A machine vision-based mechanical hand polishing and grinding switching system

Abstract

The present application relates to the technical field of polishing and grinding, in particular to a mechanical hand polishing and grinding switching system based on machine vision, comprising: a rack; a horizontal moving unit; a vertical moving unit; a switching mechanical hand unit; polishing units and grinding units symmetrically arranged on both sides of the rack; a data acquisition module for obtaining texture information of each sub-area and curvature values of surfaces of each sub-area; a control module for determining, under the condition that polishing of the workpiece does not meet the preset standard according to the texture direction representation value obtained according to the data texture direction and the texture quantity, the surface curvature change value obtained according to the curvature value for secondary determination, or determining, under the condition that polishing of the workpiece does not meet the preset standard according to the surface peak and valley value obtained according to the height value, the reason why polishing of the workpiece does not meet the preset standard and determining, under the condition that polishing of the workpiece does not meet the preset standard according to the glossiness of the workpiece, the control module for determining to increase the polishing time length or the grinding pressure according to the gray scale characteristic value, thereby improving the polishing and grinding effect.

Description

Technical Field

[0001] This invention relates to the field of polishing technology, and more particularly to a robotic arm polishing and grinding adapter system based on machine vision. Background Technology

[0002] Polishing and grinding robots are automated robots specifically designed for surface treatment. They possess a high degree of autonomy and precision, enabling them to polish and grind various material surfaces. This improves surface treatment efficiency, reduces manual labor intensity, enhances the working environment, and achieves more precise and consistent surface treatment results.

[0003] Grinding and polishing are important processing techniques in industrial manufacturing. Grinding refers to the process of increasing the surface roughness of a workpiece to obtain patterns or remove burrs, while polishing refers to the process of decreasing the surface roughness of a workpiece to obtain a bright and smooth surface. The equipment for grinding and polishing is basically the same. The difference is that grinding uses a grinding wheel to contact the workpiece surface, while polishing uses a polishing wheel. Both use a high-speed rotating grinding wheel or polishing wheel to press against the workpiece. The abrasive on the surface of the grinding wheel or polishing wheel produces rolling and micro-cutting on the workpiece surface, thereby obtaining a patterned, deburred, or bright processed surface.

[0004] However, existing robotic polishing and grinding systems still face some technical bottlenecks. For example, most systems lack precise workpiece recognition and positioning capabilities, resulting in insufficient polishing and grinding accuracy and making it difficult to meet high-quality product requirements. Furthermore, some systems lack sufficient flexibility and adaptability when handling workpieces with complex shapes and materials, limiting their application scope.

[0005] Chinese Patent Publication No. CN114029818A discloses a flexible grinding equipment for industrial robots based on machine vision, relating to the field of grinding equipment technology. The equipment includes a robotic arm with a slide base fixed to its bottom surface. A slide table is provided on the bottom surface of the slide base, and the slide table is movably connected to the slide base. A power unit at one end of the robotic arm is equipped with a connector replacement device. The connector replacement device includes a housing, inside which is an inner housing. An A motor is bolted to the top surface of the housing. A bevel gear is fixed to the rotating end of the A motor and the surface of the inner housing. A connecting rod is provided inside a mounting column on the inner wall of the inner housing. One end of each of the three connecting rods is equipped with a polishing head, a deburring head, and a scanning head. A limiting plate on the top surface of the connecting rod is welded to the top surface of the connecting rod. A cylinder is fixed to the top surface of the housing, and a pressure plate is fixed to the telescopic end of the cylinder. This device integrates grinding, polishing, and deburring functions. Multiple connectors can be automatically replaced according to the user's needs. Using standard parts as a reference, the device improves the processing accuracy of the workpiece and increases the processing qualification rate.

[0006] It can be seen that the above technical solution does not consider the influence of the workpiece surface shape on the polishing accuracy, nor does it consider the influence of grinding rate, polishing pressure and polishing time on the workpiece processing quality, thus resulting in poor polishing effect. Summary of the Invention

[0007] To address this issue, the present invention provides a robotic polishing and grinding transfer system based on machine vision, which overcomes the problem in the prior art that does not consider the influence of the workpiece surface shape on the polishing and grinding accuracy, nor does it consider the influence of grinding rate, polishing pressure and polishing time on the workpiece processing quality, thus resulting in poor polishing and grinding effects.

[0008] To achieve the above objectives, the present invention provides a machine vision-based robotic arm polishing and grinding adapter system, comprising:

[0009] The system comprises a frame, a lateral movement unit, a longitudinal movement unit, a transfer robot unit, a polishing unit, a grinding unit, a data acquisition module, and a control module.

[0010] A lateral movement unit is disposed on one side of the top of the frame to drive the longitudinal movement unit to move laterally;

[0011] A longitudinal movement unit, which is connected to the lateral movement unit, is used to drive the transfer robot unit to move longitudinally and to fix the vision sensor.

[0012] A transfer robot unit, which is connected to the longitudinal movement unit, is used for the transfer and transport of workpieces;

[0013] The polishing unit and the grinding unit are symmetrically arranged on both sides of the frame. The grinding unit is equipped with a grinding wheel, and the polishing unit is equipped with a polishing wheel.

[0014] The data acquisition module is connected to the vision sensor and is used to divide the workpiece surface image acquired by the vision sensor into several sub-regions, acquire the texture information and curvature value of each sub-region, and the texture information includes texture direction, texture quantity, gray value and surface contour height value.

[0015] The control module, which is connected to the data acquisition module, the horizontal movement unit, the vertical movement unit, the transfer robot unit, the polishing unit, and the grinding unit, is used to determine whether the grinding of the workpiece does not meet the preset standard based on the texture direction characterization value obtained from the texture direction and texture quantity, and to make a secondary judgment based on the surface curvature change value obtained from the curvature value; or, to determine the reason why the grinding of the workpiece does not meet the preset standard based on the surface peak and valley value obtained from the height value; and to determine whether to increase the polishing time or increase the grinding pressure based on the grayscale feature value when the polishing of the workpiece does not meet the preset standard based on the gloss of the workpiece.

[0016] Furthermore, the lateral movement unit includes a first guide rail, a moving block sleeved on the first guide rail, and a mounting plate vertically disposed on the side of the moving block, with guide constraint grooves evenly distributed on both sides of the edge of the mounting plate.

[0017] Furthermore, the longitudinal moving unit is slidably connected to the mounting plate via a guide constraint groove. The longitudinal moving unit includes a second guide rail, a mounting base, a hollow rotary table, a vision sensor, a connecting arm, a rotating shaft, and a mounting bracket. The side of the second guide rail away from the guide constraint groove is connected to the mounting base. A hollow rotary table is provided above the mounting base, and a vision sensor is installed inside the hollow rotary table. One end of the connecting arm is connected to the side wall of the hollow rotary table, and the other end of the connecting arm is connected to the rotating shaft. A mounting bracket is provided above the rotating shaft. The longitudinal moving direction of the second guide rail and the lateral moving direction of the first guide rail are perpendicular to each other.

[0018] Furthermore, the transfer robot unit, which is connected to the mounting frame by bolts, includes a first robot arm assembly, a second robot arm assembly, and a third robot arm assembly;

[0019] The first robotic arm assembly includes a first groove seat, a lead screw, a lead screw nut, a first motor for driving the lead screw, a guide sliding groove, a guide rail, a connecting block, and a bearing seat. The bearing seats are symmetrically installed at both ends of the bottom of the first groove, and the two ends of the lead screw are respectively connected to the bearing seats. The lead screw drives the connecting block to move by rotating the lead screw nut. The guide rail is set at both ends of the bearing seats, and the guide sliding grooves are symmetrically arranged on both sides of the inner wall of the first groove seat.

[0020] The second robotic arm assembly includes a timing belt, a second groove seat, linear guide rails, and a limiting sliding groove. The side wall of the second groove seat slides into the guide sliding groove, and the bottom of the second groove seat is connected to a lead screw nut. Linear guide rails are symmetrically arranged at the bottom of the second groove seat, and timing belts are arranged between the linear guide rails.

[0021] Furthermore, the third robotic arm assembly includes a belt, a second motor for driving the belt to rotate, a one-way bearing, a transfer suction cup, a locking block, a drive block, and a third groove seat. The locking block is located at the bottom of the third groove seat, and the synchronous belt drives the third groove seat to move through the locking block. The drive blocks are symmetrically located at the bottom of the third groove seat. A belt is installed inside the third groove seat. One end of the belt is connected to the second motor, and the other end of the belt is connected to the transfer suction cup through the one-way bearing.

[0022] Furthermore, the control module determines that the workpiece grinding does not meet the preset standard if the texture direction characterization value is less than the second preset texture direction characterization value.

[0023] And, under the condition that the texture direction characterization value is less than the first preset texture direction characterization value, determine the reason why the workpiece grinding does not meet the preset standard based on the surface peak and valley values.

[0024] And under the condition that the texture direction characterization value is greater than or equal to the first preset texture direction characterization value and less than the second preset texture direction characterization value, the surface curvature change value is used to determine whether the grinding of the workpiece meets the preset standard for the second time.

[0025] The texture direction representation value is determined by the texture direction and texture quantity collected by the data acquisition module.

[0026] Furthermore, the control module determines the reason why the workpiece grinding does not meet the preset standard based on the surface peak and valley values: the grinding rate of the grinding wheel is too high and reduces the grinding rate of the grinding wheel, or the grinding wheel is worn and issues a warning.

[0027] The surface peak and valley values ​​are determined by the vertical distance between the maximum profile peak and the maximum profile valley within the sub-region.

[0028] Furthermore, the control module further determines the grinding wheel feed rate based on the comparison result of the surface curvature change value being greater than or equal to the preset surface curvature change value.

[0029] The surface curvature change value is the maximum value among the surface curvature differences between adjacent sub-regions after polishing.

[0030] Furthermore, the control module determines whether the polishing of the workpiece meets the preset standard based on the workpiece's gloss level.

[0031] If the gloss level is less than the first preset gloss level, it is determined that the polishing of the workpiece does not meet the preset standard, and the polishing pressure of the polishing wheel is increased according to the difference between the first preset gloss level and the gloss level.

[0032] If the gloss is greater than or equal to the first preset gloss and less than the second preset gloss, the polishing of the workpiece is determined to be non-compliant with the preset standard, and the adjustment strategy under the condition that the polishing of the workpiece is non-compliant with the preset standard is determined based on the grayscale characteristic value.

[0033] If the gloss is greater than or equal to the second preset gloss, the polishing of the workpiece is determined to meet the preset standard.

[0034] The gloss level is determined by the grayscale value of the sub-region surface.

[0035] Furthermore, the control module determines adjustment strategies based on grayscale feature values ​​when the polishing of the workpiece does not meet the preset standards, including: increasing the polishing time, or increasing the grinding pressure;

[0036] The grayscale feature value is the ratio between the number of sub-regions whose grayscale mean is less than or equal to a preset grayscale mean and the total number of sub-regions.

[0037] Compared with the prior art, the beneficial effects of the present invention are as follows: The present invention achieves precise positioning and rapid transfer of workpieces through the coordinated control of the lateral and longitudinal movement units, combined with the design of screw drive, synchronous belt transmission, and belt transmission of the first, second, and third robotic arms; the symmetrical arrangement of the grinding and polishing units, in conjunction with the multi-degree-of-freedom motion of the transfer robot, adapts to the grinding and polishing of different workpiece surfaces, enhancing the system's adaptability; the nested design of the first, second, and third robotic arms improves system stability; a vision sensor is installed inside the hollow rotary table to collect real-time data on the texture direction, peak and valley values, and surface curvature changes of the workpiece surface, improving the level of intelligent processing; the grinding effect of the workpiece is inspected based on the texture direction characterization value and surface curvature change value; the polishing effect of the workpiece is inspected based on the gloss and grayscale characteristic values, thereby improving the grinding and polishing effect of the transfer system.

[0038] Furthermore, this invention uses texture direction characterization values ​​to determine the reason why the workpiece's polishing does not meet the preset standard when a secondary judgment is made, thereby avoiding the accidental error of a single detection and improving the reliability of the evaluation results.

[0039] Furthermore, the present invention determines the reasons why the workpiece grinding does not meet the preset standard by the surface peak and valley values, including excessive grinding speed of the grinding wheel or wear of the grinding wheel, thereby improving grinding efficiency.

[0040] Furthermore, the present invention reduces the grinding pressure of the grinding wheel by the difference between the surface curvature change value and the preset surface curvature change value, thereby achieving precise control over the reduction of grinding pressure.

[0041] Furthermore, this invention determines whether the polishing of a workpiece meets a preset standard by measuring the workpiece's gloss. By setting the workpiece's gloss as an evaluation index for whether the polishing of a workpiece meets the preset standard, the accuracy of the evaluation and improvement of polishing quality is enhanced.

[0042] Furthermore, the present invention determines the adjustment strategy under the condition that the polishing of the workpiece does not meet the preset standard by determining the grayscale feature value, including increasing the polishing time or increasing the grinding pressure, thereby optimizing the grinding and polishing process parameters. Attached Figure Description

[0043] Figure 1 This is a schematic diagram of the structure of the robotic arm polishing and grinding transfer system based on machine vision according to an embodiment of the present invention;

[0044] Figure 2This is a schematic diagram of the lateral movement unit of the robotic arm polishing and grinding transfer system based on machine vision according to an embodiment of the present invention;

[0045] Figure 3 This is a schematic diagram of the longitudinal moving unit of the robotic arm polishing and grinding transfer system based on machine vision according to an embodiment of the present invention;

[0046] Figure 4 This is an exploded structural diagram of the first robotic arm component of the machine vision-based robotic arm polishing and grinding transfer system according to an embodiment of the present invention.

[0047] Figure 5 This is an exploded structural diagram of the second robotic arm component of the machine vision-based robotic arm polishing and grinding transfer system according to an embodiment of the present invention.

[0048] Figure 6 This is an exploded structural diagram of the third robotic arm component of the machine vision-based robotic arm polishing and grinding transfer system according to an embodiment of the present invention.

[0049] Figure 7 This is an exploded structural diagram of the transfer robot unit of the machine vision-based robotic polishing and grinding transfer system according to an embodiment of the present invention.

[0050] Figure 8 This is a schematic diagram of the module connection of the robotic arm polishing and grinding conversion system based on machine vision according to an embodiment of the present invention;

[0051] Figure 9 This is a flowchart illustrating how the grinding of a workpiece conforms to a preset standard based on texture direction characterization values, according to an embodiment of the present invention.

[0052] In the diagram, 1. Frame; 2. Lateral movement unit; 3. Longitudinal movement unit; 4. Transfer robot unit; 5. Grinding unit; 6. Polishing unit; 51. Grinding wheel; 61. Polishing wheel; 21. First guide rail; 22. Moving block; 23. Mounting plate; 24. Guide constraint groove; 31. Second guide rail; 32. Mounting base; 33. Hollow rotary table; 34. Vision sensor; 35. Connecting arm; 36. Rotation axis; 37. Mounting bracket; 41. First robot arm assembly; 42. Second robot arm. Components; 43. Third robotic arm assembly; 411. First groove seat; 412. Lead screw; 413. Lead screw nut; 414. First motor; 415. Guide sliding groove; 416. Guide rail; 417. Connecting block; 418. Bearing seat; 421. Synchronous belt; 422. Second groove seat; 423. Linear guide rail; 424. Limiting sliding groove; 431. Belt; 432. Second motor; 434. Adapter suction cup; 435. Locking block; 436. Drive block; 437. Third groove seat. Detailed Implementation

[0053] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0054] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0055] It should be noted that the data in this embodiment are all derived from a comprehensive analysis and evaluation of historical test data and corresponding historical test results from the three months prior to this test. Those skilled in the art will understand that the determination of the above-mentioned parameters for any single item in this invention can be achieved by selecting the value with the highest percentage based on the data distribution as the preset standard parameter, using weighted summation to obtain the value as the preset standard parameter, substituting each historical data point into a specific formula and using the value obtained by that formula as the preset standard parameter, or other selection methods, as long as the method described in this invention can clearly define different specific situations in the single-item judgment process through the obtained values.

[0056] Please see Figure 1 , Figure 2 , Figure 3 , Figure 4 , Figure 5 , Figure 6 , Figure 7 , Figure 8 as well as Figure 9 The diagrams shown are, respectively, a structural schematic diagram of the machine vision-based robotic arm polishing and grinding transfer system of the present invention; a structural schematic diagram of the lateral movement unit of the machine vision-based robotic arm polishing and grinding transfer system of the present invention; a structural schematic diagram of the longitudinal movement unit of the machine vision-based robotic arm polishing and grinding transfer system of the present invention; an exploded structural schematic diagram of the first robotic arm assembly of the machine vision-based robotic arm polishing and grinding transfer system of the present invention; an exploded structural schematic diagram of the second robotic arm assembly of the machine vision-based robotic arm polishing and grinding transfer system of the present invention; an exploded structural schematic diagram of the third robotic arm assembly of the machine vision-based robotic arm polishing and grinding transfer system of the present invention; an exploded structural schematic diagram of the transfer robotic arm unit of the machine vision-based robotic arm polishing and grinding transfer system of the present invention; a module connection schematic diagram of the machine vision-based robotic arm polishing and grinding transfer system of the present invention; and a flowchart of the present invention for determining whether the grinding of the workpiece meets the preset standard based on the texture direction characterization value.

[0057] This invention provides a machine vision-based robotic arm polishing and grinding adapter system, comprising:

[0058] Please see Figure 1 As shown, the system comprises a frame 1, a horizontal movement unit 2, a vertical movement unit 3, a transfer robot unit 4, a polishing unit 6, a grinding unit 5, a data acquisition module, and a control module.

[0059] The lateral movement unit 2 is disposed on one side of the top of the frame 1 to drive the longitudinal movement unit 3 to move laterally;

[0060] The longitudinal movement unit 3 is connected to the lateral movement unit 2 to drive the transfer robot unit 4 to move longitudinally and to fix the vision sensor 34.

[0061] The transfer robot unit 4 is connected to the longitudinal moving unit 3 and is used for the transfer and transport of workpieces;

[0062] Polishing unit 6 and grinding unit 5 are symmetrically arranged on both sides of frame 1. Grinding unit 5 is equipped with grinding wheel 51, and polishing unit 6 is equipped with polishing wheel 61.

[0063] The data acquisition module is connected to the vision sensor 34 and is used to divide the workpiece surface image acquired by the vision sensor 34 into several sub-regions, acquire the texture information of each sub-region and the curvature value of the surface of each sub-region. The texture information includes texture direction, texture quantity, gray value and surface contour height value.

[0064] The control module, which is connected to the data acquisition module, the horizontal movement unit 2, the vertical movement unit 3, the transfer robot unit 4, the polishing unit 6, and the grinding unit 5, is used to determine whether the grinding of the workpiece does not meet the preset standard based on the texture direction characterization value obtained from the texture direction and texture quantity, and to make a secondary judgment based on the surface curvature change value obtained from the curvature value, or to determine the reason why the grinding of the workpiece does not meet the preset standard based on the surface peak and valley value obtained from the height value, and to determine whether to increase the polishing time or increase the grinding pressure based on the grayscale feature value when the polishing of the workpiece does not meet the preset standard based on the gloss of the workpiece.

[0065] Please see Figure 2 As shown, specifically, the lateral moving unit 2 includes a first guide rail 21, a moving block 22 sleeved on the first guide rail 21, and a mounting plate 23 vertically disposed on the side of the moving block 22. The mounting plate 23 moves along the length direction of the first guide rail 21 through the moving block 22, and guide constraint grooves 24 are evenly distributed on both sides of the edge of the mounting plate 23.

[0066] Please see Figure 3As shown, specifically, the longitudinal moving unit 3 is slidably connected to the mounting plate 23 via the guide constraint groove 24. The longitudinal moving unit 3 includes a second guide rail 31, a mounting base 32, a hollow rotary table 33, a vision sensor 34, a connecting arm 35, a rotating shaft 36, and a mounting bracket 37. The side of the second guide rail 31 away from the guide constraint groove 24 is connected to the mounting base 32. The hollow rotary table 33 is provided above the mounting base 32. The vision sensor 34 is installed inside the hollow rotary table 33. One end of the connecting arm 35 is connected to the side wall of the hollow rotary table 33, and the other end of the connecting arm 35 is connected to the rotating shaft 36. The mounting bracket 37 is provided above the rotating shaft 36. The longitudinal moving direction of the second guide rail 31 and the lateral moving direction of the first guide rail 21 are perpendicular to each other.

[0067] In this embodiment, the vision sensor 34 is selected as a 3D vision sensor 34. The specific sensor is not limited, as long as it meets the requirements for acquiring two-dimensional and three-dimensional images of the workpiece.

[0068] Please see Figure 7 As shown, specifically, the transfer robot unit 4 is connected to the mounting frame 37 by bolts, and includes a first robot arm assembly 41, a second robot arm assembly 42, and a third robot arm assembly 43;

[0069] Please see Figure 4 As shown, the first robotic arm assembly 41 includes a first groove seat 411, a lead screw 412, a lead screw 412 nut, a first motor 414 for driving the lead screw 412, a guide sliding groove 415, a guide rail 416, a connecting block 417, and a bearing seat 418. The bearing seats 418 are symmetrically installed at both ends of the bottom of the first groove. The two ends of the lead screw 412 are respectively connected to the bearing seats 418. The lead screw 412 drives the connecting block 417 to move by rotating the lead screw 412 nut. The connecting block 417 slides along the length direction of the guide rail 416. The guide rail 416 is set at both ends of the bearing seat 418. The guide sliding grooves 415 are symmetrically arranged on both sides of the inner wall of the first groove seat 411.

[0070] Please see Figure 5 As shown, the second robotic arm assembly 42 includes a timing belt 421, a second groove seat 422, a linear guide rail 423, and a limiting sliding groove 424, wherein...

[0071] The second groove seat 422 slides into the guide sliding groove 415 on its side wall. The bottom of the second groove seat 422 is connected to the lead screw 412 nut. Linear guide rails 423 are symmetrically arranged at the bottom of the second groove seat 422. Synchronous belts 421 are arranged between the linear guide rails 423.

[0072] Please see Figure 6As shown, specifically, the third robotic arm assembly 43 includes a belt 431, a second motor 432 for driving the belt 431 to rotate, a one-way bearing, a transfer suction cup 434, a locking block 435, a drive block 436, and a third groove seat 437. The locking block 435 is located at the bottom of the third groove seat 437. The synchronous belt 421 drives the third groove seat 437 to move through the locking block 435. The drive block 436 is symmetrically arranged at the bottom of the third groove seat 437 and slides along the length direction of the linear guide rail 423. The belt 431 is provided inside the third groove seat 437. One end of the belt 431 is connected to the second motor 432, and the other end of the belt 431 is connected to the transfer suction cup 434 through the one-way bearing.

[0073] Please see Figure 9 As shown, specifically, the control module determines whether the workpiece grinding meets the preset standard based on the texture direction characterization value.

[0074] If the texture direction characterization value is less than the first preset texture direction characterization value of 0.35, the workpiece is determined to meet the preset standard and the workpiece is transferred to the polishing unit 6.

[0075] If the texture direction characterization value is greater than or equal to the first preset texture direction characterization value and less than the second preset texture direction characterization value of 0.67, it is determined that the workpiece grinding does not meet the preset standard, and the workpiece grinding is further determined based on the surface curvature change value.

[0076] If the texture direction characterization value is greater than or equal to the second preset texture direction characterization value, it is determined that the workpiece grinding does not meet the preset standard, and the reason why the workpiece grinding does not meet the preset standard is determined based on the surface peak and valley values.

[0077] In this embodiment, the first preset texture direction characterization value is selected as 0.35 and the second preset texture direction characterization value is selected as 0.67, which are obtained based on the average value of historical detection data. However, the above values ​​are not limited to these values, and those skilled in the art can adjust the values ​​according to actual needs.

[0078] The process of obtaining the texture direction representation value includes:

[0079] Acquire a 2D image of the workpiece after grinding; process the 2D image using a directional filter to quantize the texture direction into several directional intervals; count the number of textures in each directional interval to form a histogram where the horizontal axis represents the texture direction and the vertical axis represents the number of textures in the corresponding direction;

[0080] Texture orientation representation values ​​are calculated using the following formula:

[0081]

[0082] In the formula, P represents the texture direction representation value; x i y represents the direction value at the midpoint of the i-th direction interval in the histogram; μ represents the weighted average of the median values ​​of the direction intervals; i This represents the ratio between the number of textures in the i-th directional interval and the total number of textures; n represents the total number of directional intervals; i = 1, 2, 3, ..., n.

[0083] The weighted average of the median values ​​in the direction interval is calculated using the following formula:

[0084]

[0085] In the formula, μ represents the weighted average of the median values ​​in the direction interval; x i f represents the direction value at the midpoint of the i-th direction interval in the histogram. i This represents the number of textures corresponding to the midpoint direction value of the i-th direction interval in the histogram, where n represents the total number of direction intervals.

[0086] Specifically, the control module determines the reason why the workpiece grinding does not meet the preset standard based on the surface peak and valley values.

[0087] If the surface peak value is less than the preset surface peak value, it is determined that the grinding speed of the grinding wheel 51 is too high, and the grinding speed of the grinding wheel 51 is reduced according to the difference between the preset surface peak value and the surface peak value.

[0088] If the surface peak-valley value is greater than or equal to the preset surface peak-valley value, the grinding wheel 51 is determined to be worn and an early warning is issued.

[0089] Specifically, the control module makes a secondary determination based on the surface curvature change value to determine whether the workpiece grinding meets the preset standard.

[0090] If the change in surface curvature is less than the preset change in surface curvature by 3mm -1 If the workpiece meets the preset standard, the workpiece is transferred to the polishing unit 6.

[0091] If the surface curvature change value is greater than or equal to the preset surface curvature change value, it is determined that the grinding of the workpiece does not meet the preset standard, and the feed rate of the grinding wheel 51 is reduced according to the difference between the surface curvature change value and the preset surface curvature change value.

[0092] The surface curvature change value is the maximum value among the surface curvature differences between adjacent sub-regions after polishing.

[0093] The 3D vision sensor 34 acquires images of the workpiece surface after grinding. The surface curvature of the ground sub-region is obtained through image processing software, such as ImageJ or Mountainsmap. The specific software is not limited, as long as it meets the curvature acquisition requirements.

[0094] In this embodiment, the preset surface curvature change value range is (2mm). -1 5mm -1 Preferably, the preset surface curvature change value is 3mm. -1 However, the above values ​​are not limited to these; they only need to meet the detection requirements.

[0095] Specifically, the control module determines whether the polishing of the workpiece meets preset standards based on the workpiece's gloss level.

[0096] If the gloss is less than the first preset gloss 60GU, it is determined that the polishing of the workpiece does not meet the preset standard, and the polishing pressure of the polishing wheel 61 is increased according to the difference between the first preset gloss and the gloss.

[0097] If the gloss is greater than or equal to the first preset gloss and less than the second preset gloss 80GU, the polishing of the workpiece is determined to be non-compliant with the preset standard, and the adjustment strategy under the condition that the polishing of the workpiece is non-compliant with the preset standard is determined based on the grayscale characteristic value.

[0098] If the gloss is greater than or equal to the second preset gloss, the polishing of the workpiece is determined to meet the preset standard.

[0099] The glossiness is the average grayscale value of all sub-region surfaces. The grayscale value is obtained through image processing software such as ImageJ. The specific type of image processing software is not limited, as long as it meets the requirement of grayscale value acquisition.

[0100] The increase in polishing pressure of polishing wheel 61 is positively correlated with the gloss difference. The positive correlation can be linear or nonlinear. The slope of the linear positive correlation is not specifically limited. It can be understood that the larger the gloss difference, the greater the increase in polishing pressure of polishing wheel 61. The gloss difference is the difference between a first preset gloss and a gloss level.

[0101] Specifically, the control module determines the adjustment strategy based on grayscale feature values ​​when the workpiece's polishing does not meet preset standards.

[0102] If the grayscale feature value is less than the preset grayscale threshold of 0.45, the polishing time is increased according to the difference between the preset grayscale threshold and the grayscale feature value.

[0103] If the grayscale feature value is greater than or equal to the preset grayscale threshold, the grinding pressure is increased according to the difference between the grayscale feature value and the preset grayscale threshold.

[0104] The grayscale feature value is the ratio between the number of sub-regions with a grayscale mean less than or equal to a preset grayscale mean of 135 and the total number of sub-regions.

[0105] The increase in polishing time of polishing wheel 61 is positively correlated with the difference between the preset grayscale threshold and the grayscale feature value. The positive correlation can be linear or nonlinear. The specific slope of the linear positive correlation is not limited. It can be understood that the greater the difference between the preset grayscale threshold and the grayscale feature value, the greater the increase in polishing pressure of polishing wheel 61.

[0106] The increase in grinding pressure of grinding wheel 51 is positively correlated with the difference between grayscale feature value and preset grayscale threshold. The positive correlation can be linear or nonlinear. The specific slope of the linear positive correlation is not limited. It can be understood that the greater the difference between the grayscale feature value and the preset grayscale threshold, the greater the increase in grinding pressure of grinding wheel 51.

[0107] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

[0108] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A robotic arm polishing and grinding transfer system based on machine vision, characterized in that, include: The system comprises a frame, a lateral movement unit, a longitudinal movement unit, a transfer robot unit, a polishing unit, a grinding unit, a data acquisition module, and a control module. A lateral movement unit is disposed on one side of the top of the frame to drive the longitudinal movement unit to move laterally; A longitudinal movement unit, which is connected to the lateral movement unit, is used to drive the transfer robot unit to move longitudinally and to fix the vision sensor. A transfer robot unit, which is connected to the longitudinal movement unit, is used for the transfer and transport of workpieces; The polishing unit and the grinding unit are symmetrically arranged on both sides of the frame. The grinding unit is equipped with a grinding wheel, and the polishing unit is equipped with a polishing wheel. The data acquisition module is connected to the vision sensor and is used to divide the workpiece surface image acquired by the vision sensor into several sub-regions, acquire the texture information of each sub-region and the curvature value of the surface of each sub-region. The texture information includes texture direction, texture quantity, gray value and surface contour height value. The control module, which is connected to the data acquisition module, the horizontal movement unit, the vertical movement unit, the transfer robot unit, the polishing unit, and the grinding unit, is used to determine whether the grinding of the workpiece does not meet the preset standard based on the texture direction characterization value obtained from the texture direction and texture quantity, and to make a secondary judgment based on the surface curvature change value obtained from the curvature value; or, to determine the reason why the grinding of the workpiece does not meet the preset standard based on the surface peak and valley value obtained from the height value; and to determine whether to increase the polishing time or increase the grinding pressure based on the grayscale feature value when the polishing of the workpiece does not meet the preset standard based on the gloss of the workpiece. The process of obtaining the texture direction representation value includes: Acquire a 2D image of the workpiece after grinding; process the 2D image using a directional filter to quantize the texture direction into several directional intervals; count the number of textures in each directional interval to form a histogram where the horizontal axis represents the texture direction and the vertical axis represents the number of textures in the corresponding direction; The texture direction representation value is calculated using the following formula: ； ； In the formula, P represents the texture direction representation value; x i y represents the direction value at the midpoint of the i-th direction interval in the histogram; μ represents the weighted average of the median values ​​of the direction intervals; i f represents the ratio between the number of textures in the i-th directional interval and the total number of textures; i This represents the number of textures corresponding to the midpoint direction value of the i-th direction interval in the histogram; n represents the total number of direction intervals; i = 1, 2, 3, ..., n.

2. The robotic arm polishing and grinding transfer system based on machine vision according to claim 1, characterized in that, The lateral movement unit includes a first guide rail, a moving block sleeved on the first guide rail, and a mounting plate vertically disposed on the side of the moving block. Guide constraint grooves are evenly distributed on both sides of the edge of the mounting plate.

3. The machine vision-based robotic polishing and grinding transfer system according to claim 2, characterized in that, The longitudinal moving unit is slidably connected to the mounting plate via a guide constraint groove. The longitudinal moving unit includes a second guide rail, a mounting base, a hollow rotary table, a vision sensor, a connecting arm, a rotating shaft, and a mounting bracket. The side of the second guide rail away from the guide constraint groove is connected to the mounting base. A hollow rotary table is provided above the mounting base, and a vision sensor is installed inside the hollow rotary table. One end of the connecting arm is connected to the side wall of the hollow rotary table, and the other end of the connecting arm is connected to the rotating shaft. A mounting bracket is provided above the rotating shaft. The longitudinal moving direction of the second guide rail and the lateral moving direction of the first guide rail are perpendicular to each other.

4. The machine vision-based robotic polishing and grinding transfer system according to claim 3, characterized in that, The transfer robot unit is connected to the mounting frame by bolts and includes a first robot arm assembly, a second robot arm assembly, and a third robot arm assembly. The first robotic arm assembly includes a first groove seat, a lead screw, a lead screw nut, a first motor for driving the lead screw, a guide sliding groove, a guide rail, a connecting block, and a bearing seat. The bearing seats are symmetrically installed at both ends of the bottom of the first groove, and the two ends of the lead screw are respectively connected to the bearing seats. The lead screw drives the connecting block to move by rotating the lead screw nut. The guide rail is set at both ends of the bearing seats, and the guide sliding grooves are symmetrically arranged on both sides of the inner wall of the first groove seat. The second robotic arm assembly includes a timing belt, a second groove seat, a linear guide rail, and a limiting sliding groove, wherein... The second groove seat slides into the guide groove on its side wall. The bottom of the second groove seat is connected to the lead screw nut. Linear guide rails are symmetrically arranged at the bottom of the second groove seat, and synchronous belts are arranged between the linear guide rails.

5. The machine vision-based robotic polishing and grinding transfer system according to claim 4, characterized in that, The third robotic arm assembly includes a belt, a second motor for driving the belt to rotate, a one-way bearing, a transfer suction cup, a locking block, a drive block, and a third groove seat. The locking block is located at the bottom of the third groove seat, and the synchronous belt drives the third groove seat to move through the locking block. The drive blocks are symmetrically arranged at the bottom of the third groove seat. A belt is installed inside the third groove seat. One end of the belt is connected to the second motor, and the other end of the belt is connected to the transfer suction cup through the one-way bearing.

6. The machine vision-based robotic polishing and grinding transfer system according to claim 5, characterized in that, The control module determines that the workpiece grinding does not meet the preset standard if the texture direction characterization value is less than the second preset texture direction characterization value. And, under the condition that the texture direction characterization value is less than the first preset texture direction characterization value, determine the reason why the workpiece grinding does not meet the preset standard based on the surface peak and valley values. And under the condition that the texture direction characterization value is greater than or equal to the first preset texture direction characterization value and less than the second preset texture direction characterization value, the surface curvature change value is used to determine whether the grinding of the workpiece meets the preset standard for the second time. The texture direction representation value is determined by the texture direction and texture quantity collected by the data acquisition module.

7. The machine vision-based robotic polishing and grinding transfer system according to claim 6, characterized in that, The control module determines the reason why the workpiece grinding does not meet the preset standard based on the surface peak and valley values. This is either because the grinding rate of the grinding wheel is too high or because the grinding wheel is worn, and it issues a warning. The surface peak and valley values ​​are determined by the vertical distance between the maximum profile peak and the maximum profile valley within the sub-region.

8. The machine vision-based robotic polishing and grinding transfer system according to claim 6, characterized in that, The control module determines the grinding wheel feed rate based on the comparison result of the surface curvature change value being greater than or equal to the preset surface curvature change value. If the workpiece grinding does not meet the preset standard, the control module will reduce the feed rate of the grinding wheel. The surface curvature change value is the maximum value among the surface curvature differences between adjacent sub-regions after polishing.

9. The machine vision-based robotic polishing and grinding transfer system according to claim 8, characterized in that, The control module determines whether the polishing of the workpiece meets the preset standard based on the workpiece's gloss level. If the gloss level is less than the first preset gloss level, it is determined that the polishing of the workpiece does not meet the preset standard, and the polishing pressure of the polishing wheel is increased according to the difference between the first preset gloss level and the gloss level. If the gloss is greater than or equal to the first preset gloss and less than the second preset gloss, the polishing of the workpiece is determined to be non-compliant with the preset standard, and the adjustment strategy under the condition that the polishing of the workpiece is non-compliant with the preset standard is determined based on the grayscale characteristic value. If the gloss is greater than or equal to the second preset gloss, the polishing of the workpiece is determined to meet the preset standard. The gloss level is determined by the grayscale value of the sub-region surface.

10. The machine vision-based robotic polishing and grinding transfer system according to claim 9, characterized in that, The control module determines adjustment strategies based on grayscale feature values ​​when the polishing of the workpiece does not meet the preset standards, including: increasing the polishing time, or increasing the grinding pressure; The grayscale feature value is the ratio between the number of sub-regions whose grayscale mean is less than or equal to a preset grayscale mean and the total number of sub-regions.

Images