A deburring process feedback optimization system and method based on automation

Abstract

The invention discloses a deburring process feedback optimization system and method based on automation, which belongs to the field of automation. The invention comprises the following steps: S1, before burr treatment of a die-casting to be treated, an image is collected, grayscale processing is performed on the acquired image, contour data of the die-casting in the image is extracted and scale normalized; S2, standard contour data of the die-casting to be treated is analyzed, and contour features of the burrs of the die-casting to be treated are obtained by comparing the contour data of the die-casting to be treated, and initial parameters of the equipment are set; S3, the effect of burr treatment is predicted according to the real-time contour data of the die-casting and the working parameters of the current equipment, and the working parameters of the equipment are adjusted according to the predicted effect; the invention analyzes the image data of the die-casting, and in the deburring process, the burr removal effect is detected in real time to adjust the working parameters of the equipment, thereby improving the deburring efficiency and the quality of the product.

Description

Technical Field

[0001] The present invention relates to the field of automation, and in particular to a deburring process feedback optimization system and method based on automation. Background Art

[0002] The main principle of physical deburring is to remove the burrs on the surface of the material by cutting. Cutting is to cut the burrs on the surface of the material longitudinally or transversely. The cutting force of the tool will turn the burrs into tiny chips. As the cutting of the material surface continues to move, the burrs are completely removed.

[0003] However, the traditional physical deburring method only analyzes the final result of deburring, and ignores the real-time detection of burr removal during the deburring process to adjust the working parameters of the equipment. As a result, the burr removal is incomplete or excessive, affecting the deburring efficiency and product quality.

[0004] Therefore, people are in urgent need of an automated deburring process feedback optimization system to solve the above problems. Summary of the invention

[0005] The object of the present invention is to provide a deburring process feedback optimization system based on automation to solve the problems raised in the above background technology.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] A deburring process feedback optimization method based on automation, the method comprising the following steps:

[0008] S1. Before the die-casting to be processed is subjected to burr removal, an image of the die-casting to be processed is collected; at the same time, a historical image of the die-casting of the same type as the die-casting to be processed after burr removal is collected, and the die-casting of the same type meets the deburring standard; the acquired image is gray-processed, and the contour data of the die-casting in the image is extracted and scale normalized;

[0009] S2. Analyze the standard contour data of the die-casting of this type after deburring based on the historical contour data, compare the contour data of the die-casting to be processed with the standard contour data, analyze the contour features of the burrs of the die-casting to be processed, and set the initial parameters of the equipment based on the contour features of the burrs of the die-casting to be processed;

[0010] S3. Perform burr treatment on die-castings according to the initial parameters of the equipment, and collect real-time image data of burr treatment on die-castings during the operation of the equipment, perform grayscale processing on the acquired real-time image data, extract the real-time contour data of the die-castings in the image and perform scale normalization, predict the effect of burr treatment according to the real-time contour data of the die-castings and the working parameters of the current equipment, and adjust the working parameters of the equipment according to the predicted effect.

[0011] According to the above technical solution, in step S1, an image of the die casting to be processed is collected; at the same time, a historical image of the die casting of the same type as the die casting to be processed after burrs are removed is collected; and the acquired image is processed, and the specific process is as follows:

[0012] S2-1. Before the die casting to be processed is subjected to burr removal, an image of the die casting to be processed is collected, and according to the specifications of the collected image of the die casting to be processed, α die castings of the same type as the die casting to be processed that meet the deburring standard are collected, and the historical images after deburring are collected, wherein α is a fixed parameter preset by the system;

[0013] S2-2, grayscale processing is performed on the acquired α+1 images using image recognition technology, and the contour of the die-casting in the image is extracted according to the same sampling density, to obtain α contour point sets with n coordinate points and 1 contour point set with m coordinate points, wherein n represents the total number of coordinate points in the contour point set of the historical image after deburring of the die-casting of the same type as the die-casting to be processed; m represents the total number of coordinate points in the contour point set of the image of the die-casting to be processed;

[0014] The contour point set with m coordinate points is recorded as point set A, and the contours in the image are extracted using image recognition technology. At this time, the algorithm will return a contour list. Each contour is composed of a series of points. The same sampling density is to make the number of coordinate points in each contour point set correspond to each other. All contour point sets are scaled normalized. Scale normalization is a common image processing technology used to adjust the size of objects in the image to a uniform standard size. In contour feature processing, scale normalization can ensure that contours of different sizes have similar sizes, making them easier to compare and analyze.

[0015] According to the above technical solution, in step S2, the contour characteristics of the burrs of the die casting to be processed are analyzed, and the specific process is as follows:

[0016] S3-1. For α die-castings that meet the deburring standard and are of the same type as the die-casting to be processed, the contour point set of the deburred historical image is contour aligned, and the average coordinate value corresponding to each coordinate point in each contour point set is calculated according to the following formula:

[0017]

[0018] Among them, (x i ,y i ) represents the average coordinate value corresponding to the i-th coordinate point, x i Represents the average horizontal coordinate value corresponding to the i-th coordinate point, y i represents the average ordinate value corresponding to the i-th coordinate point, (x j，i ,y j，i ) represents the coordinate value of the i-th coordinate point of the j-th contour point set, x j，i Represents the horizontal coordinate value of the i-th coordinate point of the j-th contour point set, y j，i Represents the ordinate value of the i-th coordinate point of the j-th contour point set, i∈[1,n], j∈[1,α];

[0019] According to the above calculation, the standard contour point set of this type of die casting is obtained and recorded as point set B;

[0020] S3-2, performing contour alignment on point set A and point set B. The contour alignment is to align multiple contour point sets using translation or rotation transformation, the purpose of which is to facilitate the subsequent analysis. The coordinate points in the point sets after contour alignment are matched and analyzed according to the minimum distance matching algorithm to obtain point set C and point set D, wherein the coordinate points in point set C are the coordinate points that point set A has but point set B does not have, and the coordinate points in point set D are the coordinate points that point set A does not have but point set B has;

[0021] S3-3, record the first coordinate point in point set C as coordinate point O, record the last coordinate point in point set C as coordinate point P, record the coordinate point with the largest ordinate value in point set C as coordinate point Q, and record the coordinate point in point set D whose abscissa value differs the least from that of coordinate point Q as coordinate point R;

[0022] Coordinate point O and coordinate point P, calculate the width of the burr of the die casting to be processed according to the following formula:

[0023] W=|x O -x P |

[0024] Where W represents the width of the burr of the die casting to be processed, x O Indicates the horizontal coordinate value of the coordinate point O, x P Indicates the horizontal coordinate value of coordinate point P;

[0025] Coordinate point Q and coordinate point R, calculate the length of the burr of the die casting to be processed according to the following formula:

[0026] L=|y Q -y R |

[0027] Where, L represents the length of the burr of the die casting to be processed, y Q Indicates the ordinate value of the coordinate point Q, y R Represents the ordinate value of coordinate point R.

[0028] According to the above technical solution, in step S2, the initial parameters of the equipment are set according to the contour characteristics of the burrs of the die casting to be processed. The specific process is as follows:

[0029] The speed and time of the initial operation of the device are set according to W. The initial speed and initial operation time of the device satisfy v0·t0≥W, where v0 represents the initial speed of the device and t0 represents the initial operation time of the device;

[0030] According to L, the adjustment distance of the initial operation of the equipment is set, and the adjustment distance of the equipment meets Wherein, l0 represents the initial distance of the equipment adjustment, γ is a fixed parameter preset by the system, and γ represents the number of times the equipment is adjusted. The adjustment distance means that the equipment does not remove the burrs at one time, but first removes them multiple times from the position of half the burr length. This not only gives the equipment adjustment space, but also reduces the burrs caused by the equipment deburring, thereby increasing the quality of the product.

[0031] According to the above technical solution, in step S3, the effect of burr processing according to the current device parameters is predicted, and the specific process is as follows:

[0032] S5-1, collecting real-time image data of burr processing of die castings, gray-processing the acquired real-time image data, and extracting the contour of the die casting in the image according to the same sampling density as point set A, obtaining the real-time contour point set of the die casting as point set E, and aligning the contours of point set E with point set A;

[0033] S5-2, after contour alignment, the coordinate points in the point set E and the point set A are matched and analyzed according to the minimum distance matching algorithm to obtain the point set F, wherein the coordinate points in the point set F are the coordinate points in the point set E but not in the point set A, and the change trends of the ordinate values ​​of the coordinate points in the point set F in the direction of equipment operation are compared;

[0034] If the ordinate value changes stably in the interval [y'-δ, y'+δ], the device continues to operate according to the current working parameters, and the burr processing is predicted to meet the standard, where y' represents the average value of the ordinate values ​​of the coordinate points in the device running direction in the set F, and δ is a fixed parameter preset by the system;

[0035] If the ordinate value gradually decreases, the device continues to operate according to the current working parameters, and the burr treatment is predicted to be excessive;

[0036] If the vertical axis value gradually increases, and the operation continues according to the current working parameters of the equipment, it is predicted that the burr treatment is not clean.

[0037] According to the above technical solution, in step S3, the equipment parameters are adjusted according to the prediction results. The specific process is as follows:

[0038] S6-1. When the burr processing is predicted to be excessive, the first coordinate point in the point set F in the direction of the equipment is recorded as coordinate point F1, and the last coordinate point in the point set F in the direction of the equipment is recorded as coordinate point F2. The adjustment angle of the equipment is calculated according to the following formula:

[0039]

[0040] Wherein, θ represents the adjustment angle of the device, x1 represents the abscissa value of coordinate point F1, y1 represents the ordinate value of coordinate point F1, x2 represents the abscissa value of coordinate point F2, y2 represents the ordinate value of coordinate point F2;

[0041] According to θ, the running direction of the equipment is rotated by θ with F1 as the origin in the direction of increasing ordinate value, and then the equipment is run;

[0042] S6-2. When it is predicted that the burr treatment is not clean, the first coordinate point in the point set F in the direction of the equipment is recorded as coordinate point F1', and the last coordinate point in the point set F in the direction of the equipment is recorded as coordinate point F2'. The adjustment angle of the equipment is calculated according to the following formula:

[0043]

[0044] Wherein, θ' represents the adjustment angle of the device, x1' represents the abscissa value of the coordinate point F1', y1' represents the ordinate value of the coordinate point F1', x2' represents the abscissa value of the coordinate point F2', y2' represents the ordinate value of the coordinate point F2';

[0045] According to θ', the running direction of the equipment is rotated by θ' with F1' as the origin in the direction of decreasing ordinate value, and then the equipment is run.

[0046] A deburring process feedback optimization system based on automation, the system comprises an information acquisition module, an information processing module and an execution module;

[0047] The information acquisition module is used to acquire various information required by the system; the information processing module is used to store, analyze and transmit various information of each module; and the execution module is used to execute various information of the information processing module.

[0048] According to the above technical solution, the information acquisition module includes a die casting information unit and an equipment information unit;

[0049] The die-casting information unit is used to collect data information of the die-casting, and the equipment information unit is used to collect data information of the equipment.

[0050] According to the above technical solution, the information processing module includes an information storage unit, an information analysis unit and an information transmission unit;

[0051] The information storage unit is used to store various information acquired by the information acquisition module; the information analysis unit is used to analyze various information acquired by the information acquisition module; and the information transmission unit is used for information transmission among various modules in the system.

[0052] According to the above technical solution, the execution module includes a device adjustment unit and a display unit;

[0053] The device adjustment unit is used to perform device adjustment according to the adjustment control information sent by the information processing unit, and the display unit is used to display data information and burr processing information of the device.

[0054] Compared with the prior art, the beneficial effects achieved by the present invention are:

[0055] The present invention analyzes the image data before and after the burr treatment of the die casting, sets the initial working parameters of the equipment, makes a real-time prediction of the burr removal effect during the deburring process, and adjusts the working parameters of the equipment accordingly based on the prediction, thereby improving the deburring efficiency and product quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0057] Figure 1 It is a flow chart of a deburring process feedback optimization method based on automation of the present invention;

[0058] Figure 2 It is a structural schematic diagram of an automated deburring process feedback optimization system of the present invention. DETAILED DESCRIPTION

[0059] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0060] See also Figure 1 , the present invention provides a technical solution:

[0061] A deburring process feedback optimization method based on automation, the method comprising the following steps:

[0062] S1. Before the die-casting to be processed is subjected to burr removal, an image of the die-casting to be processed is collected; at the same time, a historical image of the die-casting of the same type as the die-casting to be processed after burr removal is collected, and the die-casting of the same type meets the deburring standard; the acquired image is gray-processed, and the contour data of the die-casting in the image is extracted and scale normalized;

[0063] In step S1, an image of the die casting to be processed is collected; at the same time, a historical image of the die casting of the same type as the die casting to be processed after burrs are removed is collected; and the acquired image is processed, and the specific process is as follows:

[0064] S2-1. Before the die casting to be processed is subjected to burr removal, an image of the die casting to be processed is collected, and according to the specifications of the collected image of the die casting to be processed, α die castings of the same type as the die casting to be processed that meet the deburring standard are collected, and the historical images after deburring are collected, wherein α is a fixed parameter preset by the system;

[0065] S2-2, grayscale processing is performed on the acquired α+1 images using image recognition technology, and the contour of the die-casting in the image is extracted according to the same sampling density, to obtain α contour point sets with n coordinate points and 1 contour point set with m coordinate points, wherein n represents the total number of coordinate points in the contour point set of the historical image after deburring of the die-casting of the same type as the die-casting to be processed; m represents the total number of coordinate points in the contour point set of the image of the die-casting to be processed;

[0066] The contour point set with m coordinate points is recorded as point set A, and the contours in the image are extracted using image recognition technology. At this time, the algorithm will return a contour list. Each contour is composed of a series of points. The same sampling density is to make the number of coordinate points in each contour point set correspond to each other. All contour point sets are scaled normalized. Scale normalization is a common image processing technology used to adjust the size of objects in the image to a uniform standard size. In contour feature processing, scale normalization can ensure that contours of different sizes have similar sizes, making them easier to compare and analyze.

[0067] S2. Analyze the standard contour data of the die-casting of this type after deburring based on the historical contour data, compare the contour data of the die-casting to be processed with the standard contour data, analyze the contour features of the burrs of the die-casting to be processed, and set the initial parameters of the equipment based on the contour features of the burrs of the die-casting to be processed;

[0068] In step S2, the contour features of the burrs of the die casting to be processed are analyzed, and the specific process is as follows:

[0069] S3-1. For α die-castings that meet the deburring standard and are of the same type as the die-casting to be processed, the contour point set of the deburred historical image is contour aligned, and the average coordinate value corresponding to each coordinate point in each contour point set is calculated according to the following formula:

[0070]

[0071] Among them, (x i ,y i ) represents the average coordinate value corresponding to the i-th coordinate point, x i Represents the average horizontal coordinate value corresponding to the i-th coordinate point, y i represents the average ordinate value corresponding to the i-th coordinate point, (x j，i ,y j，i ) represents the coordinate value of the i-th coordinate point of the j-th contour point set, x j，i Represents the horizontal coordinate value of the i-th coordinate point of the j-th contour point set, y j，i Represents the ordinate value of the i-th coordinate point of the j-th contour point set, i∈[1,n], j∈[1,α];

[0072] According to the above calculation, the standard contour point set of this type of die casting is obtained and recorded as point set B;

[0073] S3-2, performing contour alignment on point set A and point set B. The contour alignment is to align multiple contour point sets using translation or rotation transformation, the purpose of which is to facilitate the subsequent analysis. The coordinate points in the point sets after contour alignment are matched and analyzed according to the minimum distance matching algorithm to obtain point set C and point set D, wherein the coordinate points in point set C are the coordinate points that point set A has but point set B does not have, and the coordinate points in point set D are the coordinate points that point set A does not have but point set B has;

[0074] The point set C is the contour data of the burr of the die casting to be processed;

[0075] S3-3, record the first coordinate point in point set C as coordinate point O, record the last coordinate point in point set C as coordinate point P, record the coordinate point with the largest ordinate value in point set C as coordinate point Q, and record the coordinate point in point set D whose abscissa value differs the least from that of coordinate point Q as coordinate point R;

[0076] Coordinate point O and coordinate point P, calculate the width of the burr of the die casting to be processed according to the following formula:

[0077] W=|x O -x P |

[0078] Where W represents the width of the burr of the die casting to be processed, x O Indicates the horizontal coordinate value of the coordinate point O, x P Indicates the horizontal coordinate value of coordinate point P;

[0079] Coordinate point Q and coordinate point R, calculate the length of the burr of the die casting to be processed according to the following formula:

[0080] L=|y Q -y R |

[0081] Where, L represents the length of the burr of the die casting to be processed, y Q Indicates the ordinate value of the coordinate point Q, y R Represents the ordinate value of coordinate point R;

[0082] The width and length of the burr are both the maximum values ​​of the burr of the die casting to be processed.

[0083] Further, in step S2, the initial parameters of the equipment are set according to the contour characteristics of the burrs of the die casting to be processed. The specific process is as follows:

[0084] The speed and time of the initial operation of the device are set according to W. The initial speed and initial operation time of the device satisfy v0·t0≥W, where v0 represents the initial speed of the device and t0 represents the initial operation time of the device;

[0085] According to L, the adjustment distance of the initial operation of the equipment is set, and the adjustment distance of the equipment meets Wherein, l0 represents the initial distance of the equipment adjustment, γ is a fixed parameter preset by the system, and γ represents the number of times the equipment is adjusted. The adjustment distance means that the equipment does not remove the burrs at one time, but first removes them multiple times from the position of half the burr length. This not only gives the equipment adjustment space, but also reduces the burrs caused by the equipment deburring, thereby increasing the quality of the product.

[0086] S3. Perform burr treatment on die castings according to the initial parameters of the equipment, and collect real-time image data of burr treatment on die castings during the operation of the equipment, perform grayscale processing on the acquired real-time image data, extract real-time contour data of the die castings in the image and normalize the scale, predict the effect of burr treatment according to the real-time contour data of the die castings and the working parameters of the current equipment, and adjust the working parameters of the equipment according to the predicted effect;

[0087] In step S3, the effect of burr processing according to the current device parameters is predicted, and the specific process is as follows:

[0088] S5-1, collecting real-time image data of burr processing of die castings, gray-processing the acquired real-time image data, and extracting the contour of the die casting in the image according to the same sampling density as point set A, obtaining the real-time contour point set of the die casting as point set E, and aligning the contours of point set E with point set A;

[0089] S5-2, after contour alignment, the coordinate points in the point set E and the point set A are matched and analyzed according to the minimum distance matching algorithm to obtain the point set F, wherein the coordinate points in the point set F are the coordinate points in the point set E but not in the point set A, and the change trends of the ordinate values ​​of the coordinate points in the point set F in the direction of equipment operation are compared;

[0090] If the ordinate value changes stably in the interval [y'-δ, y'+δ], the equipment continues to run according to the current working parameters, and it is predicted that the burr treatment meets the standard, where y' represents the average value of the ordinate values ​​of the coordinate points in the equipment running direction in set F, and δ is a fixed parameter preset by the system, indicating that the burr treatment continues in the direction of the equipment running at this time, and the contour of the die casting will eventually fit the standard contour after the burr treatment is completed;

[0091] If the ordinate value gradually decreases, the current equipment continues to run according to the working parameters, and the burr treatment is predicted to be excessive, which means that the burr treatment will continue according to the direction of the equipment operation at this time. Eventually, after the burr treatment is completed, the part of the die casting that was not originally a burr will be processed, resulting in unqualified products;

[0092] If the vertical axis value gradually increases, and the operation continues according to the current working parameters of the equipment, it is predicted that the burr treatment is not clean.

[0093] In step S3, the equipment parameters are adjusted according to the prediction results. The specific process is as follows:

[0094] S6-1. When the burr processing is predicted to be excessive, the first coordinate point in the point set F in the direction of the equipment is recorded as coordinate point F1, and the last coordinate point in the point set F in the direction of the equipment is recorded as coordinate point F2. The adjustment angle of the equipment is calculated according to the following formula:

[0095]

[0096] Wherein, θ represents the adjustment angle of the device, x1 represents the abscissa value of coordinate point F1, y1 represents the ordinate value of coordinate point F1, x2 represents the abscissa value of coordinate point F2, y2 represents the ordinate value of coordinate point F2;

[0097] According to θ, the running direction of the equipment is rotated by θ with F1 as the origin in the direction of increasing ordinate value, and then the equipment is operated. Such adjustment is to reduce the processing degree, so that the burr processing meets the standard and the product is qualified;

[0098] S6-2. When it is predicted that the burr treatment is not clean, the first coordinate point in the point set F in the direction of the equipment is recorded as coordinate point F1', and the last coordinate point in the point set F in the direction of the equipment is recorded as coordinate point F2'. The adjustment angle of the equipment is calculated according to the following formula:

[0099]

[0100] Wherein, θ' represents the adjustment angle of the device, x1' represents the abscissa value of the coordinate point F1', y1' represents the ordinate value of the coordinate point F1', x2' represents the abscissa value of the coordinate point F2', y2' represents the ordinate value of the coordinate point F2';

[0101] According to θ', the running direction of the equipment is rotated by θ' with F1' as the origin in the direction of decreasing vertical coordinate value, and then the equipment is operated. Such adjustment increases the processing degree so that the burr processing meets the standard.

[0102] See also Figure 2 , a deburring process feedback optimization system based on automation, the system includes an information acquisition module, an information processing module and an execution module;

[0103] The information collection module is used to collect various information required by the system;

[0104] The information acquisition module includes a die casting information unit and an equipment information unit;

[0105] The die-casting information unit is used to collect data information of the die-casting, and the equipment information unit is used to collect data information of the equipment.

[0106] The information processing module is used to store, analyze and transmit various information of each module;

[0107] The information processing module includes an information storage unit, an information analysis unit and an information transmission unit;

[0108] The information storage unit is used to store various information acquired by the information acquisition module; the information analysis unit is used to analyze various information acquired by the information acquisition module; and the information transmission unit is used for information transmission among various modules in the system.

[0109] The execution module is used to execute various information of the information processing module;

[0110] According to the above technical solution, the execution module includes a device adjustment unit and a display unit;

[0111] The device adjustment unit is used to perform device adjustment according to the adjustment control information sent by the information processing unit, and the display unit is used to display data information and burr processing information of the device.

[0112] Example:

[0113] The existing equipment using this system needs to process a certain type of die castings. The width W = 10 and the length L = 20 of the burr of the die casting to be processed have been obtained. The initial running speed of the equipment is set to v0 = 5 and the time t0 = 2, satisfying v0·t0≥W. The adjustment distance of the initial running of the equipment is

[0114] The real-time image data of die casting burr treatment is collected and processed to obtain the point set F. The change trend of the ordinate values ​​of the coordinate points in the equipment running direction in the point set F is that the ordinate values ​​gradually decrease. The first coordinate point in the equipment running direction in the point set F is recorded as coordinate point F1 (x1=0, y1=0), and the last coordinate point in the equipment running direction in the point set F is recorded as coordinate point F2 (x2=1, y2=1). The adjustment angle of the equipment is calculated:

[0115]

[0116] According to θ, the running direction of the equipment is rotated by θ=45° with F1 as the origin in the direction of increasing vertical coordinate value, and then the equipment is run.

[0117] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0118] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A deburring process feedback optimization method based on automation, characterized in that: The method comprises the following steps: S1. Before the die-casting to be processed is subjected to burr removal, an image of the die-casting to be processed is collected; at the same time, a historical image of the die-casting of the same type as the die-casting to be processed after burr removal is collected, and the die-casting of the same type meets the deburring standard; the acquired image is gray-processed, and the contour data of the die-casting in the image is extracted and scale normalized; S2. Analyze the standard contour data of the same type of die-castings according to the historical contour data after deburring, compare the contour data of the die-casting to be processed with the standard contour data, analyze the contour features of the burrs of the die-casting to be processed, and set the initial parameters of the equipment according to the contour features of the burrs of the die-casting to be processed; S3. Perform burr treatment on die castings according to the initial parameters of the equipment, and collect real-time image data of burr treatment on die castings during the operation of the equipment, perform grayscale processing on the acquired real-time image data, extract real-time contour data of the die castings in the image and perform scale normalization, predict the effect of burr treatment according to the real-time contour data of the die castings and the working parameters of the current equipment, and adjust the working parameters of the equipment according to the predicted effect; In step S3, the effect of burr processing according to the current device parameters is predicted, and the specific process is as follows: S5-1, collecting real-time image data of burr processing of die castings, gray-processing the acquired real-time image data, and extracting the contour of the die casting in the image according to the same sampling density as point set A, obtaining the real-time contour point set of the die casting as point set E, and aligning the contours of point set E with point set A; S5-2, after contour alignment, the coordinate points in the point set E and the point set A are matched and analyzed according to the minimum distance matching algorithm to obtain the point set F, wherein the coordinate points in the point set F are the coordinate points in the point set E but not in the point set A, and the change trends of the ordinate values ​​of the coordinate points in the point set F in the direction of equipment operation are compared; If the vertical coordinate value is in the interval Stable changes, continue to operate according to the current working parameters of the equipment, and predict that the burr treatment will meet the standards, among which, It represents the average value of the ordinate values ​​of the coordinate points in the point set F in the direction of equipment operation. It is a fixed parameter preset by the system; If the ordinate value gradually decreases, the device continues to operate according to the current working parameters, and the burr treatment is predicted to be excessive; If the ordinate value gradually increases, the burr treatment is predicted to be unclean according to the current equipment operating parameters and continue to operate; In step S3, the equipment parameters are adjusted according to the prediction results. The specific process is as follows: S6-1. When the burr processing is predicted to be excessive, the first coordinate point in the point set F in the direction of equipment operation is recorded as the coordinate point , record the last coordinate point in the point set F in the direction of equipment operation as the coordinate point , according to formula (1), calculate the adjustment angle of the device: （1）； in, Indicates the adjustment angle of the device. Indicates coordinate points The horizontal axis value of The coordinate point The vertical coordinate value of Indicates coordinate points The horizontal axis value of The coordinate point The vertical coordinate value of according to , change the running direction of the equipment to Rotate the origin in the direction of increasing ordinate value Then run the device; S6-2. When the burr processing is not clean, the first coordinate point in the point set F in the direction of equipment operation is recorded as the coordinate point , record the last coordinate point in the point set F in the direction of equipment operation as the coordinate point , according to formula (2), calculate the adjustment angle of the device: （2）； in, Indicates the adjustment angle of the device. Indicates coordinate points The horizontal axis value of The coordinate point The vertical coordinate value of Indicates coordinate points The horizontal axis value of The coordinate point The vertical coordinate value of according to , change the running direction of the equipment to Rotate the origin in the direction of decreasing ordinate value Then run the device.

2. The deburring process feedback optimization method based on automation according to claim 1, characterized in that: In step S1, an image of the die casting to be processed is collected; at the same time, a historical image of the die casting of the same type as the die casting to be processed after burrs are removed is collected; and the acquired image is gray-processed. The specific process is as follows: S2-1. Before the die casting to be processed is subjected to burr treatment, an image of the die casting to be processed is collected, and according to the specifications of the collected image of the die casting to be processed, A historical image of a die casting of the same type as the die casting to be processed after deburring that meets the deburring standard; S2-2. Obtain The images are processed in grayscale using image recognition technology, and the contours of the die castings in the images are extracted according to the same sampling density to obtain a contour point set with n coordinate points and a contour point set with m coordinate points, wherein n represents the total number of coordinate points in the contour point set of the historical image after deburring of the die casting of the same type as the die casting to be processed; m represents the total number of coordinate points in the contour point set of the image of the die casting to be processed; The contour point set with m coordinate points is recorded as point set A, and all contour point sets are scaled normalized.

3. The deburring process feedback optimization method based on automation according to claim 2, characterized in that: In step S2, the contour features of the burrs of the die casting to be processed are analyzed, and the specific process is as follows: S3-1. Targeting The contour point sets of the deburred historical images of the same type of die castings that meet the deburring standards are aligned, and the average coordinate values ​​corresponding to the coordinate points in each contour point set are calculated according to formula (3): （3）； in, represents the average coordinate value corresponding to the i-th coordinate point, represents the average horizontal coordinate value corresponding to the i-th coordinate point, represents the average ordinate value corresponding to the i-th coordinate point, Represents the coordinate value of the i-th coordinate point of the j-th contour point set, Represents the horizontal coordinate value of the i-th coordinate point of the j-th contour point set, Represents the ordinate value of the i-th coordinate point in the j-th contour point set, i∈[1,n], j∈[1, ]; According to the above calculation, the standard contour point set of the same type of die casting is obtained and recorded as point set B; S3-2, aligning the contours of point set A and point set B, and performing matching analysis on the coordinate points in the point sets after contour alignment according to the minimum distance matching algorithm to obtain point set C and point set D, wherein the coordinate points in point set C are the coordinate points that point set A has but point set B does not have, and the coordinate points in point set D are the coordinate points that point set A does not have but point set B has; S3-3, record the first coordinate point in point set C as coordinate point O, record the last coordinate point in point set C as coordinate point P, record the coordinate point with the largest ordinate value in point set C as coordinate point Q, and record the coordinate point in point set D whose abscissa value differs the least from that of coordinate point Q as coordinate point R; Coordinate point O and coordinate point P, calculate the width of the burr of the die casting to be processed according to formula (4): （4）； Wherein, W represents the width of the burr of the die casting to be processed, represents the horizontal coordinate value of the coordinate point O, Indicates the horizontal coordinate value of coordinate point P; Coordinate point Q and coordinate point R, calculate the length of the burr of the die casting to be processed according to formula (5): （5）； Wherein, L represents the length of the burr of the die casting to be processed, Indicates the ordinate value of coordinate point Q, Represents the ordinate value of coordinate point R.

4. The deburring process feedback optimization method based on automation according to claim 3, characterized in that: In step S2, the initial parameters of the equipment are set according to the contour characteristics of the burrs of the die casting to be processed. The specific process is as follows: Set the initial running speed and time of the equipment according to W, and the initial speed and initial running time of the equipment meet ,in, Indicates the initial speed of the device. Indicates the initial operation time of the device; According to L, the adjustment distance of the initial operation of the equipment is set, and the adjustment distance of the equipment meets ,in, Indicates the initial distance of the device adjustment. Indicates the number of times the device has been adjusted.

Images