Automatic detection method, system and device for bogie completion and storage medium

Abstract

The application relates to an automatic detection method, system and device for bogie completion and a storage medium, the method comprising the following steps: controlling an industrial robot to move a three-dimensional scanner and a two-dimensional camera to a preset position according to a preset motion track; controlling the three-dimensional scanner to acquire point cloud data corresponding to the preset position, and / or controlling the two-dimensional camera to acquire image data corresponding to the preset position; detecting the gap between accessories or the height difference between accessories of the bogie completion according to the point cloud data; and detecting the accessory identification or the installation quality of the accessories of the bogie completion according to the image data. The automatic measurement, automatic identification and automatic comparison of the bogie completion are realized, the actual data of the bogie completion can be accurately acquired, the labor cost and the management cost of a sample caliper are greatly reduced, and the full-automatic online detection of the bogie completion is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of bogie completion detection, in particular to an automatic detection system for bogie completion. BACKGROUND

[0002] The bogie completion of a railway freight car is formed by assembling the bogie and its accessories. After the bogie completion is assembled, the assembly quality and the identification of the accessories need to be detected.

[0003] The detection of the bogie completion is currently performed by personnel using a gauge caliper and a template for manual measurement. However, manual measurement cannot obtain specific measurement data, and the types of templates are numerous, and there are many detection items, which can easily lead to missed detection, and the tool management and human resource management costs are high. SUMMARY

[0004] Therefore, it is necessary to provide an automatic detection system for bogie completion which can accurately detect the bogie completion.

[0005] In a first aspect, an embodiment of the present application provides an automatic detection method for bogie completion, applied to a bogie completion detection system, the bogie completion detection system comprising: an industrial robot, a three-dimensional scanner and a two-dimensional camera being arranged on a shaft arm of the industrial robot;

[0006] The automatic detection method comprises:

[0007] controlling the industrial robot to move the three-dimensional scanner and the two-dimensional camera to a preset position according to a preset motion trajectory;

[0008] controlling the three-dimensional scanner to obtain point cloud data corresponding to the preset position, and / or controlling the two-dimensional camera to obtain image data corresponding to the preset position;

[0009] detecting a gap between accessories or a height difference between accessories of the bogie completion according to the point cloud data;

[0010] detecting an accessory identification or an installation quality of the accessories of the bogie completion according to the image data.

[0011] The industrial robot is controlled to start moving the shaft arm according to a preset track, so that the three-dimensional scanner and the two-dimensional camera are moved to a to-be-measured position and point cloud data and / or picture data are acquired, and then detection is performed on the bogie assembly according to the point cloud data and the picture data to obtain a detection result. The whole process is automatically controlled by the industrial robot, automatic measurement, automatic identification and automatic comparison of the bogie assembly are realized, actual data of the bogie assembly can be accurately acquired, whether the detection is qualified is judged through comparison of the actual data and standard data, the whole process does not need personnel to participate, the labor cost of the whole assembly detection process is greatly reduced, and the management cost of the sample caliper is reduced, and full automation of the online detection of the bogie assembly is realized.

[0012] In a second aspect, the embodiments of the present application provide an automatic detection system for a bogie assembly, comprising:

[0013] An industrial robot, wherein a shaft arm of the industrial robot is provided with a three-dimensional scanner and a two-dimensional camera;

[0014] A general control device connected with the industrial robot, the three-dimensional scanner and the two-dimensional camera respectively;

[0015] The general control device comprises a memory and a processor, and the memory stores a computer program, and the processor realizes the steps of the method when executing the computer program.

[0016] In a third aspect, the embodiments of the present application provide an automatic detection device for a bogie assembly, comprising:

[0017] A control module for controlling the industrial robot to move the three-dimensional scanner and the two-dimensional camera to a preset position according to a preset motion track;

[0018] An acquisition module for controlling the three-dimensional scanner to acquire point cloud data corresponding to the preset position, and / or controlling the two-dimensional camera to acquire image data corresponding to the preset position;

[0019] A first processing module for detecting a gap between parts or a height difference between parts of the bogie assembly according to the point cloud data;

[0020] A second processing module for detecting a part identification or an installation quality of the parts of the bogie assembly according to the image data to obtain a detection result.

[0021] In a fourth aspect, the embodiments of the present application provide a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to realize the steps of the method.

[0022] It can be understood that the beneficial effects of the bogie completion automatic detection system of the second aspect, the bogie completion automatic detection device of the third aspect and the computer readable storage medium of the fourth aspect provided above can refer to the beneficial effects of the bogie completion automatic detection method of the first aspect and any one of the embodiments thereof, which will not be repeated here. BRIEF DESCRIPTION OF DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present application or the prior art, the drawings required to be used in the embodiments or the prior art description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0024] Figure 1 A flowchart of a bogie completion automatic detection method in an embodiment;

[0025] Figure 2 A structural diagram of a bogie completion automatic detection system in an embodiment;

[0026] Figure 3 A structural diagram of a height detection device in an embodiment;

[0027] Figure 4 A structural diagram of a wheel pair alignment device in an embodiment;

[0028] Figure 5 A structural block diagram of a bogie completion automatic detection device in an embodiment. DETAILED DESCRIPTION

[0029] In order to facilitate the understanding of the present application, the present application will be described more fully below with reference to the related drawings. The drawings show embodiments of the present application. However, the present application can be implemented in many different forms, and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present application more thorough and comprehensive.

[0030] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs. The terms used in the specification of the present application are only for the purpose of describing the specific embodiments of the present application, and are not intended to limit the present application.

[0031] It is to be understood that the terms "first", "second", etc. are used herein only for descriptive purposes and not to denote or imply relative importance or an indicated number of technical features. Thus, features defined with "first", "second" can include at least one of the features explicitly or implicitly. The terms "first", "second" and the like can be used herein to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from another element. In addition, in the description of the present application, the meaning of "a plurality of" is at least two, such as two, three, etc., unless otherwise explicitly specified. In the description of the present application, the meaning of "several" is at least one, such as one, two, etc., unless otherwise explicitly specified.

[0032] It should be noted that when an element is considered to be "connected" to another element, it can be directly connected to another element, or connected to another element through a central element. In addition, "connection" in the following embodiments should be understood as "electrically connected", "communicatively connected" and the like if there is transmission of electrical signals or data between the connected objects.

[0033] As used herein, the singular forms "a", "an" and "the" can also include plural forms unless the context clearly indicates otherwise. It should also be understood that the terms "include / contain" or "have" and the like specify the presence of stated features, integers, steps, operations, components, parts or combinations thereof, but do not exclude the presence or addition of one or more other features, integers, steps, operations, components, parts or combinations thereof.

[0034] As described in the background, the detection of the bogie in the prior art has the problems of inaccurate detection and high detection cost. Therefore, the present application provides an automatic detection system for bogie, which realizes automatic detection, automatic identification and automatic comparison of railway wagon bogie by automatic control technology, robot technology and robot detection technology, realizes full automation of bogie online detection, and greatly reduces the labor cost and sample management cost.

[0035] In one embodiment, as shown in Figure 1 An automatic detection method for bogie is provided, applied to a bogie detection system, the bogie detection system comprising: an industrial robot, a three-dimensional scanner and a two-dimensional camera are arranged on the shaft arm of the industrial robot; the automatic detection method for the bogie comprises the following steps S100 to S300.

[0036] S100, control the industrial robot to move the three-dimensional scanner and the two-dimensional camera to a preset position according to a preset motion track.

[0037] The control subject of the embodiment can be an external control device or an industrial robot, which controls the movement trajectory of the industrial robot as a whole and controls the movement trajectory of the shaft arm of the industrial robot. The preset position refers to the position of the three-dimensional scanner and the two-dimensional camera for obtaining the position of the part of the bogie to be detected. The point cloud data or image data obtained by the three-dimensional scanner and the two-dimensional camera at the preset position is the data of the position of the bogie to be detected. The preset position in the embodiment is not only one position, but also one or more positions determined according to the items to be detected in the bogie.

[0038] S200, control the three-dimensional scanner to obtain point cloud data corresponding to the preset position, and / or control the two-dimensional camera to obtain image data corresponding to the preset position.

[0039] According to the type of the item to be detected, the type of data to be obtained at different preset positions can be different, that is, at a certain preset position, only the point cloud data corresponding to the preset position is obtained, or only the image data corresponding to the preset position is obtained, or both types of data can be obtained. The point cloud data obtained at different preset positions is different, and the image data obtained is also different. In data processing, different detection positions can be detected by different data processing methods and recognition methods.

[0040] S300, detecting the gap between the parts or the height difference between the parts of the bogie according to the point cloud data.

[0041] Since the detection positions of different detection items are different, the corresponding point cloud data is also different. In the embodiment, since the gap between the parts cannot be detected, the surface of the part is not smooth, and the picture shooting method cannot accurately detect the gap and the height difference between the parts, the point cloud data is mainly used to detect the gap between the parts and the height difference between the parts of the bogie.

[0042] S400, detecting the part identification or the installation quality of the part of the bogie according to the image data.

[0043] The part identification and the installation quality of the part can be detected by image recognition. The installation quality of the part is mainly to detect whether the installation position of the part is correct, whether the cooperation mode with other parts is correct, and whether the installation direction is correct.

[0044] In the above embodiment, the industrial robot is controlled to start moving the shaft arm according to the preset track, so that the three-dimensional scanner and the two-dimensional camera move to the to-be-measured position and acquire point cloud data and / or picture data, and then detection results of the bogie assembly are obtained according to the point cloud data and the picture data. The whole process is automatically controlled by the industrial robot, and automatic measurement, automatic identification and automatic comparison of the bogie assembly are realized. At the same time, actual data of the bogie assembly can be accurately acquired, and whether the detection is qualified is judged by comparing the actual data with standard data. The whole process does not need personnel to participate, greatly reduces the labor cost of the whole assembly detection process, and reduces the management cost of the sample caliper, and realizes the full automation of the online detection of the bogie assembly.

[0045] In one embodiment, step S300 specifically comprises:

[0046] S310a, fitting the point cloud data with a corresponding standard gap model to obtain a gap width;

[0047] S320a, if the gap width does not exceed the maximum gap width of the standard gap model, the gap between the fittings is qualified.

[0048] If the collected point cloud data is the point cloud data of the gap between the fittings, after the total control device acquires the point cloud data, the point cloud data is fitted with a standard gap model. The standard gap model is a standard CAD gap model. The standard CAD gap model is established by collecting point clouds of the gap part between the fittings of a qualified bogie assembly, and then processing the collected point clouds by reverse engineering. The gap part is set to the maximum value. The standard CAD gap model is stored as a standard gap model for fitting the point cloud data acquired in the detection process. The fitting process is to accurately match the point cloud data with the standard gap model by using a reference alignment algorithm and a best fitting algorithm. The gap width is obtained by analyzing the gap width of the edge line, plane and other information. The gap width is compared with the maximum gap width of the standard gap model. If the gap width does not exceed the maximum gap width of the standard gap model, the gap between the fittings is qualified.

[0049] Alternatively, step S300 specifically comprises:

[0050] S310b, fitting the point cloud data with a corresponding standard height difference model to obtain a height difference;

[0051] S320b, if the height difference does not exceed the maximum height difference of the standard height difference model, the height difference between the fittings is qualified.

[0052] If the collected point cloud data is the point cloud data of the height difference between the accessories, after the total control device acquires the point cloud data, the point cloud data is fitted by using a standard height difference model, the standard height difference model is a standard CAD height difference model, the corresponding two accessories of a qualified bogie are subjected to point cloud collection, and then the collected point cloud is processed by using reverse engineering to establish a standard CAD height difference model. The standard CAD height difference model is stored as a standard gap model and is used for fitting of the point cloud data acquired in the detection process. The fitting process is to accurately match the point cloud data and the standard gap model by using a reference alignment algorithm and a best fitting algorithm to obtain a height difference. The height difference is compared with the maximum height difference of the standard height difference model. If the height difference does not exceed the maximum height difference of the standard height difference model, the height difference between the accessories is qualified.

[0053] In one embodiment, the point cloud data includes first accessory data and second accessory data, and the Z-axis zero point of the three-dimensional coordinate system corresponding to the first accessory data and the Z-axis zero point of the three-dimensional coordinate system corresponding to the second accessory data are in the same plane; step S310b specifically includes: obtaining combined point cloud data according to mapping the first accessory data and the second accessory data into the same coordinate system; fitting the combined point cloud data with the corresponding standard height difference detection model to obtain a height difference.

[0054] Since the bogie is large in volume, the range of the three-dimensional scanner may not be able to simultaneously scan and acquire point cloud data of two accessories far apart. When detecting two accessories far apart, point cloud data of the two accessories in different coordinate systems, i.e., first accessory data and second accessory data, need to be acquired. Although the reference coordinate systems of the point cloud data of the two accessories are different, the reference longitudinal coordinates of the point cloud data of the two accessories are required to be the same, that is, during acquisition of the point cloud data of the two accessories, the camera of the three-dimensional scanner is required to be in the same horizontal plane to ensure the accuracy of the height difference detection of the two accessories after subsequent data processing. The first accessory data and the second accessory data are mapped into the same coordinate system, that is, the first accessory data and the second accessory data are moved in the X-axis direction or the Y-axis direction for coordinate alignment to obtain combined point cloud data in the same coordinate system. Then, the combined point cloud data is fitted with the corresponding standard height difference detection model to accurately match the combined point cloud data and the standard height difference detection model to obtain a height difference.

[0055] In one embodiment, step S400 specifically includes: performing binaryzation processing and edge detection on the image data to extract structured features of the accessory identification; identifying the structured features of the accessory identification to obtain an accessory identification result; and comparing the identification result with a standard identification.

[0056] If the image data is a part identification image, a target extraction algorithm and an edge detection algorithm are used to extract the structural features of the part identification in the image data. The target extraction algorithm usually adopts a threshold-based or difference-based method, and the edge detection algorithm usually involves differential-based, template matching-based, and binary image processing, etc. After obtaining the structural features of the part identification, the structural features are identified, and the identification method can use a deep learning network for identification to obtain an identification result. The identification result is compared with a standard identification to obtain a comparison result. Different identifications have different comparison result forms. For example, when comparing the maintenance identification, it is only necessary to determine whether the maintenance identification exists. When comparing the age identification, the identified age needs to be compared with the age of the current year to determine whether the detected part is at the end of its life.

[0057] Alternatively, step S400 specifically includes: using a target extraction algorithm and an edge detection algorithm to extract the structural features of the image data to obtain the installation quality structural features of the part, wherein the installation quality structural features include the installation direction features of the part and the cooperation mode features with other parts; identifying the installation quality structural features of the part to obtain a quality identification result; and comparing the quality identification result with a standard installation quality.

[0058] If the image data is an image for detecting the installation quality of the part, a target extraction algorithm and an edge detection algorithm are used to extract the installation direction and cooperation mode structural features of the part in the image data. The target extraction algorithm usually adopts a threshold-based or difference-based method, and the edge detection algorithm usually involves differential-based, template matching-based, and binary image processing, etc. After obtaining the installation quality structural features of the part, the structural features are identified, and the identification result is compared with a standard installation quality result to determine whether the installation direction and cooperation mode of the part are qualified.

[0059] In one embodiment, as shown in Figure 2 A bogie completion automatic detection system is provided, which includes an industrial robot 100 and a general control device 200. A three-dimensional scanner and a two-dimensional camera are arranged on the shaft arm of the industrial robot 100. The general control device 200 is connected with the industrial robot 100, the three-dimensional scanner, and the two-dimensional camera. The general control device 200 includes a memory and a processor. The memory stores a computer program. When the processor executes the computer program, the steps of any one of the embodiments of the bogie completion automatic detection method are implemented.

[0060] Specifically, the shaft arm of the industrial robot 100 is provided with a three-dimensional scanner and a two-dimensional camera, the three-dimensional scanner is used to obtain point cloud data of the bogie assembly, and the two-dimensional camera is used to obtain image data of the bogie assembly. The general control device 200 controls the shaft arm of the industrial robot 100 to start moving the shaft arm according to a preset motion track, and after the three-dimensional scanner and the two-dimensional camera move to a preset position, controls the three-dimensional scanner and / or the two-dimensional camera to obtain point cloud data and / or image data corresponding to the preset position. The three-dimensional scanner is used to obtain point cloud data of a to-be-detected position of the bogie assembly, and the point cloud data refers to a data set of points in a three-dimensional coordinate system, which can be used for three-dimensional modeling. The three-dimensional scanner scans the to-be-detected position of the bogie assembly, extracts point cloud data, and transmits the point cloud data to the general control device 200. The two-dimensional camera is used to obtain image data of the to-be-detected position of the bogie assembly, and the image data is a two-dimensional image. Specifically, the two-dimensional camera takes a picture of the to-be-detected position, and transmits the picture to the general control device 200. The preset positions corresponding to the data to be collected by the three-dimensional scanner and the two-dimensional camera can be the same or different, and are specifically determined according to the detection mode and the items to be detected. After the general control device 200 obtains the point cloud data and the image data from the three-dimensional scanner and the two-dimensional camera, the point cloud data and the image data are processed respectively, and the bogie assembly is detected.

[0061] In one embodiment, the automatic detection system for the bogie assembly further comprises a guide rail 300, an assembly detection station 400, and a rail guide vehicle. The rail guide vehicle is connected to the bogie assembly and is used to move the bogie assembly along the guide rail 300 to the assembly detection station 400. After the previous detection item of the bogie assembly is completed, the general control device 200 controls the rail guide vehicle to move, so that the rail guide vehicle pulls the bogie assembly to move along the guide rail 300 to the assembly detection station 400. After the bogie assembly enters the assembly detection station 400, the general control device 200 controls the industrial robot 100 to move to the side of the assembly detection station 400 for detection. After the detection is completed, the general control device 200 controls the rail guide vehicle to move the bogie assembly to the detection station of the next detection item.

[0062] In one embodiment, the automatic detection system for the bogie assembly further comprises a height detection device, which is used to detect whether the distance between the bottom accessory of the bogie assembly and the ground is qualified.

[0063] Specifically, a height detection device is used to measure the height of the bottom components of the bogie assembly relative to the ground. The bottom components refer to those installed at the bottom of the bogie assembly, and are the components closest to the ground besides the wheels. The height of the lowest point of the bogie assembly's bottom needs to be controlled above a preset height to ensure the bottom height test is qualified. Since the bogie assembly is composed of multiple components, its bottom is uneven due to the presence of these components. However, since the installation method of the components is fixed, the height detection device mainly checks whether the distance between the lowest component and the ground meets the qualification requirements. If the distance between the bottom component and the ground is insufficient, the bottom test fails. Different height detection devices can be used depending on the position of the lowest component. For example, an infrared transmitter and receiver can be set at a specific location, and the bottom height can be judged by whether the infrared signal is blocked by the bottom of the bogie assembly. Alternatively, a fixed-height baffle can be set, and the bottom height can be judged by whether the baffle is pushed over by the bogie assembly.

[0064] In one embodiment, such as Figure 3 As shown, the height detection device 500 includes a base 510 and a plate 520, a compression spring 530, and a micro switch 540 disposed on the base 510; wherein, the base 510 is disposed on the detection station of the bogie landing 700; the first end of the plate 520 is rotatably connected to the base 510, and the second end of the plate 520 is connected to the base 510 through the compression spring 530, for being pressed down by the bottom component when the distance between the bottom component of the bogie landing 700 and the ground is unqualified; the micro switch 540 is disposed between the plate 520 and the base 510, for closing to generate an electrical signal when the plate 520 is pressed down; the micro switch is connected to the main control device 200.

[0065] Specifically, Figure 3The arrow direction in the bogie assembly is the movement direction of the bogie assembly, the base 510 is fixed on the ground at the bogie assembly detection station 400, the plate 520 with a preset height is arranged on the base 510, the height of the plate 520 is used to detect whether the bottom height of the bogie assembly is qualified, and the position and width of the plate 520 on the bogie assembly detection station 400 can be determined according to the position of the bottom accessory to be detected. The first end of the plate 520 is rotatably connected with the base 510, the plate 520 is arranged obliquely towards the movement direction of the bogie assembly, and forms an angle with the base 510, that is, the first end of the plate 520 is directed away from the movement direction of the bogie assembly 700, and the movement direction is the movement direction of the bogie assembly 700 into the detection station. The second end of the plate 520 is connected with the first end of the compression spring 530, and the second end of the plate 520 is directed towards the movement direction of the bogie assembly 700, and the plate is used to be pressed down by the bottom accessory in the case that the distance between the bottom accessory of the bogie assembly 700 and the ground is unqualified. The second end of the compression spring 530 is fixed on the base 510, the micro switch 540 is arranged between the plate 520 and the base 510, and is connected with the general control device 200. The driving rod of the micro switch 540 is close to or contacts the plate 520 below. In the case that the compression spring 530 is not compressed, the second end of the plate 520 is supported by the compression spring 530 to keep at a preset height. If the bottom of the bogie assembly is unqualified, the lowest part of the bottom will move the second end of the plate 520 downwards, so as to press the driving rod of the micro switch 540, the driving rod acts on the moving spring sheet of the micro switch 540, so that the circuit in which the micro switch 540 is located is quickly connected, so as to generate an electrical signal. The general control device 200 receives the electrical signal, and judges that the bottom height of the bogie assembly is unqualified.

[0066] In one embodiment, the automatic detection system of the bogie assembly further comprises a positioning device arranged at the bogie assembly detection station 400, and the positioning device is used to fix the bogie assembly at the bogie assembly detection station 400.

[0067] Specifically, the positioning device for fixing the bogie assembly at the bogie assembly detection station 400 is arranged at the bogie assembly detection station 400. In the process of acquiring detection data, since the position of the industrial robot 100 during detection is fixed, the movement track of the shaft arm is also fixed. Therefore, it is necessary to ensure that the bogie assembly is fixed at a fixed position on the bogie assembly detection station 400 and cannot move during the whole process of acquiring detection data, so as to accurately extract the point cloud data and image data of the position to be detected. The positioning device can be arranged on the guide rail 300 and fixed on the wheel set through the telescopic baffle, or a device for clamping the wheel set can be arranged on the ground to fix the wheel set.

[0068] In one embodiment, as Figure 4As shown, the positioning device is a wheel set alignment device, which fixes the bogie 700 by clamping the first wheel set and the second wheel set of the bogie 700.

[0069] Specifically, since the width of the wheel is greater than the width of the guide rail 300, one wheel set alignment device is arranged beside each guide rail 300 of the drop detection station 400, and the wheel set of the bogie 700 includes a first wheel set and a second wheel set, the first wheel set can be a front wheel or a rear wheel, if the first wheel set is a front wheel, the second wheel set is a rear wheel, and if the first wheel set is a rear wheel, the second wheel set is a front wheel. The wheel set alignment device of the present embodiment is used to clamp the wheels of the first wheel set and the wheels of the second wheel set located on the same guide rail. The wheel set alignment device includes a first folding rod 610 and a second folding rod 620, one end of the first folding rod 610 and the second folding rod 620 is symmetrically arranged on the ground, and the other end of the first folding rod 610 and the second folding rod 620 is used to clamp the wheel set. When positioning is not required, the general control device 200 controls the first folding rod 610 and the second folding rod 620 to extend, so that the bogie can move along the guide rail 300, and when positioning is required, the first folding rod 610 and the second folding rod 620 are controlled to retract, thereby clamping the wheel set of the bogie.

[0070] In one embodiment, the general control device 200 is connected with the industrial robot 100 through an Ethernet communication connection, and the general control device 200 is connected with the three-dimensional scanner and the two-dimensional camera through a USB connection respectively.

[0071] In one embodiment, the three-dimensional scanner is a binocular structured light scanner, and the camera lens of the two-dimensional camera is arranged between the two camera lenses of the binocular structured light scanner.

[0072] Specifically, the binocular structured light scanner combines binocular stereo vision technology and coded structured light technology, uses visible light to project specific Gray code grating fringes onto the surface of the position to be measured, and includes two high-resolution digital cameras, such as CCD cameras. The binocular structured light scanner can obtain complete point clouds of a complex working surface in a very short time by taking pictures of the grating interference fringes through the two high-resolution CCD digital cameras, using optical photographing positioning technology and grating measurement principle. During measurement, the grating projection device projects specific coded structured light onto the object to be measured, two CCD digital cameras at a certain angle synchronously collect images, then the images are decoded and phase calculation is performed, and the three-dimensional coordinates of the pixel points in the common view area of the two CCD digital cameras, i.e. point cloud data, are calculated by using matching technology and triangulation principle. Since the measurement method is based on grating measurement, it does not need to fix the coordinates, and the unique flow design and automatic splicing technology of different view point clouds make the scanning not need to limit the position and trajectory of the measurement system, so that large workpieces can be efficiently and easily scanned. The two-dimensional camera is an industrial digital camera, such as a CCD camera. The two-dimensional camera is arranged between the two camera lenses of the binocular structured light scanner, and can simultaneously obtain two kinds of data of the same position to be measured without needing to convert the position of the camera.

[0073] In one embodiment, the bogie completion automatic detection system further comprises light sources arranged at both sides of the completion detection station 400 and the end of the shaft arm of the industrial robot 100, and the light sources are used for light compensation.

[0074] Specifically, in order to obtain accurate data, light sources are arranged at both sides of the completion detection station 400, and the number of light sources on each side can be one or more, which is determined according to the position to be detected. For example, one light source can be arranged at the position opposite to each wheel on the side, and the light can cover the entire side of the bogie completion. Meanwhile, light sources are also arranged at the end of the shaft arm of the industrial robot 100. In the case of dark light, the light sources are turned on for light compensation each time the picture is taken, so as to improve the accuracy of the data.

[0075] In one embodiment, the bogie completion automatic detection system further comprises an alarm device, and the alarm device is connected with the general control device 200. The general control device 200 is further used for controlling the alarm device to alarm if the detection result of the bogie completion is unqualified.

[0076] Specifically, after obtaining the detection result, the general control device 200 controls the alarm device to alarm if the detection result is unqualified, so that the staff can know in time, and check the unqualified items by calling the detection report, so as to process in time. If the problem is small, the bogie completion can be directly repaired or repaired on the completion detection station 400, and if the problem is large, the bogie completion can be moved out of the completion detection station 400 for repair or repair.

[0077] In a specific embodiment, after the bogie erection is completed at the end of the previous inspection item (such as the static load test), the master control device controls the guided vehicle to push the bogie to the erection inspection station, and controls the wheel pair centering device to clamp the wheel pairs of the bogie to fix the bogie erection. After the staff inputs the model of the bogie to be inspected in the master control device, the master control device controls the industrial robot to move the shaft arm along a preset movement path, so that the 3D scanner and the 2D camera move to the preset positions. Then, it controls the 3D scanner to obtain point cloud data and / or controls the 2D camera to obtain picture data, and then moves the 3D scanner and the 2D camera to another preset position to obtain data until the point cloud data and / or image data corresponding to all preset positions are obtained. After processing the point cloud data, a clearance model between the accessories of the bogie erection, a height difference model between the accessories, and an accessory model are obtained. The standard model is used to fit with each clearance model, each height difference model, and each accessory model to obtain each clearance deviation, each height deviation, and each accessory size deviation respectively. If each deviation does not exceed the corresponding deviation threshold, the inspection is qualified; if there is a deviation exceeding the corresponding deviation threshold, the inspection is unqualified, and the alarm device is controlled to give an alarm to remind the staff. After processing the image data, the structured feature data corresponding to the 2D image is obtained. The structured feature data is compared with the standard structured feature data. If the comparison result is qualified, the inspection is qualified; if the comparison result is unqualified, the inspection is unqualified, and the alarm device is controlled to give an alarm. After the acquisition of the 3D point cloud data and the image data is completed, the centering device is controlled to be released, that is, the wheel pairs of the bogie are loosened, and the guided vehicle is controlled to push the bogie out of the erection inspection station. When the bogie erection completely passes through the height detection device, if the electrical signal of the height detection device is not received, the inspection is qualified; if the electrical signal of the height detection device is received, the inspection is unqualified, and the alarm device is controlled to give an alarm. After all inspections are completed, the inspection data and the inspection results are formed into an inspection report and the inspection report is stored.

[0078] In one embodiment, as Figure 5 shown, an automatic inspection device 800 for bogie erection is provided, including: a control module 810, an acquisition module 820, a first processing module 830, and a second processing module 840. The control module 810 is used to control the industrial robot to move the 3D scanner and the 2D camera to the preset positions along a preset movement trajectory. The acquisition module 820 is used to control the 3D scanner to obtain the point cloud data corresponding to the preset positions and / or control the 2D camera to obtain the image data corresponding to the preset positions. The first processing module 830 is used to detect the clearance between the accessories of the bogie erection or the height difference between the accessories according to the point cloud data. The second processing module 840 is used to detect the accessory identification or the installation quality of the accessories of the bogie erection according to the image data to obtain the inspection results.

[0079] In one embodiment, a computer readable storage medium is provided, having stored thereon a computer program, which, when executed by a processor, implements the steps of the method of any one of the above embodiments.

[0080] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiments. Any reference to memory, storage, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0081] In the description of the present specification, the description of the terms "some embodiments", "other embodiments", "ideal embodiments" and the like means that the specific features, structures, materials or characteristics described in connection with the embodiments or examples are included in at least one embodiment or example of the present application. In the present specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example.

[0082] The technical features of the above embodiments can be combined in any way. In order to make the description simple, not all possible combinations of the technical features in the above embodiments are described, however, as long as the combinations of the technical features do not contradict, they should be considered as the scope of the present application.

[0083] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent. It should be pointed out that for those of ordinary skill in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the scope of the present application. Therefore, the scope of the patent of the present application should be subject to the appended claims.

Claims

1. A method for automatically detecting completion of a bogie, characterized by, The application is applied to a bogie completion detection system, and the bogie completion detection system comprises an industrial robot, and a three-dimensional scanner and a two-dimensional camera are arranged on the shaft arm of the industrial robot; The automatic detection method comprises: controlling the industrial robot to move the three-dimensional scanner and the two-dimensional camera to a preset position according to a preset motion track; wherein the preset position refers to a position where the three-dimensional scanner and the two-dimensional camera are located for acquiring a part of the bogie completion to be detected; controlling the three-dimensional scanner to acquire point cloud data corresponding to the preset position, and / or controlling the two-dimensional camera to acquire image data corresponding to the preset position; detecting a gap between parts of the bogie completion or a height difference between the parts according to the point cloud data; detecting part identification or installation quality of the parts of the bogie completion according to the image data; wherein the detection of the gap between the parts of the bogie completion or the height difference between the parts according to the point cloud data comprises: fitting the point cloud data with a corresponding standard gap model to obtain a gap width; if the gap width does not exceed a maximum gap width of the standard gap model, the gap between the parts is qualified; or, fitting the point cloud data with a corresponding standard height difference model to obtain a height difference; if the height difference does not exceed a maximum height difference of the standard height difference model, the height difference between the parts is qualified; wherein the point cloud data comprises first part data and second part data, and when two parts far away from each other are detected, point cloud data of the two parts in different coordinate systems, i.e. the first part data and the second part data, need to be acquired respectively; a Z-axis zero point of a three-dimensional coordinate system corresponding to the first part data and a Z-axis zero point of a three-dimensional coordinate system corresponding to the second part data are located on the same plane; and the fitting of the point cloud data with the corresponding standard height difference model to obtain the height difference comprises: moving the first part data and the second part data in an X-axis direction or a Y-axis direction for coordinate alignment, so as to map the first part data and the second part data into the same coordinate system to obtain combined point cloud data; fitting the combined point cloud data with a corresponding standard height difference detection model to obtain the height difference.

2. The method of claim 1, wherein the method further comprises: The detection of the part identification or the installation quality of the parts of the bogie completion according to the image data comprises: performing structured feature extraction on the image data by using a target extraction algorithm and an edge detection algorithm to obtain structured features of the part identification; recognizing the structured features of the part identification to obtain a part recognition result; comparing the recognition result with a standard identification to obtain a comparison result; or, performing structured feature extraction on the image data by using a target extraction algorithm and an edge detection algorithm to obtain installation quality structured features of the parts, wherein the installation quality structured features comprise installation direction features of the parts and cooperation mode features with other parts; recognizing the installation quality structured features of the parts to obtain a quality recognition result; The quality identification result is compared with a standard installation quality to obtain a comparison result.

3. An automatic detection system for detecting completion of a bogie, characterized in that, The industrial robot is provided with a three-dimensional scanner and a two-dimensional camera on a shaft arm of the industrial robot; A total control device is connected with the industrial robot, the three-dimensional scanner and the two-dimensional camera respectively; the total control device comprises a memory and a processor, the memory stores a computer program, and the processor realizes the steps of the method of any one of claims 1-2 when executing the computer program. Further comprising a height detection device connected with the total control device, the height detection device is used for detecting the bottom height of the bogie assembly.

4. The automatic detection system for the presence of a truck landing according to claim 3, characterized in that, The height detection device comprises a base, a plate, a compression spring and a micro switch, the first end of the plate is rotatably connected with the base, the second end of the plate is connected with the first end of the compression spring, the second end of the compression spring is connected with the base, the micro switch is arranged between the plate and the base, and the micro switch is connected with the total control device.

5. The automatic detection system for the presence of a truck landing according to claim 4, characterized in that, Further comprising a positioning device, the positioning device is used for fixing the bogie assembly in the bogie assembly detection station.

6. The automatic detection system for the presence of a truck landing according to claim 3, characterized in that, The control module controls the industrial robot to move the three-dimensional scanner and the two-dimensional camera to a preset position according to a preset motion track; wherein the preset position refers to the position of the three-dimensional scanner and the two-dimensional camera for acquiring the part of the bogie assembly to be detected; 7. An automatic detection device for bogie assembly, characterized in that, The acquisition module is used for controlling the three-dimensional scanner to acquire point cloud data corresponding to the preset position, and / or controlling the two-dimensional camera to acquire image data corresponding to the preset position; The first processing module is used for detecting the gap between the parts or the height difference between the parts of the bogie assembly according to the point cloud data; The second processing module is used for detecting the part identification or the installation quality of the parts of the bogie assembly according to the image data to obtain a detection result; The first processing module is used for: Fitting the point cloud data with a corresponding standard gap model to obtain a gap width; If the gap width does not exceed the maximum gap width of the standard gap model, the gap between the parts is qualified; Or, Fitting the point cloud data with a corresponding standard height difference model to obtain a height difference; If the height difference does not exceed the maximum height difference of the standard height difference model, the height difference between the parts is qualified; The point cloud data comprises first part data and second part data, when detecting two parts far away from each other, point cloud data of the two parts in different coordinate systems, i.e. the first part data and the second part data, need to be acquired respectively; The Z-axis zero point of the three-dimensional coordinate system corresponding to the first part data and the Z-axis zero point of the three-dimensional coordinate system corresponding to the second part data are in the same plane; and the fitting of the point cloud data with the corresponding standard height difference model to obtain the height difference comprises: ​ ​ The first accessory data and the second accessory data are moved in an X-axis direction or a Y direction for coordinate alignment to map the first accessory data and the second accessory data into the same coordinate system to obtain combined point cloud data; The combined point cloud data is fitted with a corresponding standard height difference detection model to obtain a height difference.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by a processor to implement the steps of the method of any one of claims 1-2.

Images