An automatic sorting device and method for stamping gaskets based on machine vision

Abstract

The present invention discloses an automatic sorting device and method for stamping gaskets based on machine vision. The device includes a control device, a conveyor belt assembly, a separating device, and a turning device; the first separating device is arranged at one end where conveyor belt three, conveyor belt four, and conveyor belt two are commonly connected, and is used for separately sending gaskets with the front side facing up and the back side facing up to conveyor belt three and conveyor belt four; the turning device is arranged between conveyor belt four and conveyor belt five and is used for turning over the gaskets; a second camera is arranged above conveyor belt two and is used for collecting images of the gaskets and transmitting them to the control device; the control device controls the first separating device to act, sends the gaskets with the back side facing up to conveyor belt four, and after being turned over by the turning device, sends them to conveyor belt five. The automatic sorting device and method for stamping gaskets based on machine vision provided by the present invention can cyclically identify the placement state of the gaskets, timely screen the gaskets with the back side facing up, have a high level of automatic control, and improve the gasket identification efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of automatic detection equipment for production lines, and particularly to an automatic sorting device and method for stamping gaskets based on machine vision. Background Art

[0002] During industrial production, in order to prevent the influence of pressure, corrosion or thermal expansion and contraction of pipelines between two parts, it is usually necessary to install gaskets on bolts to increase friction and reduce pressure, thereby playing a role in protecting parts and bolts. Gaskets have front and back sides. The correct method should be that the front side of the gasket is close to the bolt side. If the gasket is placed in the reverse direction, not only will the friction be reduced, but the gasket will also be deformed and lose its function, failing to play a protective role.

[0003] In related technologies, during the resistance welding process, it is necessary to manually identify the front and back sides of the gasket, and then manually assemble the bolt and the gasket with the front side facing up and feed it into the resistance welding equipment manually. This has problems such as high labor intensity and low production efficiency. In addition, the resistance welding process will generate metal dust, toxic gases, etc., which are harmful to the health of operators. Moreover, in the patent document CN201710258563 - An automatic gasket sorting machine, a laser identifier is used to identify the front and back sides. The reverse - side gaskets are blown out of the gasket groove by an air jet valve and fall into the gasket hopper. The principle of using the laser identifier to identify the front and back sides is not very clear. Generally speaking, it can identify the front and back sides with different colors. The equipment investment is large, there is no turning - over device, and the reverse - side gaskets are blown out, affecting production efficiency. In addition, in the patent document 201910675064.4 - Automatic gasket sorting device and method, an image sensor is used to detect the inner and outer edges and textures of the hole - type gasket, and image processing is used to identify the front and back sides, and a pneumatic device is used to turn it over. The air holes jet air to impact the edge to achieve the purpose of turning over. However, this solution requires adding a set of pneumatic devices, which requires the support of power, pneumatic equipment, etc., and the cost is high. Summary of the Invention

[0004] The object of the present invention is to provide an automatic sorting device and method for stamping gaskets based on machine vision, which has a simple structure, a high level of automatic control, can cyclically identify the placement state of the gaskets, timely screen the gaskets with the reverse side facing up, perform turning - over adjustment, has a high recognition accuracy, and a good effect of automatic gasket sorting.

[0005] To achieve the above object, the present invention provides the following solutions:

[0006] An automatic sorting device for stamping gaskets based on machine vision, comprising a control device, a conveyor belt assembly, a first separating device and a turning device. The conveyor belt assembly includes conveyor belt two, conveyor belt three, and conveyor belt five connected in sequence. One end of conveyor belt two connected to conveyor belt three is also connected to conveyor belt four. The first separating device is arranged at one end where conveyor belt three, conveyor belt four and conveyor belt two are commonly connected, and is used to separately send gaskets with the front side facing up and the back side facing up to conveyor belt three and conveyor belt four. The turning device is arranged between conveyor belt four and conveyor belt five and is used to turn over the gaskets.

[0007] Above conveyor belt two, a second camera is arranged, which is used to collect images of the gaskets and transmit them to the control device. The control device is electrically connected to the first separating device, and the control device controls the first separating device to act, sending the gaskets with the back side facing up to conveyor belt four, and after being turned over by the turning device, sending them to conveyor belt five.

[0008] Optionally, the automatic sorting device for stamping gaskets based on machine vision further includes a third camera arranged above conveyor belt five and a second separating device arranged at the end of conveyor belt five. The third camera and the second separating device are respectively electrically connected to the controller. The end of conveyor belt five is connected to conveyor belt six, and the controller controls the second separating device to act, which is used to send the gaskets with the back side facing up to conveyor belt six.

[0009] Optionally, the conveyor belt assembly further includes conveyor belt one. Conveyor belt one is connected to conveyor belt two and is used to convey the gaskets to conveyor belt two. Above conveyor belt one, a first camera is arranged. Conveyor belt one is inclined, and the first camera is arranged vertically downward. Conveyor belt two is horizontal, and the second camera is inclined. The first camera and the second camera are connected to the control device and are used to collect the inner and outer hole cylinder surface images of the gaskets from different angles respectively. Conveyor belt six is connected to conveyor belt one and is used to send the gaskets with the back side facing up back to conveyor belt two.

[0010] Optionally, both the first separating device and the second separating device include an electric control rotating shaft and a baffle. One end of the baffle is fixedly connected to the electric control rotating shaft and rotates within a set angle around the axis of the electric control rotating shaft.

[0011] Optionally, the control device is further connected to a light source controller. The light source controller is connected to a first light source, a second light source and a third light source. The first light source, the second light source and the third light source are respectively arranged in a matching manner with the first camera, the second camera and the third camera.

[0012] Optionally, the turning device is a bent pipe.

[0013] The present invention also provides an automatic sorting method for stamping gaskets based on machine vision, which is applied to the above-mentioned automatic sorting device for stamping gaskets based on machine vision, and includes the following steps:

[0014] S1. Based on the images of the gaskets collected by at least one of the first camera and the second camera, determine whether the gasket is face up or face down;

[0015] S2. If it is face up, control the first separation device to seal conveyor belt four, and the gasket flows from conveyor belt two into conveyor three and reaches conveyor belt five;

[0016] S3. If it is face down, control the first separation device to seal conveyor belt three, and the gasket flows from conveyor belt two into conveyor belt four, and after being turned over by the turning device, it reaches conveyor belt five.

[0017] Optionally, the method further includes:

[0018] S4. Based on the images of the gaskets collected by the third camera, perform detection on the turned-over state of the gaskets, specifically including:

[0019] S401. Determine whether the gasket is face up or face down;

[0020] S402. If it is face up, control the second separation device to seal conveyor belt six, and the gasket flows out from conveyor belt five;

[0021] S403. If it is face down, control the second separation device to seal conveyor belt five, and the gasket flows from conveyor belt five into conveyor belt six, and then through conveyor belt one and back to conveyor belt two, and repeat steps S1 - S4.

[0022] Optionally, in step S1, based on the images of the gaskets collected by at least one of the first camera and the second camera, determine whether the gasket is face up or face down, specifically including:

[0023] Perform gray-scale processing on the images of the gaskets, set a gray-scale value threshold, extract the regions within the gray-scale value range, calculate the area of this region, and set an area threshold. If the area of the region is greater than the area threshold, it is the front side, otherwise it is the back side.

[0024] According to the specific embodiments provided by the present invention, the following technical effects are disclosed: The automatic sorting device and method for stamping gaskets based on machine vision provided by the present invention can collect pictures of the inner and outer hole cylindrical surfaces of stamping gaskets through an inclined conveyor belt or a camera, perform image processing, extract features, and identify the front and back sides. The method is simple and the recognition accuracy is high; the classification and transmission of gaskets with the front side up and the back side up can be realized through a separating device, and gaskets with the back side up can be quickly screened out; the gaskets with the back side up can be turned over through a turning device, and a bent pipe structure can be used to turn over the back gaskets. The principle is simple. The gaskets will automatically turn over by relying on the gravity factor when passing through the pipeline, without the need for additional electric or pneumatic devices, with low cost and simple structure; finally, a third camera is set to continuously monitor the placement state of the gaskets, which can further screen whether there are still gaskets with the back side up, thereby improving the accuracy of recognition and sorting and ensuring that the output gaskets are all in the required placement state. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0026] Figure 1 Structural schematic diagram of the automatic sorting device for stamping gaskets based on machine vision in the embodiment of the present invention;

[0027] Figure 2 Schematic diagram of the working principle of the automatic sorting device for stamping gaskets based on machine vision in the embodiment of the present invention;

[0028] Figure 3 Structural schematic diagram of the separating device in the embodiment of the present invention;

[0029] Figure 4 Structural schematic diagram of the turning device in the embodiment of the present invention;

[0030] Figure 5 Structural schematic diagram of the gasket in the embodiment of the present invention;

[0031] Figure 6 Schematic diagram of the imaging principle of the third camera in the embodiment of the present invention;

[0032] Description of reference numerals: 1, the first conveyor belt; 2, the second conveyor belt; 3, the third conveyor belt; 4, the fourth conveyor belt; 5, the fifth conveyor belt; 6, the sixth conveyor belt; 7, the first light source; 8, the first camera; 9, the second light source; 10, the second camera; 11, the control device; 12, the light source controller; 13, the first separating device; 14, the turning device; 15, the third camera; 16, the third light source; 17, the second separating device. Detailed implementation manners

[0033] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0034] The object of the present invention is to provide an automatic sorting device and method for stamping gaskets based on machine vision, which has a simple structure and a high level of automatic control. It can cyclically identify the placement state of gaskets, timely screen out gaskets with the reverse side up, perform turning adjustments, has a high recognition accuracy, and a good effect of automatic sorting of gaskets.

[0035] To make the above objects, features, and advantages of the present invention more obvious and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific implementation manners.

[0036] As Figure 1 - Figure 2 shown, the automatic sorting device for stamping gaskets based on machine vision provided by the present invention includes a control device 11, a conveyor belt assembly, a first separating device 13, and a turning device 14. The conveyor belt assembly includes a second conveyor belt 2, a third conveyor belt, and a fifth conveyor belt 5 that are connected in sequence. One end of the second conveyor belt 2 connected to the third conveyor belt 3 is also connected to a fourth conveyor belt. The first separating device 13 is arranged at one end where the third conveyor belt, the fourth conveyor belt, and the second conveyor belt are commonly connected, and is used to send gaskets with the front side up and the reverse side up to the third conveyor belt 3 and the fourth conveyor belt 4 respectively. The turning device 14 is arranged between the fourth conveyor belt 4 and the fifth conveyor belt 5 and is used to perform a turning operation on the gaskets.

[0037] A second camera 10 is arranged above the second conveyor belt 2 and is used to collect images of the gaskets and transmit them to the control device 11. The control device 11 is electrically connected to the first separating device 13, and the control device 11 controls the first separating device 13 to act, sending the gaskets with the reverse side up to the fourth conveyor belt 4, and after being turned over by the turning device 14, sending them to the fifth conveyor belt 5.

[0038] The automatic sorting device for stamping gaskets based on machine vision further includes a third camera 15 disposed above the conveyor belt five 5 and a second separating device 17 disposed at the end of the conveyor belt five 5. The third camera 15 and the second separating device 17 are electrically connected to the controller respectively. The end of the conveyor belt five 5 is connected to a conveyor belt six 6. The controller controls the second separating device 17 to act to send the gaskets with the reverse side facing up to the conveyor belt six 6.

[0039] The conveyor belt assembly further includes a first conveyor belt. The first conveyor belt 1 is connected to the second conveyor belt 2. The first conveyor belt 1 is used to convey the gaskets to the second conveyor belt 2. A first camera 8 is disposed above the first conveyor belt. The first conveyor belt 1 is inclined. The first camera 8 is vertically downward. The second conveyor belt 2 is horizontally disposed. The second camera 10 is inclined. The first camera 8 and the second camera 10 are connected to the control device 11 and are used to collect the inner and outer hole cylinder images of the gaskets from different angles respectively. The conveyor belt six 6 is connected to the first conveyor belt 1 and is used to send the gaskets with the reverse side facing up back to the second conveyor belt 2.

[0040] Both the first separating device 13 and the second separating device 17 include an electrically controlled rotating shaft and a baffle. One end of the baffle is fixedly connected to the electrically controlled rotating shaft and rotates within a set angle around the axis of the electrically controlled rotating shaft.

[0041] The control device 11 is further connected to a light source controller 12. The light source controller 12 is connected to a first light source 7, a second light source 9 and a third light source 16. The first light source 7, the second light source 9 and the third light source 16 are respectively arranged in a matching manner with the first camera 8, the second camera 10 and the third camera 15.

[0042] As shown in the figure, the turning device 14 is a bent pipe. The bent pipe is vertically placed or inclined in the vertical direction to facilitate the sliding of the gaskets.

[0043] The automatic sorting device for stamping gaskets based on machine vision provided by the present invention can collect the pictures of the inner and outer hole cylinder surfaces of the stamping gaskets through an inclined conveyor belt or a camera, perform image processing, extract features and identify the front and back sides. The method is simple and the recognition accuracy is high. The classification transmission of the gaskets with the front side facing up and the gaskets with the reverse side facing up can be realized through the separating device, and the gaskets with the reverse side facing up can be quickly screened out. The gaskets with the reverse side facing up can be turned over through the turning device. A bent pipe structure can be used to turn over the reverse gaskets. The principle is simple. The gaskets will automatically turn over by relying on the gravity factor when passing through the pipe, without the need for additional electric or pneumatic devices, with low cost and simple structure. Finally, a third camera is set to continuously monitor the placement state of the gaskets, which can further screen whether there are still gaskets with the reverse side facing up, thereby improving the accuracy of recognition and sorting and ensuring that the output gaskets are all in the required placement state.

[0044] The present invention also provides an automatic sorting method for stamping gaskets based on machine vision, which is applied to the above-mentioned automatic sorting device for stamping gaskets based on machine vision, and includes the following steps:

[0045] S1. Based on the images of the gaskets collected by at least one of the first camera and the second camera, determine whether the gasket is face up or face down;

[0046] S2. If it is face up, control the first separation device to seal conveyor belt four, and the gasket flows from conveyor belt two into conveyor three and reaches conveyor belt five;

[0047] S3. If it is face down, control the first separation device to seal conveyor belt three, and the gasket flows from conveyor belt two into conveyor belt four, and after being turned over by the turning device, it reaches conveyor belt five.

[0048] Optionally, the method further includes:

[0049] S4. Based on the images of the gaskets collected by the third camera, perform detection on the turned-over state of the gaskets, specifically including:

[0050] S401. Determine whether the gasket is face up or face down;

[0051] S402. If it is face up, control the second separation device to seal conveyor belt six, and the gasket flows out from conveyor belt five;

[0052] S403. If it is face down, control the second separation device to seal conveyor belt five, and the gasket flows from conveyor belt five into conveyor belt six, and then through conveyor belt one and back to conveyor belt two, and repeat steps S1 - S4.

[0053] Among them, in step S1, based on the images of the gaskets collected by at least one of the first camera and the second camera, determine whether the gasket is face up or face down, specifically including:

[0054] Perform grayscale processing on the images of the gaskets, set the grayscale value threshold, extract the regions within the grayscale value range, calculate the area of this region, and set the area threshold. If the area of the region is greater than the area threshold, it is the front side, otherwise it is the back side.

[0055] Among them, by tilting the conveyor belt or the camera, the first camera and the second camera are combined to take pictures of the inner and outer hole cylindrical surfaces of the gasket, and the pictures are processed. It can be seen that there is an obvious difference in the color depth on the left and right sides of the inner diameter. This is because due to the impact of the stamping process, there is a folded surface near the front side, and there is no folded surface on the back side, as Figure 5 shown.

[0056] As Figure 6As shown in the figure, for the inclined arrangement of the camera, the relationships such as the height of the camera and the tilt angle of the camera are described. In the figure, the tilt angle θ of the camera, the thickness of the folded layer area formed by the stamping process is a, and the thickness of the gasket is a + b.

[0057] Adjust the angle θ so that the axis of the camera lens falls between points A and B of the gasket;

[0058] Adjust the height h and the distance x so that the field of view includes the area between A and D.

[0059] To make the folded area clearly imaged and facilitate subsequent image processing, the relationship between the height and the tilt angle of the camera is:

[0060] θ = arctan(h - b) / x

[0061] x

[0062] Generally, the angle θ is preferably between 30 and 60 degrees.

[0063] This is a schematic diagram for measuring the folded layer of the inner cylindrical surface, and the folded layer of the outer cylindrical surface is similar.

[0064] This method is to take pictures of the gasket through a conveyor belt passing by the camera, and the data is transmitted to the computer. The computer analyzes the characteristics of the inner hole cylindrical surface or the outer cylindrical surface to realize the classification of the front and back sides of the gasket. After the computer finishes processing the data, it controls the baffle to achieve the classification of the front and back sides, reaches the turning device to realize automatic turning, and is sent onto the conveyor belt again. At this time, the turning of the gasket has been realized, and the next process can be carried out. This invention solves the problems of consuming human resources, taking a long time, and having low artificial work efficiency.

[0065] In this article, specific examples are used to elaborate on the principle and implementation mode of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation mode and application scope. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. An automatic sorting device for stamping gaskets based on machine vision, characterized in that, Including: A control device, a conveyor belt assembly, a first separating device, and a turning device. The conveyor belt assembly includes conveyor belt two, conveyor belt three, and conveyor belt five connected in sequence. One end where conveyor belt two is connected to conveyor belt three is also connected to conveyor belt four. The first separating device is arranged at one end where conveyor belt three, conveyor belt four, and conveyor belt two are commonly connected, and is used to separately send gaskets with the front side facing up and the back side facing up to conveyor belt three and conveyor belt four. The turning device is arranged between conveyor belt four and conveyor belt five and is used to perform a turning operation on the gaskets. A second camera is arranged above conveyor belt two and is used to collect images of the gaskets and transmit them to the control device. The control device is electrically connected to the first separating device. The control device controls the first separating device to act, sends the gaskets with the back side facing up to conveyor belt four, and after being turned over by the turning device, sends them to conveyor belt five. The turning device is a bent pipe. The bent pipe is placed vertically or obliquely in the vertical direction. The automatic sorting device for stamping gaskets based on machine vision further includes a third camera arranged above conveyor belt five and a second separating device arranged at the end of conveyor belt five. The third camera and the second separating device are respectively electrically connected to the controller. The end of conveyor belt five is connected to conveyor belt six. The controller controls the second separating device to act and is used to send the gaskets with the back side facing up to conveyor belt six. The conveyor belt assembly further includes conveyor belt one. Conveyor belt one is connected to conveyor belt two and is used to convey gaskets to conveyor belt two. A first camera is arranged above conveyor belt one. Conveyor belt one is arranged obliquely, and the first camera is arranged vertically downward. Conveyor belt two is arranged horizontally, and the second camera is arranged obliquely. The first camera and the second camera are connected to the control device and are used to collect inner and outer hole cylindrical surface images of the gaskets from different angles respectively. Conveyor belt six is connected to conveyor belt one and is used to send the gaskets with the back side facing up back to conveyor belt two. In the inner and outer hole cylindrical surface images of the gaskets, the folding surface on the front side of the gaskets makes the color depths on the left and right sides of the inner diameter of the front side and the back side have obvious differences. Among them, the automatic sorting device determines whether the gasket is facing up or facing down based on the images of the gaskets collected by at least one of the first camera and the second camera. Specifically, it includes: Performing gray-scale processing on the images of the gaskets, setting a gray-scale value threshold, extracting the area within the gray-scale value range, calculating the area of this area, and setting an area threshold. If the area of the area is greater than the area threshold, it is the front side, otherwise it is the back side. Both the first separating device and the second separating device include an electric control rotating shaft and a baffle. One end of the baffle is fixedly connected to the electric control rotating shaft and rotates within a set angle around the axis of the electric control rotating shaft.

2. The automatic sorting device for stamping gaskets based on machine vision according to claim 1, wherein The control device is also connected to a light source controller. The light source controller is connected to a first light source, a second light source, and a third light source. The first light source, the second light source, and the third light source are respectively arranged in a matching manner with the first camera, the second camera, and the third camera.

3. An automatic sorting method for stamping gaskets based on machine vision, characterized in that, Applied to the automatic sorting device for stamping gaskets based on machine vision according to any one of claims 1-2, the method includes the following steps: S1. Based on the images of the gaskets collected by at least one of the first camera and the second camera, determine whether the gasket is face up or face down. S2. If it is face up, control the first separating device to seal conveyor belt four, and the gasket flows from conveyor belt two into conveyor belt three and reaches conveyor belt five. S3. If it is face down, control the first separating device to seal conveyor belt three, and the gasket flows from conveyor belt two into conveyor belt four, is turned over by the turning device, and then reaches conveyor belt five.

4. The automatic sorting method of stamping gaskets based on machine vision according to claim 3, wherein The method further includes: S4. Based on the images of the gaskets collected by the third camera, perform detection on the turning state of the gaskets, specifically including: S401. Determine whether the gasket is face up or face down. S402. If it is face up, control the second separating device to seal conveyor belt six, and the gasket flows out from conveyor belt five. S403. If it is face down, control the second separating device to seal conveyor belt five, and the gasket flows from conveyor belt five into conveyor belt six, passes through conveyor belt one, and flows back to conveyor belt two, and repeat steps S1-S4.

5. The automatic sorting method of stamping gaskets based on machine vision according to claim 3, wherein In step S1, based on the images of the gaskets collected by at least one of the first camera and the second camera, determine whether the gasket is face up or face down, specifically including: Perform grayscale processing on the images of the gaskets, set the grayscale value threshold, extract the area within the grayscale value range, calculate the area of this area, and set the area threshold. If the area of the area is greater than the area threshold, it is face up, otherwise it is face down.

Images