A detection method and system for identifying surface defects of polishing grinding heads

By establishing the correspondence relationship between the types of polishing grinding head defects and polishing errors and the error superposition model, the problem of time-consuming and labor-intensive defect recognition in traditional methods is solved, and efficient and accurate detection of polishing grinding head defects is achieved.

CN118952041BActive Publication Date: 2025-03-21CHUANLING TECH (HUIZHOU) CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202410955714.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-17
Publication Date
2025-03-21
Estimated Expiration
2044-07-17

AI Technical Summary

Technical Problem

The traditional polishing head defect identification method consumes a lot of time and manpower, and has limited accuracy.

Method used

By obtaining defect sample images based on historical data, forming damage degree judgment indicators, establishing the correspondence between defect types and polishing errors, establishing a polishing error superposition model, identifying the surface defects of the polishing grinding head and calculating its comprehensive polishing errors.

Benefits of technology

Accurate identification of surface defects of polishing heads and comprehensive calculation of polishing errors is realized, which improves the accuracy of detection and reduces detection time and labor costs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118952041B_ABST
    Figure CN118952041B_ABST
Patent Text Reader

Abstract

The present invention discloses a detection method and system for surface defect identification after the polishing grinding head is manufactured, which relates to the field of polishing technology, including: forming a judgment index of the damage degree of the defect type; establishing a corresponding relationship between the damage degree of the defect type and the polishing error of the polishing grinding head; establishing a polishing error superposition model of the defect type; obtaining at least one surface defect of the polishing grinding head; obtaining the actual polishing error corresponding to the surface defect; obtaining the actual comprehensive polishing error of the polishing grinding head based on the polishing error superposition model of the defect type; judging whether the actual comprehensive polishing error is greater than the minimum allowable polishing error. By forming a judgment index of the damage degree of the defect type, establishing a corresponding relationship between the damage degree of the defect type and the polishing error of the polishing grinding head, and establishing a polishing error superposition model of the defect type, the accuracy of detection is improved, and the time and manpower consumed in detection are reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of polishing, and in particular to a detection method and system for identifying surface defects of a polishing grinding head after manufacture. Background Art

[0002] Polishing heads are important components used in polishing equipment, and are mainly used to polish workpieces to ensure a beautiful appearance. These polishing heads are usually prone to burrs, scratches, oxide films, scars, bubbles and other defects during the processing, which can easily affect the polishing effect.

[0003] The presence of surface defects in polishing heads can seriously affect the performance and reliability of polishing equipment. Therefore, early identification and accurate assessment of the extent of defects are essential for the use of polishing equipment. Traditional defect identification methods may require a lot of time and manpower, and have limited accuracy, so it is necessary to develop a more efficient and accurate defect identification method. Summary of the invention

[0004] In order to solve the above technical problems, a detection method and system for surface defect identification after polishing grinding head is manufactured are provided. This technical solution solves the problem that the traditional defect identification method proposed in the above background technology may require a lot of time and manpower and has limited accuracy.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] A detection method for identifying surface defects of a polishing grinding head after manufacture, comprising:

[0007] Based on the historical data, at least one defect type of the polishing grinding head is obtained, and a defect sample image set corresponding to the defect type is obtained, wherein the defect sample image set includes at least one defect sample image corresponding to the defect type;

[0008] Based on the defect sample image set, a judgment index of the damage degree of the defect type is formed;

[0009] Establish a corresponding relationship between the damage degree of the defect type and the polishing error of the polishing grinding head;

[0010] Establish polishing error superposition model of defect types;

[0011] Acquire a front surface image and a rear surface image of the polishing head after manufacture, analyze and compare the front surface image and the rear surface image, obtain at least one surface defect of the polishing head, and determine the position of the surface defect on the polishing head;

[0012] Based on at least one surface defect, obtaining an actual polishing error corresponding to the surface defect;

[0013] Based on the polishing error superposition model of defect types, the actual comprehensive polishing error of the polishing head is obtained;

[0014] Obtain the minimum allowable polishing error of the polishing head, and determine whether the actual comprehensive polishing error is greater than the minimum allowable polishing error. If so, the polishing head is unqualified, and the position of the surface defect on the polishing head is used as the position to be repaired. If not, the polishing head is qualified.

[0015] Preferably, the step of obtaining a defect sample image set corresponding to a defect type comprises the following steps:

[0016] Under the conditions of different damage degrees of defect types, defect sample images are obtained;

[0017] The defect sample images are matched one by one with the damage degree of the defect type.

[0018] Preferably, the judgment index of the damage degree of the defect type includes the following steps:

[0019] Obtaining a defect sample image corresponding to the damage degree of the defect type as a target defect sample image;

[0020] Calculate the mean of the pixel values ​​of the pixels in the target defect sample image to obtain the target pixel value;

[0021] Obtain a value range of a difference between a pixel value of a pixel point in a target defect sample image and a target pixel value as a floating range;

[0022] The target pixel value and the floating range are used as the judgment indexes of the damage degree of the defect type corresponding to the target defect sample image.

[0023] Preferably, establishing a corresponding relationship between the damage degree of the defect type and the polishing error of the polishing grinding head comprises the following steps:

[0024] Obtain an error polishing grinding head in which the existing defect is consistent with the defect type and the defect degree is consistent with the damage degree of the defect type;

[0025] Obtain qualified sample polishing grinding heads;

[0026] Use an error polishing grinding head to perform polishing operation to obtain an error polished surface;

[0027] Perform polishing operation using a sample polishing grinding head to obtain a sample polished surface;

[0028] The error polishing surface is compared with the sample polishing surface to obtain the polishing error of the error polishing grinding head;

[0029] The polishing error of the error polishing grinding head is matched with the damage degree of the defect type corresponding to the error polishing grinding head.

[0030] Preferably, the establishment of the polishing error superposition model of defect types comprises the following steps:

[0031] Obtain the number of at least one defect type as a characteristic value;

[0032] Randomly combining at least one defect type to obtain at least one defect combination, wherein the number of defect types in the defect combination is any number between 0 and the characteristic value;

[0033] Setting the damage degree of the defect type in the defect combination to a preset degree, and obtaining the polishing error corresponding to the defect type with the damage degree of the preset degree as the preset polishing error;

[0034] Acquire a characteristic polishing grinding head, wherein the characteristic polishing grinding head is satisfied with just including all defect types in the defect combination, and the damage degree of the defect types of the characteristic polishing grinding head is a preset degree;

[0035] Use a characteristic polishing grinding head to perform polishing operation to obtain a characteristic polished surface;

[0036] The characteristic polishing surface is compared with the sample polishing surface to obtain the polishing error of the characteristic polishing grinding head;

[0037] The polishing error corresponding to the damage degree of at least one defect type of the characteristic polishing grinding head is fitted with the polishing error of the characteristic polishing grinding head to obtain an error superposition fitting function, wherein the polishing error corresponding to the damage degree of at least one defect type of the characteristic polishing grinding head is an independent variable, and the polishing error of the characteristic polishing grinding head is a dependent variable.

[0038] Preferably, obtaining the front surface image and the rear surface image of the polishing grinding head after manufacture comprises the following steps:

[0039] Selecting a reference point on the manufactured polishing grinding head, and obtaining a tangent plane of the polishing grinding head at the reference point;

[0040] Obtain a normal line passing through the reference point, wherein the normal line is perpendicular to the cutting plane;

[0041] The part of the normal line located at the front side of the polishing grinding head after manufacture is used as the front photographic line;

[0042] The part of the normal line located at the rear side of the polishing grinding head after manufacture is used as the rear photographic line;

[0043] Acquire an image of the front side of the polishing grinding head after manufacture along the front photographic line as a front surface image;

[0044] An image of the rear side of the finished polishing grinding head is acquired along the rear photographic line as a rear surface image.

[0045] Preferably, analyzing and comparing the front surface image and the rear surface image to obtain at least one surface defect of the polishing grinding head comprises the following steps:

[0046] Pixel points are identified in both the front surface image and the back surface image, and the pixels whose difference from the target pixel value is less than the floating range are summarized as surface defects;

[0047] The defect type corresponding to the target pixel value is matched to the surface defect, and the damage degree of the defect type corresponding to the target pixel value is used as the damage degree of the surface defect.

[0048] Preferably, determining the position of the surface defect on the polishing head comprises the following steps:

[0049] Carry out three-dimensional coordinate modeling on the manufactured polishing grinding head, with the reference point being the coordinate origin;

[0050] Establishing a one-to-one correspondence between the pixel points in the front surface image and the rear surface image and the actual coordinates of the pixel points in the polishing grinding head after manufacture;

[0051] The center of the area where the surface defect is located in the front surface image and the back surface image is used as the positioning point of the surface defect;

[0052] The coordinates of the corresponding points of the positioning points on the manufactured polishing grinding head are obtained as the positions of the surface defects on the polishing grinding head.

[0053] Preferably, obtaining the actual polishing error corresponding to the surface defect based on at least one surface defect comprises the following steps:

[0054] Obtaining the damage degree of the defect type corresponding to the damage degree of the surface defect as the damage degree of the actual defect type;

[0055] Obtaining a polishing error corresponding to the damage degree of an actual defect type as an actual polishing error;

[0056] Based on the polishing error superposition model of defect types, obtaining the actual comprehensive polishing error of the polishing head includes the following steps:

[0057] The actual polishing error corresponding to at least one surface defect is substituted into the error superposition fitting function to obtain the actual comprehensive polishing error of the polishing grinding head.

[0058] A detection system for identifying surface defects of a polishing head after manufacture, used to implement the above-mentioned detection method for identifying surface defects of a polishing head after manufacture, comprising:

[0059] A data acquisition module, wherein the data acquisition module acquires at least one defect type of the polishing grinding head based on historical data, and acquires a defect sample image set corresponding to the defect type, wherein the defect sample image set includes at least one defect sample image corresponding to the defect type;

[0060] An index forming module, wherein the index forming module forms a judgment index of the damage degree of the defect type based on the defect sample image set;

[0061] A relationship building module, wherein the relationship building module establishes a corresponding relationship between the damage degree of the defect type and the polishing error of the polishing grinding head;

[0062] A model building module, wherein the model building module builds a polishing error superposition model of defect types;

[0063] A defect acquisition module, wherein the defect acquisition module acquires a front surface image and a rear surface image of the polishing head after manufacture, analyzes and compares the front surface image and the rear surface image, obtains at least one surface defect of the polishing head, and determines a position of the surface defect on the polishing head;

[0064] An error acquisition module, wherein the error acquisition module obtains an actual polishing error corresponding to the surface defect based on at least one surface defect, and obtains an actual comprehensive polishing error of the polishing grinding head based on a polishing error superposition model of defect types;

[0065] The identification and judgment module obtains the minimum allowable polishing error of the polishing grinding head and judges whether the actual comprehensive polishing error is greater than the minimum allowable polishing error.

[0066] Compared with the prior art, the present invention has the following beneficial effects:

[0067] By forming a judgment index of the damage degree of the defect type, establishing a corresponding relationship between the damage degree of the defect type and the polishing error of the polishing head, and establishing a polishing error superposition model of the defect type, various defects on the surface of the polishing head can be accurately identified, and by compounding the polishing errors caused by various defects, the actual comprehensive polishing error of the polishing head can be obtained, and then the qualification of the polishing head can be judged based on this, thereby avoiding misjudging the negligible defects of the polishing head as non-negligible defects, thereby improving the accuracy of detection. At the same time, the use of algorithms for identification can reduce the time and manpower consumed in detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1 It is a schematic flow chart of a detection method for identifying surface defects of a polishing grinding head after manufacture according to the present invention;

[0069] Figure 2A schematic diagram of a process of obtaining a defect sample image set corresponding to a defect type according to the present invention;

[0070] Figure 3 A schematic diagram of a flow chart of a judgment index of the degree of damage of a defect type according to the present invention;

[0071] Figure 4 It is a schematic diagram of a flow chart of establishing a corresponding relationship between the damage degree of defect type and the polishing error of the polishing grinding head according to the present invention;

[0072] Figure 5 A schematic diagram of a process for establishing a polishing error superposition model of defect types according to the present invention;

[0073] Figure 6 A schematic diagram of a process of obtaining a front surface image and a rear surface image of a polishing grinding head after manufacture according to the present invention;

[0074] Figure 7 A schematic diagram of a process of analyzing and comparing the front surface image and the rear surface image to obtain at least one surface defect of the polishing grinding head according to the present invention;

[0075] Figure 8 A schematic diagram of a process for determining the position of a surface defect on a polishing grinding head according to the present invention;

[0076] Fig. 9 The present invention is a flow chart of obtaining an actual polishing error corresponding to a surface defect based on at least one surface defect. DETAILED DESCRIPTION

[0077] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0078] Reference Figure 1 As shown, a detection method for identifying surface defects of a polishing grinding head after it is manufactured comprises:

[0079] Based on the historical data, at least one defect type of the polishing grinding head is obtained, and a defect sample image set corresponding to the defect type is obtained, wherein the defect sample image set includes at least one defect sample image corresponding to the defect type;

[0080] Based on the defect sample image set, a judgment index of the damage degree of the defect type is formed;

[0081] Establish a corresponding relationship between the damage degree of the defect type and the polishing error of the polishing grinding head;

[0082] Establish polishing error superposition model of defect types;

[0083] Acquire a front surface image and a rear surface image of the polishing head after manufacture, analyze and compare the front surface image and the rear surface image, obtain at least one surface defect of the polishing head, and determine the position of the surface defect on the polishing head;

[0084] Based on at least one surface defect, obtaining an actual polishing error corresponding to the surface defect;

[0085] Based on the polishing error superposition model of defect types, the actual comprehensive polishing error of the polishing head is obtained;

[0086] Obtain the minimum allowable polishing error of the polishing head, and determine whether the actual comprehensive polishing error is greater than the minimum allowable polishing error. If so, the polishing head is unqualified, and the position of the surface defect on the polishing head is used as the position to be repaired. If not, the polishing head is qualified.

[0087] Reference Figure 2 As shown, obtaining a defect sample image set corresponding to a defect type includes the following steps:

[0088] Under the conditions of different damage degrees of defect types, defect sample images are obtained;

[0089] The defect sample images are matched one by one with the damage degree of the defect type.

[0090] The defect sample image set includes defect sample images under different damage degrees of the defect type. Therefore, the defect image can be identified and the corresponding defect type can be determined. At the same time, the defect image of the same defect type can also be judged to determine its defect degree. Because different defect degrees have different effects on polishing, they need to be taken into consideration.

[0091] Reference Figure 3 As shown, the judgment index of the damage degree of the defect type includes the following steps:

[0092] Obtaining a defect sample image corresponding to the damage degree of the defect type as a target defect sample image;

[0093] Calculate the mean of the pixel values ​​of the pixels in the target defect sample image to obtain the target pixel value;

[0094] Obtain a value range of a difference between a pixel value of a pixel point in a target defect sample image and a target pixel value as a floating range;

[0095] The target pixel value and the floating range are used as the judgment indexes of the damage degree of the defect type corresponding to the target defect sample image.

[0096] The judgment index includes the target pixel value and the floating range. The reason is that the images of defect types are usually not completely consistent. There will be certain changes, that is, there will be small fluctuations around the target pixel value. Therefore, if only points consistent with the target pixel value are considered, the judgment of the defective area will be omitted, resulting in large judgment errors.

[0097] Reference Figure 4 As shown, establishing a corresponding relationship between the damage degree of the defect type and the polishing error of the polishing grinding head includes the following steps:

[0098] Obtain an error polishing grinding head in which the existing defect is consistent with the defect type and the defect degree is consistent with the damage degree of the defect type;

[0099] Obtain qualified sample polishing grinding heads;

[0100] Use an error polishing grinding head to perform polishing operation to obtain an error polished surface;

[0101] Perform polishing operation using a sample polishing grinding head to obtain a sample polished surface;

[0102] The error polishing surface is compared with the sample polishing surface to obtain the polishing error of the error polishing grinding head;

[0103] The polishing error of the error polishing grinding head is matched with the damage degree of the defect type corresponding to the error polishing grinding head.

[0104] The polishing error caused by the damage degree of each defect type is different. The purpose of surface defect identification after the polishing head is manufactured is to determine whether the polishing head can meet the polishing requirements. Any polishing head has defects, but the degree of defects is different. Some defects are very small and the polishing error caused can be ignored. Therefore, it is necessary to establish a corresponding relationship. According to this, the polishing error of the damage degree of the defect type can be obtained based on the corresponding relationship.

[0105] Reference Figure 5 As shown, establishing the polishing error superposition model of defect types includes the following steps:

[0106] Obtain the number of at least one defect type as a characteristic value;

[0107] Randomly combining at least one defect type to obtain at least one defect combination, wherein the number of defect types in the defect combination is any number between 0 and the characteristic value;

[0108] Setting the damage degree of the defect type in the defect combination to a preset degree, and obtaining the polishing error corresponding to the defect type with the damage degree of the preset degree as the preset polishing error;

[0109] Acquire a characteristic polishing grinding head, wherein the characteristic polishing grinding head is satisfied with just including all defect types in the defect combination, and the damage degree of the defect types of the characteristic polishing grinding head is a preset degree;

[0110] Use a characteristic polishing grinding head to perform polishing operation to obtain a characteristic polished surface;

[0111] The characteristic polishing surface is compared with the sample polishing surface to obtain the polishing error of the characteristic polishing grinding head;

[0112] The polishing error corresponding to the damage degree of at least one defect type of the characteristic polishing grinding head is fitted with the polishing error of the characteristic polishing grinding head to obtain an error superposition fitting function, wherein the polishing error corresponding to the damage degree of at least one defect type of the characteristic polishing grinding head is an independent variable, and the polishing error of the characteristic polishing grinding head is a dependent variable.

[0113] There may be multiple defects in the polishing head, and the polishing error caused by them cannot be obtained by simple superposition. Function fitting is required to establish an error superposition fitting function. Therefore, the actual comprehensive polishing error of the polishing head can be obtained more accurately according to the error superposition fitting function, and then analysis and judgment can be made based on this.

[0114] Reference Figure 6 As shown, obtaining the front surface image and the rear surface image of the polishing grinding head after manufacture includes the following steps:

[0115] Selecting a reference point on the manufactured polishing grinding head, and obtaining a tangent plane of the polishing grinding head at the reference point;

[0116] Obtain a normal line passing through the reference point, wherein the normal line is perpendicular to the cutting plane;

[0117] The part of the normal line located at the front side of the polishing grinding head after manufacture is used as the front photographic line;

[0118] The part of the normal line located at the rear side of the polishing grinding head after manufacture is used as the rear photographic line;

[0119] Acquire an image of the front side of the polishing grinding head after manufacture along the front photographic line as a front surface image;

[0120] An image of the rear side of the finished polishing grinding head is acquired along the rear photographic line as a rear surface image.

[0121] The polishing head is three-dimensional, and one image cannot obtain all its information. Using the front surface image and the back surface image in this solution can include all the image information of the polishing head, and there will be no overlapping parts between the front surface image and the back surface image. Therefore, using the front surface image and the back surface image for image analysis can meet the needs, and there will be no repeated analysis.

[0122] Reference Figure 7 As shown, analyzing and comparing the front surface image and the rear surface image to obtain at least one surface defect of the polishing grinding head includes the following steps:

[0123] Pixel points are identified in both the front surface image and the back surface image, and the pixels whose difference from the target pixel value is less than the floating range are summarized as surface defects;

[0124] The defect type corresponding to the target pixel value is matched to the surface defect, and the damage degree of the defect type corresponding to the target pixel value is used as the damage degree of the surface defect.

[0125] When performing surface defect analysis, it is necessary not only to obtain the defect type corresponding to the surface defect, but also to obtain the degree of damage of the surface defect. Otherwise, the polishing error caused by the surface defect cannot be obtained based on the defect type alone.

[0126] Reference Figure 8 As shown, determining the location of the surface defect on the polishing head includes the following steps:

[0127] Carry out three-dimensional coordinate modeling on the manufactured polishing grinding head, with the reference point being the coordinate origin;

[0128] Establishing a one-to-one correspondence between the pixel points in the front surface image and the rear surface image and the actual coordinates of the pixel points in the polishing grinding head after manufacture;

[0129] The center of the area where the surface defect is located in the front surface image and the back surface image is used as the positioning point of the surface defect;

[0130] The coordinates of the corresponding points of the positioning points on the manufactured polishing grinding head are obtained as the positions of the surface defects on the polishing grinding head.

[0131] The purpose of determining the position of the surface defect on the polishing head is to be able to repair it at the corresponding position according to its position when the defect cannot be ignored. Because some surface defects can be repaired, they are tested again after repair and can be used if qualified.

[0132] Reference Fig. 9 As shown, based on at least one surface defect, obtaining the actual polishing error corresponding to the surface defect includes the following steps:

[0133] Obtaining the damage degree of the defect type corresponding to the damage degree of the surface defect as the damage degree of the actual defect type;

[0134] Obtaining a polishing error corresponding to the damage degree of an actual defect type as an actual polishing error;

[0135] Based on the polishing error superposition model of defect types, obtaining the actual comprehensive polishing error of the polishing head includes the following steps:

[0136] The actual polishing error corresponding to at least one surface defect is substituted into the error superposition fitting function to obtain the actual comprehensive polishing error of the polishing grinding head.

[0137] The actual comprehensive polishing error is the result of combining the polishing errors caused by the damage degree of various actual defect types. Based on this, the qualification degree of the polishing head can be judged and the repair plan can be determined.

[0138] A detection system for identifying surface defects of a polishing head after manufacture, used to implement the above-mentioned detection method for identifying surface defects of a polishing head after manufacture, comprising:

[0139] A data acquisition module, wherein the data acquisition module acquires at least one defect type of the polishing grinding head based on historical data, and acquires a defect sample image set corresponding to the defect type, wherein the defect sample image set includes at least one defect sample image corresponding to the defect type;

[0140] An index forming module, wherein the index forming module forms a judgment index of the damage degree of the defect type based on the defect sample image set;

[0141] A relationship building module, wherein the relationship building module establishes a corresponding relationship between the damage degree of the defect type and the polishing error of the polishing grinding head;

[0142] A model building module, wherein the model building module builds a polishing error superposition model of defect types;

[0143] A defect acquisition module, wherein the defect acquisition module acquires a front surface image and a rear surface image of the polishing head after manufacture, analyzes and compares the front surface image and the rear surface image, obtains at least one surface defect of the polishing head, and determines a position of the surface defect on the polishing head;

[0144] An error acquisition module, wherein the error acquisition module obtains an actual polishing error corresponding to the surface defect based on at least one surface defect, and obtains an actual comprehensive polishing error of the polishing grinding head based on a polishing error superposition model of defect types;

[0145] The identification and judgment module obtains the minimum allowable polishing error of the polishing grinding head and judges whether the actual comprehensive polishing error is greater than the minimum allowable polishing error.

[0146] Furthermore, the present solution also proposes a storage medium on which a computer-readable program is stored. When the computer-readable program is called, the above-mentioned detection method for identifying surface defects of a polishing grinding head after manufacture is executed.

[0147] It is understandable that the storage medium may be a magnetic medium, such as a floppy disk, a hard disk, or a magnetic tape; an optical medium, such as a DVD; or a semiconductor medium, such as a solid state drive (SSD).

[0148] In summary, the advantages of the present invention are: by forming a judgment index of the damage degree of the defect type, a corresponding relationship is established between the damage degree of the defect type and the polishing error of the polishing head, and a polishing error superposition model of the defect type is established, so that various defects on the surface of the polishing head can be accurately identified, and by compounding the polishing errors caused by various defects, the actual comprehensive polishing error of the polishing head can be obtained, and then whether the polishing head is qualified can be judged based on this, thereby avoiding misjudging the negligible defects of the polishing head as non-negligible defects, thereby improving the accuracy of detection. At the same time, the use of algorithms for identification can reduce the time and manpower consumed in detection.

[0149] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. A detection method for identifying surface defects of a polishing head after manufacture, characterized in that: include: Based on the historical data, at least one defect type of the polishing grinding head is obtained, and a defect sample image set corresponding to the defect type is obtained, wherein the defect sample image set includes at least one defect sample image corresponding to the defect type; Based on the defect sample image set, a judgment index of the damage degree of the defect type is formed; Establish a corresponding relationship between the damage degree of the defect type and the polishing error of the polishing grinding head; Establish polishing error superposition model of defect types; Acquire a front surface image and a rear surface image of the polishing head after manufacture, analyze and compare the front surface image and the rear surface image, obtain at least one surface defect of the polishing head, and determine the position of the surface defect on the polishing head; Based on at least one surface defect, obtaining an actual polishing error corresponding to the surface defect; Based on the polishing error superposition model of defect types, the actual comprehensive polishing error of the polishing head is obtained; Obtain the minimum allowable polishing error of the polishing head, and determine whether the actual comprehensive polishing error is greater than the minimum allowable polishing error. If so, the polishing head is unqualified, and the position of the surface defect on the polishing head is used as the position to be repaired. If not, the polishing head is qualified; The method of establishing the polishing error superposition model of defect types comprises the following steps: Obtain the number of at least one defect type as a characteristic value; Randomly combining at least one defect type to obtain at least one defect combination, wherein the number of defect types in the defect combination is any number between 0 and the characteristic value; Setting the damage degree of the defect type in the defect combination to a preset degree, and obtaining the polishing error corresponding to the defect type with the damage degree of the preset degree as the preset polishing error; Acquire a characteristic polishing grinding head, wherein the characteristic polishing grinding head is satisfied with just including all defect types in the defect combination, and the damage degree of the defect types of the characteristic polishing grinding head is a preset degree; Use a characteristic polishing grinding head to perform polishing operation to obtain a characteristic polished surface; The characteristic polishing surface is compared with the sample polishing surface to obtain the polishing error of the characteristic polishing grinding head; The polishing error corresponding to the damage degree of at least one defect type of the characteristic polishing grinding head is fitted with the polishing error of the characteristic polishing grinding head to obtain an error superposition fitting function, wherein the polishing error corresponding to the damage degree of at least one defect type of the characteristic polishing grinding head is an independent variable, and the polishing error of the characteristic polishing grinding head is a dependent variable.

2. A detection method for identifying surface defects of a polishing grinding head after manufacture according to claim 1, characterized in that: The method of obtaining a defect sample image set corresponding to a defect type comprises the following steps: Under the conditions of different damage degrees of defect types, defect sample images are obtained; The defect sample images are matched one by one with the damage degree of the defect type.

3. A detection method for identifying surface defects of a polishing grinding head after manufacture according to claim 2, characterized in that: The determination index of the damage degree of the defect type comprises the following steps: Obtaining a defect sample image corresponding to the damage degree of the defect type as a target defect sample image; Calculate the mean of the pixel values ​​of the pixels in the target defect sample image to obtain the target pixel value; Obtain a value range of a difference between a pixel value of a pixel point in a target defect sample image and a target pixel value as a floating range; The target pixel value and the floating range are used as the judgment indexes of the damage degree of the defect type corresponding to the target defect sample image.

4. A detection method for identifying surface defects of a polishing head after manufacture according to claim 3, characterized in that: The step of establishing a corresponding relationship between the damage degree of the defect type and the polishing error of the polishing grinding head comprises the following steps: Obtain an error polishing grinding head in which the existing defect is consistent with the defect type and the defect degree is consistent with the damage degree of the defect type; Obtain qualified sample polishing grinding heads; Use an error polishing grinding head to perform polishing operation to obtain an error polished surface; Perform polishing operation using a sample polishing grinding head to obtain a sample polished surface; The error polishing surface is compared with the sample polishing surface to obtain the polishing error of the error polishing grinding head; The polishing error of the error polishing grinding head is matched with the damage degree of the defect type corresponding to the error polishing grinding head.

5. A detection method for identifying surface defects of a polishing grinding head after manufacture according to claim 4, characterized in that: The method of obtaining the front surface image and the rear surface image of the polishing grinding head after manufacture comprises the following steps: Selecting a reference point on the manufactured polishing grinding head, and obtaining a tangent plane of the polishing grinding head at the reference point; Obtain a normal line passing through the reference point, wherein the normal line is perpendicular to the cutting plane; The part of the normal line located at the front side of the polishing grinding head after manufacture is used as the front photographic line; The part of the normal line located at the rear side of the polishing grinding head after manufacture is used as the rear photographic line; Acquire an image of the front side of the polishing grinding head after manufacture along the front photographic line as a front surface image; An image of the rear side of the finished polishing grinding head is acquired along the rear photographic line as a rear surface image.

6. A detection method for identifying surface defects of a polishing head after manufacture according to claim 5, characterized in that: The analyzing and comparing the front surface image and the rear surface image to obtain at least one surface defect of the polishing grinding head comprises the following steps: Pixel points are identified in both the front surface image and the back surface image, and the pixels whose difference from the target pixel value is less than the floating range are summarized as surface defects; The defect type corresponding to the target pixel value is matched to the surface defect, and the damage degree of the defect type corresponding to the target pixel value is used as the damage degree of the surface defect.

7. A detection method for identifying surface defects of a polishing grinding head after manufacture according to claim 6, characterized in that: Determining the position of the surface defect on the polishing head comprises the following steps: Carry out three-dimensional coordinate modeling on the manufactured polishing grinding head, with the reference point being the coordinate origin; Establishing a one-to-one correspondence between the pixel points in the front surface image and the rear surface image and the actual coordinates of the pixel points in the polishing grinding head after manufacture; The center of the area where the surface defect is located in the front surface image and the back surface image is used as the positioning point of the surface defect; The coordinates of the corresponding points of the positioning points on the manufactured polishing grinding head are obtained as the positions of the surface defects on the polishing grinding head.

8. A detection method for identifying surface defects of a polishing grinding head after manufacture according to claim 7, characterized in that: The step of obtaining the actual polishing error corresponding to the surface defect based on at least one surface defect comprises the following steps: Obtaining the damage degree of the defect type corresponding to the damage degree of the surface defect as the damage degree of the actual defect type; Obtaining a polishing error corresponding to the damage degree of an actual defect type as an actual polishing error; Based on the polishing error superposition model of defect types, obtaining the actual comprehensive polishing error of the polishing head includes the following steps: The actual polishing error corresponding to at least one surface defect is substituted into the error superposition fitting function to obtain the actual comprehensive polishing error of the polishing grinding head.

9. A detection system for identifying surface defects of a polishing head after manufacture, used to implement the detection method for identifying surface defects of a polishing head after manufacture as claimed in any one of claims 1 to 8, characterized in that: include: A data acquisition module, wherein the data acquisition module acquires at least one defect type of the polishing grinding head based on historical data, and acquires a defect sample image set corresponding to the defect type, wherein the defect sample image set includes at least one defect sample image corresponding to the defect type; An index forming module, wherein the index forming module forms a judgment index of the damage degree of the defect type based on the defect sample image set; A relationship building module, wherein the relationship building module establishes a corresponding relationship between the damage degree of the defect type and the polishing error of the polishing grinding head; A model building module, wherein the model building module builds a polishing error superposition model of defect types; A defect acquisition module, wherein the defect acquisition module acquires a front surface image and a rear surface image of the polishing head after manufacture, analyzes and compares the front surface image and the rear surface image, obtains at least one surface defect of the polishing head, and determines a position of the surface defect on the polishing head; An error acquisition module, wherein the error acquisition module obtains an actual polishing error corresponding to the surface defect based on at least one surface defect, and obtains an actual comprehensive polishing error of the polishing grinding head based on a polishing error superposition model of defect types; An identification and judgment module, wherein the identification and judgment module obtains a minimum allowable polishing error of the polishing grinding head and judges whether an actual comprehensive polishing error is greater than the minimum allowable polishing error; The method of establishing the polishing error superposition model of defect types comprises the following steps: Obtain the number of at least one defect type as a characteristic value; Randomly combining at least one defect type to obtain at least one defect combination, wherein the number of defect types in the defect combination is any number between 0 and the characteristic value; Setting the damage degree of the defect type in the defect combination to a preset degree, and obtaining the polishing error corresponding to the defect type with the damage degree of the preset degree as the preset polishing error; Acquire a characteristic polishing grinding head, wherein the characteristic polishing grinding head is satisfied with just including all defect types in the defect combination, and the damage degree of the defect types of the characteristic polishing grinding head is a preset degree; Use a characteristic polishing grinding head to perform polishing operation to obtain a characteristic polished surface; The characteristic polishing surface is compared with the sample polishing surface to obtain the polishing error of the characteristic polishing grinding head; The polishing error corresponding to the damage degree of at least one defect type of the characteristic polishing grinding head is fitted with the polishing error of the characteristic polishing grinding head to obtain an error superposition fitting function, wherein the polishing error corresponding to the damage degree of at least one defect type of the characteristic polishing grinding head is an independent variable, and the polishing error of the characteristic polishing grinding head is a dependent variable.

Citation Information

Patent Citations

  • Surface defect detecting system of crystalline silicon polished wafer

    CN102621152A

  • Plate blank automatic grinding wheel grinding device based on defect identification system

    CN109807750A