichun Road Patentee before: BEIJING CTROWELL INFRARED TECHNOLOGY Co.,Ltd. Patentee before: BEIJING AEROSPACE CTROWELL INFORMATION TECHNOLOGY CO.,LTD. |
|
| CP03 | Change of name, title or address |