CN111957592A - Railway wagon bogie sleeper spring sorting system and sorting method thereof - Google Patents
Railway wagon bogie sleeper spring sorting system and sorting method thereof Download PDFInfo
- Publication number
- CN111957592A CN111957592A CN202010780430.5A CN202010780430A CN111957592A CN 111957592 A CN111957592 A CN 111957592A CN 202010780430 A CN202010780430 A CN 202010780430A CN 111957592 A CN111957592 A CN 111957592A
- Authority
- CN
- China
- Prior art keywords
- spring
- image
- sleeper
- occipital
- image acquisition
- 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.)
- Withdrawn
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/04—Sorting according to size
- B07C5/10—Sorting according to size measured by light-responsive means
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/02—Measures preceding sorting, e.g. arranging articles in a stream orientating
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/04—Sorting according to size
- B07C5/12—Sorting according to size characterised by the application to particular articles, not otherwise provided for
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/36—Sorting apparatus characterised by the means used for distribution
- B07C5/361—Processing or control devices therefor, e.g. escort memory
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/36—Sorting apparatus characterised by the means used for distribution
- B07C5/361—Processing or control devices therefor, e.g. escort memory
- B07C5/362—Separating or distributor mechanisms
Landscapes
- Image Processing (AREA)
Abstract
The invention relates to the technical field of bogie spring sleeper sorting, in particular to a railway wagon bogie spring sleeper sorting system based on machine vision and a sorting method thereof. The device comprises a sleeper spring transferring and grabbing system, an image acquisition system, an image processing system and a control system; the sleeper spring transferring and grabbing system is provided with a mechanical arm; the image acquisition system comprises a frame, a working table, a harness, a camera and an image acquisition card; the sorting method comprises the following steps: firstly, a mechanical arm is used for grabbing a sleeper spring and placing the sleeper spring on a harness; then the image collected by the image system is transmitted to the image processing system by the image collecting card; and the image processing system processes the received image to obtain the size data of the occipital spring, and judges the type of the occipital spring according to the size parameter of the occipital spring. The method overcomes the defects of time consumption and low accuracy of traditional manual sleeper spring sorting operation measurement, and realizes automatic identification of the type of the bogie sleeper spring; the labor intensity is reduced; the invention has the advantages of non-contact, high detection speed, high efficiency, high precision and the like.
Description
Technical Field
The invention relates to the technical field of bogie spring sleeper sorting, in particular to a railway wagon bogie spring sleeper sorting system based on machine vision and a sorting method thereof.
Background
The damping spring and the swing bolster spring are important components of the railway freight car bogie and are collectively called as the bolster spring; the sleeper spring is mainly used for alleviating vibration and impact of a railway wagon in operation, and various types of bogies (such as rotary K2, rotary K3, rotary K6, SW-200, SW-220K and the like) are available in the railway locomotive standard in China. The springs in the same set of bogie systems must be of the same type, as required by the section repair code of railway freight cars. It is therefore necessary to distinguish the types of bogies.
However, the traditional pillow spring sorting operation mode is mainly to distinguish pillow spring model and type through manual measurement, measures the free height of pillow spring through the pillow spring height gauge, adopts the spring diameter gauge to carry out round steel diameter detection, because pillow spring is in large quantity and the kind is different on a railway freight car, traditional operation mode is efficient, intensity of labour is big and the degree of accuracy of sorting is easily disturbed by human factor.
In summary, the traditional sleeper spring sorting operation mode is difficult to meet the current increasing maintenance task amount (sleeper spring maintenance requirement) of the bogie, so that the development of a system for automatically sorting sleeper springs is a practical matter.
Disclosure of Invention
The invention provides a railway wagon bogie sleeper spring sorting system based on machine vision and a sorting method thereof, and aims to solve the problems that the traditional sleeper spring overhauling operation is low in efficiency and high in labor intensity, and sorting quality is easily influenced by human factors.
The main inventive thought of the invention is as follows: the size sorting of the occipital springs is to calculate the size of each object in the image after the obtained image is calculated, and then the size is matched with the known size data of the occipital springs of various types, so that different occipital spring types are distinguished.
In order to achieve the purpose, the invention adopts the following technical scheme: a railway freight car bogie sleeper spring sorting system comprises a sleeper spring transferring and grabbing system, an image acquisition system, an image processing system and a control system; the sleeper spring transferring and grabbing system is provided with a mechanical arm, a sleeper spring gripper is mounted at the tail end of the mechanical arm, and the mechanical arm drives the sleeper spring gripper to complete grabbing and transferring of a sleeper spring under the action of the control system; the image acquisition system comprises a frame, a worktable, a tool for placing the occipital spring, a camera and an image acquisition card, wherein the worktable is arranged in the frame, and the tool for placing the occipital spring is fixed at the center of the upper surface of the worktable; setting a reference object with a known real size on the working table, wherein the reference object is used for obtaining the ratio of the actual size of the calculated outline in the image processing system, and the ratio = object pixel width/object real width; the camera is arranged on the frame and positioned above the harness, and the camera is electrically connected and in signal connection with the control system; the image acquisition card is used as a communication module of the image acquisition system, and the image acquired by the camera is transmitted to the image processing system through the image acquisition card; the image processing system comprises a data analysis and processing module, a database, an algorithm library and a corresponding hardware system, and is responsible for parameter setting of the detection process and processing, analysis and transmission of image data; after a series of basic data analysis and processing, the required detection values are calculated through a detection algorithm provided by an algorithm library, and the detection values are the free height value, the inner diameter value and the outer diameter value of the occipital spring.
The sleeper spring sorting method based on the railway wagon bogie sleeper spring sorting system specifically comprises the following steps:
step (1): after the sleeper spring to be detected is conveyed to a preset position through a conveying line, a sleeper spring transferring and grabbing system is used for grabbing the sleeper spring and placing the grabbed sleeper spring on an apparatus;
step (2): after the sleeper spring is placed on the harness, the image acquisition system starts image acquisition work, and acquired images are transmitted to the image processing system through the image acquisition card;
and (3): the image processing system carries out a series of processing on the received image to obtain corresponding size data of the tested occipital spring, and the image processing system compares the measured size data with size parameters of the occipital spring preset in the system to finish the discrimination of the occipital spring model;
and (4): after the type of the occipital spring is judged, the image processing system transmits the judgment result to the control system, and the occipital spring is taken away by the occipital spring transferring and grabbing system under the action of the control system and is placed at the designated position corresponding to the type of the occipital spring.
As can be seen from the above, the present invention has the following advantageous effects compared to the prior art: by arranging the image acquisition system and the image processing system, the defects of time consumption and low accuracy of traditional manual bolster spring sorting operation are overcome, and the automatic identification of the type of the bogie bolster spring is realized; the sleeper spring transferring and grabbing system realizes automatic grabbing and transferring of sleeper springs, and reduces labor intensity; the working table is provided with a tool for positioning the sleeper spring, and the position posture of the sleeper spring is limited to a certain extent, so that the measurement is more accurate; the invention has the advantages of non-contact property, high detection speed, high efficiency and high precision.
In order to further improve the technical effect of the invention, the technical scheme can be improved as follows.
Furthermore, the frame is provided with a vertical frame and a horizontal frame, and the lower end of the vertical frame is fixedly connected to the upper side of the horizontal frame; a moving axis Y arranged along the vertical direction and a moving axis X arranged along the horizontal direction are arranged on the vertical frame; the X axis is fixed on the slide block of the Y axis; a camera is arranged on the sliding block of the X axis, and a lens of the camera is arranged downwards; a moving shaft Z is arranged in the horizontal frame, the Z shaft is respectively vertical to the X shaft and the Y shaft, and a sliding block of the Z shaft is fixedly connected with the working table; the driving of the X axis, the Y axis and the Z axis is electrically connected with a control system. The image acquisition system has the function of adjusting the relative position of the camera and the occipital spring to be measured, the control system can adjust the positions of the camera on the X axis and the Y axis according to the requirement, and the position of the working platform on the Z axis can be adjusted to further aim at the target detection body, so that the measurement is more flexible.
Furthermore, the working table surface and the tool for placing the pillow spring in the image acquisition system are both made of transparent acrylic plates.
Further, a light source and a light source controller are arranged below the working table, and the light source adopts an LED lamp ring; the light source controller is electrically connected with the control system and is used for controlling the on-off and brightness adjustment of the light source.
Further, the GMT200-H high frame rate 200 ten thousand pixel industrial camera is selected as the camera in the image acquisition system, and the optical lens used by the camera is selected from SA1620M-10 MP.
The working process of the image acquisition in the step (2) comprises the following steps: step (2.1): in the image acquisition system, a working platform and a harness are both made of transparent acrylic materials, and a normally open LED light source is arranged below the working platform; step (2.2): the relative position of the camera and the occipital spring to be measured can be adjusted according to the requirement, and the adjustment of the relative position is realized by controlling the driving motors of the X axis, the Y axis and the Z axis by the control system; step (2.3): after the relative position of the camera and the occipital spring to be detected is adjusted, the control system controls the camera to complete image acquisition; step (2.4): and after the image acquisition is finished, transmitting the acquired image to an image processing system through an image acquisition card.
The working process of the image processing in the step (3) comprises the following steps: step (3.1): loading an image to be processed and performing preprocessing operation, specifically comprising: graying an image, Gaussian filtering, edge detection, expansion and corrosion, and searching for a contour line; step (3.2): traversing and screening the obtained object contours, traversing each object contour, and outputting a corresponding object boundary contour; step (3.3): calculating the coordinates of the central point of each contour and drawing the result; step (3.4): calculating Euclidean distances between the central point sets according to a ratio value obtained by a preset reference object, and dividing the Euclidean distances by the pixel value of the object to obtain the actual size of the object; step (3.5): and (4) matching the model of the occipital spring according to the size data obtained in the step (3.4).
The specific process of the pretreatment operation in the step (3.1) is as follows: step (3.1.1): loading an image, wherein the image is completed by an image acquisition system and is transmitted to an image processing system by an image acquisition card; step (3.1.2): graying, namely performing gray level conversion by adopting a weighted average algorithm, and respectively giving different weights according to the contribution of R, G, B in the image to gray level; the obtained original image is a color image, the color image is formed by R, G, B (red, green and blue) 3 channels, and only one channel is formed after gray level conversion, so that the detection speed can be improved by changing processing 3 channels into processing 1 channel in the detection process; step (3.1.3): gaussian filtering, wherein a lot of noises are introduced into an image in the imaging, transmission and storage processes, and the detail information of the image is kept as far as possible while the image denoising aims at removing the noises; step (3.1.4): edge detection, wherein the purpose of the edge detection is to find a set formed by pixel points with severe brightness change in an image, and the displayed set is the outline of a target body; step (3.1.5): dilation-erosion to eliminate any gaps between edges in the edge map; step (3.1.6): and (3) searching contours, wherein the result obtained in the step (3.1.4) of edge detection is in a contour line form constructed by a plurality of contours, and in the step, a contour line corresponding to the size of the reaction object in the edge map is searched.
The step (3.2) of profile traversal screening comprises the following specific steps: step (3.2.1): arranging the contour regions obtained in the step (3.1) from left to right, and facilitating the extraction of a reference datum; step (3.2.2): knowing the reference datum position and the pixel size, initializing the ratio; step (3.2.3): checking and checking the size of each contour region value, and circulating each individual contour value in the process; step (3.2.4): judging the size of the high-speed line area, if the high-speed line area is not large enough, excluding the area, and judging the area to be the noise left in the edge detection process; step (3.2.5): if the contour line area is large enough, calculating a rotating boundary frame of the image, and then arranging coordinates of the rotating boundary frame in the upper left corner, the upper right corner, the lower right corner and the lower left corner in sequence; step (3.2.6): drawing the outline of the object by using colored lines, and then drawing colored circles at the vertexes of the rectangle of the bounding box; now that the bounding box is available, a series of midpoints is calculated from the existing bounding box.
Drawings
Fig. 1 is a schematic diagram of signal connection relationship of a occipital spring sorting system according to an embodiment of the present invention.
Fig. 2 is a schematic structural diagram of an image acquisition system in the occipital spring sorting system according to the embodiment of the present invention.
Fig. 3 is a basic flowchart of a occipital spring sorting method according to an embodiment of the present invention.
Fig. 4 is a flowchart of an image processing method in the occipital spring sorting method.
In the figure: a frame 1; 1-1 of a vertical frame; a horizontal frame 1-2; an X axis 2; a Y axis 3; a Z axis 4; a work table top 5; a harness 6; a camera 7.
Detailed Description
The invention is further explained below with reference to the drawings.
The railway wagon bogie sleeper spring sorting system provided by the embodiment of the invention comprises a sleeper spring transferring and grabbing system, an image acquisition system, an image processing system and a control system. As shown in fig. 1, in the embodiment of the present invention, the signal direction and the connection relation are used, and the transportation and grasping system of the occipital spring accomplishes the grasping and transportation of the occipital spring under the action of the control system; under the control of the control system, the image processing system finishes image acquisition, the acquired image is transmitted to the image processing system by the image acquisition system, the image processing system carries out a series of processing and calculation on the image and finishes the discrimination of the model of the sleeper spring to be detected, the discrimination structure is transmitted to the control system, and the control system controls the transferring and grabbing system to take away the detected sleeper spring and place the corresponding designated position.
The sleeper spring transferring and grabbing system is provided with a mechanical arm, a sleeper spring gripper is mounted at the tail end of the mechanical arm, and the mechanical arm drives the sleeper spring gripper to complete grabbing and transferring of the sleeper spring under the action of the control system. The mechanical arm realizes automatic taking and placing of the sleeper spring under the action of the control system, greatly reduces the labor intensity of operating personnel, and saves the labor cost.
As shown in fig. 2, the image acquisition system comprises a frame 1, a workbench surface 5, a harness 6 for placing a occipital spring, a camera 7 and an image acquisition card, wherein the workbench surface 5 is installed in the frame 1, the harness 6 for placing the occipital spring is fixed at the center of the upper surface of the workbench surface 5, and the harness 6 is used for ensuring that the occipital spring is placed reasonably, is fixed and cannot be skewed, so that the imaging quality and the size identification precision of the industrial camera 7 are ensured.
A reference object with a known real size is arranged on the working table 5, the reference object is used for obtaining the ratio of the real size of the calculated outline in the image processing system, the ratio = object pixel width/object real width, when in size measurement, the reference object is used as a reference, and the real size of the tested occipital spring is obtained through the measured pixel value and the ratio.
The camera 7 is arranged on the frame 1 and positioned above the harness 6, and the camera 7 is electrically and signal-connected with the control system; the image acquisition card is used as a communication module of the image acquisition system, and the image acquired by the camera 7 is transmitted to the image processing system through the image acquisition card. The image processing system obtains the geometric dimension of the occipital spring to be measured after a series of calculation processing. When the occipital spring type detection device is used for measurement, the occipital spring type can be automatically distinguished only by placing the occipital spring in a specified region to be detected.
The image processing system comprises a data analysis and processing module, a database, an algorithm library and a corresponding hardware system, and is responsible for parameter setting of the detection process and processing, analysis and transmission of image data.
After a series of basic data analysis and processing, the required detection values are calculated through a detection algorithm provided by an algorithm library, and the detection values are the free height value, the inner diameter value and the outer diameter value of the occipital spring.
A method for sorting the sleeper springs based on the railway wagon bogie sleeper spring sorting system is described below, and referring to fig. 3, the method specifically includes the following steps:
step (1): after the sleeper spring to be detected is conveyed to a preset position through a conveying line, the sleeper spring is grabbed by a sleeper spring transferring and grabbing system, and the grabbed sleeper spring is placed on the device 6.
Step (2): after the occipital spring is placed on the harness 6, the image acquisition system starts image acquisition work, and acquired images are transmitted to the image processing system through the image acquisition card.
And (3): the image processing system carries out a series of processing on the received image to obtain corresponding size data of the tested occipital spring, and the image processing system compares the measured size data with preset size parameters of the occipital spring in the system (the image processing system) to finish the discrimination of the occipital spring type.
And (4): after the type of the occipital spring is judged, the image processing system transmits the judgment result to the control system, and the occipital spring is taken away by the occipital spring transferring and grabbing system under the action of the control system and is placed at the designated position corresponding to the type of the occipital spring.
In order to achieve better results in use, the following preferred embodiments may be selected for carrying out the present invention.
As a preferred scheme, the frame 1 is provided with a vertical frame 1-1 and a horizontal frame 1-2, and the lower end of the vertical frame 1-1 is fixedly connected to the upper side of the horizontal frame 1-2; a moving axis Y arranged along the vertical direction and a moving axis X arranged along the horizontal direction are arranged on the vertical frame 1-1; the X shaft 2 is fixed on a slide block of the Y shaft 3; a camera 7 is arranged on the sliding block of the X-axis 2, and a lens of the camera 7 is arranged downwards; a moving axis Z is arranged in the horizontal frame 1-2, a Z axis 4 is respectively vertical to the X axis 2 and the Y axis 3, and a sliding block of the Z axis 4 is fixedly connected with a working table surface 5; the driving of the X-axis 2, the Y-axis 3 and the Z-axis 4 is electrically connected with a control system.
Through setting up X axle 2, Y axle 3 and Z axle 4 for the relative position between camera 7 and the occipital spring that awaits measuring can the nimble adjustment of multiposition, provides convenience for the better image that contains more effective characteristics of gathering.
Preferably, the work table 5 and the tool 6 for placing the occipital spring in the image acquisition system are both made of transparent acrylic plates.
The harness 6 and the working table 5 are made of transparent acrylic plates (or other transparent materials such as toughened glass) and are beneficial to arranging a light source at the bottom, so that the quality of the collected image is improved.
As a preferred scheme, a light source and a light source controller are arranged below the working table surface 5, and the light source adopts an LED lamp ring; the light source controller is electrically connected with the control system and is used for controlling the on-off and brightness adjustment of the light source.
Preferably, the camera 7 in the image acquisition system is a GMT200-H industrial camera 7 with high frame rate of 200 ten thousand pixels, and an optical lens used by the camera 7 is SA1620M-10 MP.
The high frame rate can effectively ensure that the industrial camera 7 can acquire images with high pixels and less environmental noise on the working table 5. The optical lens adopts SA1620M-10MP to realize better focusing and imaging.
The detection method of the occipital spring is also optimized.
Optimizing the step (2): the working process of the image acquisition in the step (2) comprises the following steps.
Step (2.1): in the image acquisition system, the working platform and the harness 6 are both made of transparent acrylic materials, and a normally open LED light source is arranged below the working platform.
Step (2.2): the relative position of the camera 7 and the occipital spring to be measured can be adjusted as required, and the adjustment of the relative position is realized by controlling the driving motors of the X-axis 2, the Y-axis 3 and the Z-axis 4 by the control system.
Step (2.3): after the relative position of the camera 7 and the occipital spring to be measured is adjusted, the control system controls the camera 7 to complete image acquisition.
Step (2.4): and after the image acquisition is finished, transmitting the acquired image to an image processing system through an image acquisition card.
Optimizing the step (3): the working process of the image processing in the step (3) comprises the following steps.
Step (3.1): loading an image to be processed and performing preprocessing operation, specifically comprising: image graying, Gaussian filtering, edge detection, expansion and corrosion, and contour line searching.
Step (3.2): and traversing and screening the obtained object contours, traversing each object contour, and outputting a corresponding object boundary contour.
Step (3.3): and calculating the coordinates of the center point of each contour, and drawing the result.
Step (3.4): and calculating Euclidean distances between the central point sets according to a ratio value obtained by a preset reference object, and dividing the Euclidean distances by the pixel value of the object to obtain the actual size of the object.
Step (3.5): and (4) matching the model of the occipital spring according to the size data obtained in the step (3.4).
The specific process of the pretreatment operation in the step (3.1) is as follows:
step (3.1.1): and loading an image, wherein the image is completed by an image acquisition system and is transmitted to an image processing system by an image acquisition card.
Step (3.1.2): graying, namely performing gray level conversion by adopting a weighted average algorithm, and respectively giving different weights according to the contribution of R, G, B to gray level in an image; the obtained original image is a color image, the color image is formed by R, G, B (red, green and blue) 3 channels, and only one channel is formed after gray level conversion, so that the detection speed can be improved by changing processing 3 channels into processing 1 channel in the detection process.
Step (3.1.3): gaussian filtering, wherein a lot of noises are introduced into an image in the processes of imaging, transmission and storage, and image denoising aims to remove the noises and simultaneously retain detailed information of the image as much as possible.
Step (3.1.4): and edge detection, wherein the purpose of the edge detection is to find a set formed by pixel points with severe brightness change in the image, and the displayed set is the outline of the target body.
Step (3.1.5): swelling corrosion to eliminate any gaps between edges in the edge map.
Step (3.1.6): and (3) searching contours, wherein the result obtained in the step (3.1.4) of edge detection is in a contour line form constructed by a plurality of contours, and in the step, a contour line corresponding to the size of the reaction object in the edge map is searched.
The step (3.2) of profile traversal screening comprises the following specific steps:
step (3.2.1): and (4) arranging the contour regions obtained in the step (3.1) from left to right, and facilitating the extraction of a reference datum.
Step (3.2.2): knowing the reference base position and the pixel size, the ratio is initialized.
Step (3.2.3): check checking is performed on the size of each contour region value, and each individual contour value is cycled through in the process.
Step (3.2.4): and judging the size of the high-line area, if the high-line area is not large enough, excluding the area, and judging the area to be the noise left in the edge detection process.
Step (3.2.5): if the contour region is large enough, a rotated bounding box of the image is computed, and then we arrange the coordinates of the rotated bounding box in order at the top left, top right, bottom right, and bottom left.
Step (3.2.6): drawing the outline of the object by using colored lines, and then drawing colored circles at the vertexes of the rectangle of the bounding box; now that the bounding box is available, a series of midpoints is calculated from the existing bounding box.
Based on the content, the railway wagon bogie sleeper spring sorting system and the sorting method thereof have the advantages of unmanned automatic operation, non-contact property, high detection speed, high efficiency, high identification precision and the like.
Claims (10)
1. A railway freight car bogie sleeper spring sorting system comprises a sleeper spring transferring and grabbing system, an image acquisition system, an image processing system and a control system;
the sleeper spring transferring and grabbing system is provided with a mechanical arm, a sleeper spring gripper is mounted at the tail end of the mechanical arm, and the mechanical arm drives the sleeper spring gripper to complete grabbing and transferring of a sleeper spring under the action of the control system;
the image acquisition system comprises a frame, a worktable, a tool for placing the occipital spring, a camera and an image acquisition card, wherein the worktable is arranged in the frame, and the tool for placing the occipital spring is fixed at the center of the upper surface of the worktable; setting a reference object with a known real size on the working table, wherein the reference object is used for obtaining the ratio of the actual size of the calculated outline in the image processing system, and the ratio = object pixel width/object real width; the camera is arranged on the frame and positioned above the harness, and the camera is electrically connected and in signal connection with the control system; the image acquisition card is used as a communication module of the image acquisition system, and the image acquired by the camera is transmitted to the image processing system through the image acquisition card;
the image processing system comprises a data analysis and processing module, a database, an algorithm library and a corresponding hardware system, and is responsible for parameter setting of the detection process and processing, analysis and transmission of image data;
after a series of basic data analysis and processing, the required detection values are calculated through the detection algorithm provided by the algorithm library, and the detection values are the free height value, the inner diameter value and the outer diameter value of the occipital spring.
2. The railway freight car truck spring sleeper spring sorting system of claim 1, wherein: the frame is provided with a vertical frame and a horizontal frame, and the lower end of the vertical frame is fixedly connected to the upper side of the horizontal frame; a moving axis Y arranged along the vertical direction and a moving axis X arranged along the horizontal direction are arranged on the vertical frame; the X axis is fixed on the slide block of the Y axis; a camera is arranged on the sliding block of the X axis, and a lens of the camera is arranged downwards; a moving shaft Z is arranged in the horizontal frame, the Z shaft is respectively vertical to the X shaft and the Y shaft, and a sliding block of the Z shaft is fixedly connected with the working table; the driving of the X axis, the Y axis and the Z axis is electrically connected with a control system.
3. The railway freight car truck spring sleeper spring sorting system of claim 2, wherein: the working table surface and the harness for placing the pillow spring in the image acquisition system are both made of transparent acrylic plates.
4. The railway freight car truck spring sleeper spring sorting system of claim 3, wherein: a light source and a light source controller are arranged below the working table surface, and the light source adopts an LED lamp ring; the light source controller is electrically connected with the control system and is used for controlling the on-off and brightness adjustment of the light source.
5. The railway freight car truck spring sleeper spring sorting system of claim 1, wherein: the camera in the image acquisition system is GMT200-H industrial camera with high frame rate of 200 ten thousand pixels, and the optical lens used by the camera is SA1620M-10 MP.
6. The method for sorting the sleeper springs of the railway wagon bogie sleeper spring sorting system based on the claim 1, which comprises the following steps:
step (1): after the sleeper spring to be detected is conveyed to a preset position through a conveying line, a sleeper spring transferring and grabbing system is used for grabbing the sleeper spring and placing the grabbed sleeper spring on an apparatus;
step (2): after the sleeper spring is placed on the harness, the image acquisition system starts image acquisition work, and acquired images are transmitted to the image processing system through the image acquisition card;
and (3): the image processing system carries out a series of processing on the received image to obtain corresponding size data of the tested occipital spring, and the image processing system compares the measured size data with size parameters of the occipital spring preset in the system to finish the discrimination of the occipital spring model;
and (4): after the type of the occipital spring is judged, the image processing system transmits the judgment result to the control system, and the occipital spring is taken away by the occipital spring transferring and grabbing system under the action of the control system and is placed at the designated position corresponding to the type of the occipital spring.
7. The method of sorting occipital springs of claim 6 wherein: the working process of the image acquisition in the step (2) comprises the following steps:
step (2.1): in the image acquisition system, a working platform and a harness are both made of transparent acrylic materials, and a normally open LED light source is arranged below the working platform;
step (2.2): the relative position of the camera and the occipital spring to be measured can be adjusted according to the requirement, and the adjustment of the relative position is realized by controlling the driving motors of the X axis, the Y axis and the Z axis by the control system;
step (2.3): after the relative position of the camera and the occipital spring to be detected is adjusted, the control system controls the camera to complete image acquisition;
step (2.4): and after the image acquisition is finished, transmitting the acquired image to an image processing system through an image acquisition card.
8. The method of sorting occipital springs of claim 7 wherein: the working process of the image processing in the step (3) comprises the following steps:
step (3.1): loading an image to be processed and performing preprocessing operation, specifically comprising: graying an image, Gaussian filtering, edge detection, expansion and corrosion, and searching for a contour line;
step (3.2): traversing and screening the obtained object contours, traversing each object contour, and outputting a corresponding object boundary contour;
step (3.3): calculating the coordinates of the central point of each contour and drawing the result;
step (3.4): calculating Euclidean distances between the central point sets according to a ratio value obtained by a preset reference object, and dividing the Euclidean distances by the pixel value of the object to obtain the actual size of the object;
step (3.5): and (4) matching the model of the occipital spring according to the size data obtained in the step (3.4).
9. The method of sorting a occipital spring of claim 8, wherein: the specific process of the pretreatment operation in the step (3.1) is as follows:
step (3.1.1): loading an image, wherein the image is completed by an image acquisition system and is transmitted to an image processing system by an image acquisition card;
step (3.1.2): graying, namely performing gray level conversion by adopting a weighted average algorithm, and respectively giving different weights according to the contribution of R, G, B in the image to gray level;
step (3.1.3): gaussian filtering, wherein a lot of noises are introduced into an image in the imaging, transmission and storage processes, and the detail information of the image is kept as far as possible while the image denoising aims at removing the noises;
step (3.1.4): edge detection, wherein the purpose of the edge detection is to find a set formed by pixel points with severe brightness change in an image, and the displayed set is the outline of a target body;
step (3.1.5): dilation-erosion to eliminate any gaps between edges in the edge map;
step (3.1.6): and (3) searching contours, wherein the result obtained in the step (3.1.4) of edge detection is in a contour line form constructed by a plurality of contours, and in the step, a contour line corresponding to the size of the reaction object in the edge map is searched.
10. The method of sorting a occipital spring of claim 8, wherein: the step (3.2) of profile traversal screening comprises the following specific steps:
step (3.2.1): arranging the contour regions obtained in the step (3.1) from left to right, and facilitating the extraction of a reference datum;
step (3.2.2): knowing the reference datum position and the pixel size, initializing the ratio;
step (3.2.3): checking and checking the size of each contour region value, and circulating each individual contour value in the process;
step (3.2.4): judging the size of the high-speed line area, if the high-speed line area is not large enough, excluding the area, and judging the area to be the noise left in the edge detection process;
step (3.2.5): if the contour line area is large enough, calculating a rotating boundary frame of the image, and then arranging coordinates of the rotating boundary frame in the upper left corner, the upper right corner, the lower right corner and the lower left corner in sequence;
step (3.2.6): drawing the outline of the object by using colored lines, and then drawing colored circles at the vertexes of the rectangle of the bounding box; now that the bounding box is available, a series of midpoints is calculated from the existing bounding box.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010780430.5A CN111957592A (en) | 2020-08-06 | 2020-08-06 | Railway wagon bogie sleeper spring sorting system and sorting method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010780430.5A CN111957592A (en) | 2020-08-06 | 2020-08-06 | Railway wagon bogie sleeper spring sorting system and sorting method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111957592A true CN111957592A (en) | 2020-11-20 |
Family
ID=73365369
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010780430.5A Withdrawn CN111957592A (en) | 2020-08-06 | 2020-08-06 | Railway wagon bogie sleeper spring sorting system and sorting method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111957592A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112971739A (en) * | 2021-02-08 | 2021-06-18 | 上海掌门科技有限公司 | Pulse feeling equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103454285A (en) * | 2013-08-28 | 2013-12-18 | 南京师范大学 | Transmission chain quality detection system based on machine vision |
| CN104006837A (en) * | 2014-06-16 | 2014-08-27 | 哈尔滨工业大学 | Camera adjustment platform for automatic motormeter vision detection device |
| CN104048607A (en) * | 2014-06-27 | 2014-09-17 | 上海朗煜电子科技有限公司 | Visual identification and grabbing method of mechanical arms |
| CN105784713A (en) * | 2016-03-11 | 2016-07-20 | 南京理工大学 | Sealing ring surface defect detection method based on machine vision |
| CN109993723A (en) * | 2017-12-28 | 2019-07-09 | 南京景曜智能科技有限公司 | A kind of pillow spring classification and Detection method based on machine vision |
| CN110610141A (en) * | 2019-08-25 | 2019-12-24 | 南京理工大学 | Logistics storage regular shape goods recognition system |
-
2020
- 2020-08-06 CN CN202010780430.5A patent/CN111957592A/en not_active Withdrawn
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103454285A (en) * | 2013-08-28 | 2013-12-18 | 南京师范大学 | Transmission chain quality detection system based on machine vision |
| CN104006837A (en) * | 2014-06-16 | 2014-08-27 | 哈尔滨工业大学 | Camera adjustment platform for automatic motormeter vision detection device |
| CN104048607A (en) * | 2014-06-27 | 2014-09-17 | 上海朗煜电子科技有限公司 | Visual identification and grabbing method of mechanical arms |
| CN105784713A (en) * | 2016-03-11 | 2016-07-20 | 南京理工大学 | Sealing ring surface defect detection method based on machine vision |
| CN109993723A (en) * | 2017-12-28 | 2019-07-09 | 南京景曜智能科技有限公司 | A kind of pillow spring classification and Detection method based on machine vision |
| CN110610141A (en) * | 2019-08-25 | 2019-12-24 | 南京理工大学 | Logistics storage regular shape goods recognition system |
Non-Patent Citations (4)
| Title |
|---|
| 万月亮: "《互联网图像处理与过滤技术》", 31 August 2012, 国防工业出版社 * |
| 桑凯旋的博客: "使用OpenCVce测量图像中物体的大小", 《CSDN》 * |
| 青岛英谷教育科技股份有限公司: "《机器人控制与应用编程》", 28 February 2018, 西安电子科技大学出版社 * |
| 高宏伟: "《电子封装工艺与装备技术基础教程》", 31 July 2017, 西安电子科技大学出版社 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112971739A (en) * | 2021-02-08 | 2021-06-18 | 上海掌门科技有限公司 | Pulse feeling equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109115785B (en) | Casting polishing quality detection method and device and use method thereof | |
| CN111421425B (en) | Metal surface grinding system based on industrial vision | |
| CN109772733B (en) | Defect bamboo block detecting and sorting device and method based on vision | |
| CN110084849B (en) | Logistics system with automatic volume and weight measuring function | |
| CN203124215U (en) | Frame sealant coating machine | |
| CN111189837B (en) | Cigarette appearance online detection method and device | |
| CN106767518A (en) | A kind of phone housing quality on-line detecting device and method based on line laser structured light | |
| CN105651782A (en) | Engine cylinder cover defect automatic detection equipment based on machine vision | |
| CN107884419A (en) | Automobile chassis automatic checkout equipment, automobile intelligent detecting system | |
| CN107443428A (en) | A kind of band visual identity flapping articulation manipulator and visual identity method | |
| CN109724984A (en) | A kind of defects detection identification device and method based on deep learning algorithm | |
| CN108896547A (en) | Refractory brick measuring system based on machine vision | |
| CN101639452A (en) | 3D detection method for rail surface defects | |
| CN102890093B (en) | Machine vision detecting device of surface quality of master cylinder piston of automobile brake | |
| CN108489394A (en) | A kind of large-scale sheet metal works almost T-stable automatic detection device and method | |
| CN112881427B (en) | Electronic component defect detection device and method based on visible light and infrared thermal imaging | |
| CN110728657A (en) | Annular bearing outer surface defect detection method based on deep learning | |
| CN110186934B (en) | Axle box rubber pad crack detection method and detection device | |
| CN115482195A (en) | Train part deformation detection method based on three-dimensional point cloud | |
| CN112345553A (en) | Hard disk part detection device and detection method | |
| CN111957592A (en) | Railway wagon bogie sleeper spring sorting system and sorting method thereof | |
| CN208042989U (en) | A kind of large-scale sheet metal works almost T-stable automatic detection device | |
| CN112465741B (en) | Defect detection method and device for suspension spring and valve spring and storage medium | |
| CN113885504A (en) | Autonomous inspection method and system for train inspection robot and storage medium | |
| CN115791801A (en) | 3D glass on-line monitoring platform based on machine vision |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20201120 |
|
| WW01 | Invention patent application withdrawn after publication |