A method for automatically adjusting the concentricity of ceramic splitting cutters based on machine vision

Abstract

The invention discloses an automatic concentric grinding method for a ceramic splitting cutter based on machine vision, which relates to the technical field of ceramic splitting cutter processing and detection, and comprises a visual imaging device, a rotary clamping device, a grinding wheel grinding device, a PLC device, a correction concentric module, and a tip grinding module. The visual imaging device is used to provide visual images for the correction concentric module and the tip grinding module, the rotary clamping device is used to clamp the ceramic splitting cutter and provide rotation, and the grinding wheel grinding device is used to process and grind the ceramic splitting cutter. The invention realizes high-precision positioning of the hole center of the ceramic splitting cutter and rapid correction and precise grinding of the tip diameter of the ceramic splitting cutter based on a machine vision algorithm, solves the problems of low manual detection efficiency, easy missed detection and false detection in the original production method, improves product production efficiency, improves product quality, and thus effectively improves the use performance and service life of the ceramic splitting cutter.

Description

Technical Field

[0001] The invention relates to the technical field of ceramic splitting cutter processing and detection, and in particular to an automatic concentric grinding method for a ceramic splitting cutter based on machine vision. Background Art

[0002] Ceramic splitters, also known as porcelain nozzles, are widely used in the bonding and packaging of circuits such as thyristors, surface acoustic waves, diodes, and IC chips. In the production process of ceramic splitters, due to the low precision of production equipment, failures, deviation of the placement point of the splitter, etc., the concentricity deviation between the end face of the splitter and the center of the hole is easy to be too large, which directly affects the assembly and use of the splitter. On the other hand, the tip diameter of the splitter is also a key factor affecting its performance. If the tip diameter is too large, the ceramic splitter will touch the adjacent gold wire, causing wire damage or even wire breakage. If it is too small, the second solder joint will easily fall off and fail.

[0003] At present, the inspection of the concentricity and tip diameter of ceramic splitters is mainly completed by employees in combination with microscopes. This inspection method has the following shortcomings:

[0004] (1) The production efficiency is low and it is difficult to meet the production requirements;

[0005] (2) The detection is done manually, which may affect the accuracy of the detection;

[0006] (3) Employees working in front of the screen for a long time are prone to fatigue and distraction, which may lead to missed detection and false detection;

[0007] (4) The size of the splitting knife is small and the required precision is high. If manual grinding is not done carefully, it will be excessive, resulting in the production of defective products.

[0008] At present, there are few studies on the automated detection of the concentricity and tip diameter of ceramic splitters in China. Therefore, the purpose of the present invention is to provide a machine vision-based visual technology for automatic concentric grinding of ceramic splitters that can realize automated detection and has high production efficiency. The concentricity of the center of the ceramic splitter hole is enhanced through image recognition, and the tip diameter change is fed back to the grinding equipment in real time during the grinding process, so that the tip diameter is finally ground to an effective range, thereby effectively improving the performance and service life of the ceramic splitter. Summary of the invention

[0009] The purpose of the present invention is to solve the problems in the prior art and to propose a ceramic splitting cutter automatic concentric grinding method based on machine vision.

[0010] A method for automatically adjusting the concentricity of a ceramic splitting cutter based on machine vision, comprising a visual imaging device, a rotary clamping device, a grinding wheel grinding device, a PLC device, a correction concentricity module, and a tip grinding module, wherein the visual imaging device is used to provide visual images for the correction concentricity module and the tip grinding module, the rotary clamping device is used to clamp the ceramic splitting cutter and provide rotation, and the grinding wheel grinding device is used to process and grind the ceramic splitting cutter;

[0011] The concentricity correction module comprises the following steps:

[0012] S1, superimposing multiple frames of images to determine the rotation trajectory to determine the rotation center;

[0013] S2, threshold segmentation is performed on the real-time image to determine the hole center;

[0014] S3, real-time calibration of the coordinate system and feedback of the offset to move to the rotation center;

[0015] The tip grinding module comprises the following steps:

[0016] a. Select ROI and perform sub-pixel extraction on the ceramic splitting knife contour;

[0017] b. Fit the contour edge straight line using Tukey method and measure its tip diameter;

[0018] c. Feedback the measured value to the grinding wheel for grinding, and send an end signal when it falls below the set threshold.

[0019] Preferably, the visual imaging device and the rotary clamping device in the correction concentric module are coaxially arranged, and multiple frames of images are superimposed according to the rotation trajectory of the ceramic chopping knife to fit the rotation trajectory of the ceramic chopping knife and determine the image coordinates of its rotation center.

[0020] Preferably, in the correction concentricity module, the coordinates of point M in the original coordinate system are set to ( , ), the magnitude of the corresponding vector is r, and the angle is α, then the original coordinate ( , ) can be expressed as (rcosα,rsinα). The coordinate axis is rotated counterclockwise around the origin to form a new coordinate system. The coordinates of point M in the new coordinate system are ( , ) is (rcos(α-θ),rsin(α-θ)), which can be further decomposed into the following formula:

[0021]

[0022]

[0023] The coordinate transformation formula for the rotation of the coordinate axis is obtained as shown below:

[0024]

[0025]

[0026] After obtaining the conversion relationship of the coordinate system, the captured image is binarized, and the Blob method is used to screen out the small hole area of ​​the ceramic splitting cutter. The hole center coordinates are calculated through the Area_center operator, and the actual offset of the X-axis and Y-axis is calculated in real time according to the deviation between the hole center coordinates and the rotation center coordinates and the coordinate transformation formula, and the offset is fed back to the PLC device to move the hole center coordinates to the rotation center.

[0027] Preferably, the axis of the visual imaging device and the axis of the rotary clamping device in the tip grinding module are arranged perpendicular to each other.

[0028] Preferably, in the tip grinding module, a fitting function is used, that is, the formula:

[0029]

[0030] The fitting function is derived from partial derivatives of a and b respectively:

[0031]

[0032] Solving the above equation gives the best estimate of the line parameters a and b, as shown below:

[0033]

[0034] The Tukey weight function is used as shown below:

[0035]

[0036] In the above formula, is the distance from the point to the line, is the set threshold; when Less than or equal to When these points are given weights ,so The smaller it is, the greater the weight; when Greater than When giving weight After obtaining the diameter measurement value, the PLC device will provide real-time feedback signals to the grinding wheel grinding equipment for ceramic splitting cutter grinding. When the end face diameter is lower than the set threshold, an end signal will be sent to end the grinding.

[0037] Preferably, the visual imaging device, the rotary clamping device and the grinding wheel grinding device are all connected to the PLC device via a data transmission line.

[0038] Compared with the prior art, the present invention has the following advantages:

[0039] The present invention realizes high-precision positioning of the hole center of the ceramic chopper and rapid correction and precise grinding of the tip diameter of the ceramic chopper based on a machine vision algorithm, which solves the problems of low efficiency of manual inspection in the original production method and easy missed inspection and false inspection, improves product production efficiency, improves product quality, and effectively improves the performance and service life of the ceramic chopper. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 This is the overall flow chart of the algorithm in the present invention.

[0041] Figure 2 This is a schematic diagram of the position structure of the visual imaging device and the rotating clamping device when correcting the hole center of the present invention.

[0042] Figure 3 This is a schematic diagram of the position structure of the visual imaging device and the rotating clamping device when measuring the tip diameter of the present invention.

[0043] Figure 4 It is a schematic diagram of the rotation trajectory of the end face of the ceramic splitting cutter in the present invention.

[0044] Figure 5 It is a schematic diagram of positioning the center point of the end surface and the rotation center of the ceramic splitting cutter in the present invention.

[0045] Figure 6 It is a schematic diagram of the ceramic splitting cutter end face after being corrected to the center in the present invention.

[0046] Figure 7 This is a schematic diagram of the edge of the wedge contour fitted using the Tukey method in the present invention.

[0047] Figure 8 This is a picture of the ceramic splitting knife under a high-power microscope after final grinding of the present invention. DETAILED DESCRIPTION

[0048] In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, the present invention is further explained below in conjunction with specific implementation methods.

[0049] Reference Figure 1-8As shown, a method for automatically adjusting the concentricity and grinding of a ceramic splitting cutter based on machine vision includes a visual imaging device, a rotary clamping device, a grinding wheel grinding device, a PLC device, a correction concentricity module, and a tip grinding module. The visual imaging device is used to provide visual images for the correction concentricity module and the tip grinding module, the rotary clamping device is used to clamp the ceramic splitting cutter and provide rotation, and the grinding wheel grinding device is used to process and grind the ceramic splitting cutter;

[0050] The concentricity correction module comprises the following steps:

[0051] S1, superimposing multiple frames of images to determine the rotation trajectory to determine the rotation center;

[0052] S2, threshold segmentation is performed on the real-time image to determine the hole center;

[0053] S3, real-time calibration of the coordinate system and feedback of the offset to move to the rotation center;

[0054] The tip grinding module comprises the following steps:

[0055] a. Select ROI and perform sub-pixel extraction on the ceramic splitting knife contour;

[0056] b. Fit the contour edge straight line using Tukey method and measure its tip diameter;

[0057] c. Feedback the measured value to the grinding wheel for grinding, and send an end signal when it falls below the set threshold.

[0058] In this embodiment, Figure 2 As shown, in the correction concentric module, the visual imaging device and the rotating clamping device are coaxially arranged, and a high-brightness white point light source is arranged on the lens of the visual imaging device for coaxial lighting. According to the rotation trajectory of the ceramic chopping knife, multiple frames of images are superimposed and then the rotation trajectory of the ceramic chopping knife is fitted to determine the image coordinates of its rotation center.

[0059] In this embodiment, in the correction concentricity module, in the process of correcting the wedge hole center to the rotation center, the inconsistency between the image coordinate system and the actual coordinate system will cause inaccurate displacement. Therefore, during the correction, the coordinate system needs to be converted and calibrated. First, the coordinates of point M in the original coordinate system are set to ( , ), the magnitude of the corresponding vector is r, and the angle is α, then the original coordinate ( , ) can be expressed as (rcosα,rsinα). The coordinate axis is rotated counterclockwise around the origin to form a new coordinate system. The coordinates of point M in the new coordinate system are ( , ) is (rcos(α-θ),rsin(α-θ)), which can be further decomposed into the following formula:

[0060]

[0061]

[0062] The coordinate transformation formula for the rotation of the coordinate axis is obtained as shown below:

[0063]

[0064]

[0065] After obtaining the conversion relationship of the coordinate system, the captured image is binarized, and the Blob method is used to screen out the small hole area of ​​the ceramic splitting cutter. The hole center coordinates are calculated through the Area_center operator, and the actual offset of the X-axis and Y-axis is calculated in real time according to the deviation between the hole center coordinates and the rotation center coordinates and the coordinate transformation formula, and the offset is fed back to the PLC device to move the hole center coordinates to the rotation center.

[0066] In this embodiment, Figure 3 As shown, the axis of the visual imaging device in the tip grinding module and the axis of the rotating clamping device are arranged perpendicular to each other, and a high-brightness white point light source is fixed under the ceramic splitting knife for back lighting.

[0067] In the tip grinding module, a fitting function is used, namely:

[0068]

[0069] The fitting function is derived from partial derivatives of a and b respectively:

[0070]

[0071] Solving the above equation gives the best estimate of the line parameters a and b, as shown below:

[0072]

[0073] In actual application, there are more or less abnormal values ​​that deviate from normal values. , these outliers will cause large errors when using the least squares method for straight line fitting. For this reason, the Tukey weight function is used, as shown in the following formula:

[0074]

[0075] In the above formula, is the distance from the point to the line, is the set threshold; when Less than or equal to When these points are given weights ,so The smaller it is, the greater the weight; when Greater than When giving weight The Tukey weight function is introduced to improve the least squares method. The influence of outliers can be basically ignored. The straight line fitting result is more accurate. The fitting straight line basically coincides with the actual straight line. After obtaining the diameter measurement value, the PLC device is used to provide real-time feedback signals to the grinding wheel grinding equipment for ceramic splitting cutter grinding. When the end face diameter is lower than the set threshold, an end signal is sent to end the grinding.

[0076] In this embodiment, the visual imaging device, the rotary clamping device, and the grinding wheel grinding device are all connected to the PLC device via a data transmission line.

[0077] The final image of the ceramic splitting knife after grinding under a high-power microscope is as follows: Figure 8 As shown, compared with the images collected before grinding, it can be clearly seen that the concentricity of the ceramic splitting tool end face is greatly improved, and its tip diameter is within the effective range.

[0078] It is known from common technical knowledge that the present invention can be implemented by other embodiments that do not deviate from its spirit or essential features. Therefore, the above disclosed embodiments are only illustrative in all respects and are not exclusive. All changes within the scope of the present invention or within the scope equivalent to the present invention are included in the present invention.

Claims

1. A method for automatically adjusting the concentricity of a ceramic splitting tool based on machine vision, characterized in that: It includes a visual imaging device, a rotary clamping device, a grinding wheel grinding device, a PLC device, a correction concentric module, and a tip grinding module. The visual imaging device is used to provide visual images for the correction concentric module and the tip grinding module. The rotary clamping device is used to clamp the ceramic splitting cutter and provide rotation. The grinding wheel grinding device is used to process and grind the ceramic splitting cutter. The concentricity correction module comprises the following steps: S1, superimposing multiple frames of images to determine the rotation trajectory to determine the rotation center; S2, threshold segmentation is performed on the real-time image to determine the hole center; S3, real-time calibration of the coordinate system and feedback of the offset to move to the rotation center; The tip grinding module comprises the following steps: a. Select ROI and perform sub-pixel extraction on the ceramic splitting knife contour; b. Fit the contour edge straight line using Tukey method and measure its tip diameter; c. Feedback the measured value to the grinding wheel for grinding, and send an end signal when it falls below the set threshold; In the correction concentricity module, the coordinates of point M in the original coordinate system are set to ( , ), the magnitude of the corresponding vector is r, and the angle is α, then the original coordinate ( , ) can be expressed as (rcosα, rsinα). The coordinate axis is rotated counterclockwise around the origin to form a new coordinate system. The coordinates of point M in the new coordinate system are ( , ) is (rcos(α-θ),rsin(α-θ)), which can be further decomposed into the following formula: The coordinate transformation formula for the rotation of the coordinate axis is obtained as shown below: After obtaining the conversion relationship of the coordinate system, the collected image is binarized, and the Blob method is used to screen out the small hole area of ​​the ceramic splitting tool. The coordinates of the hole center are calculated through the Area_center operator, and the actual offsets of the X-axis and Y-axis are calculated in real time according to the deviation between the hole center coordinates and the rotation center coordinates and the coordinate transformation formula, and then fed back to the PLC device to move the hole center coordinates to the rotation center. In the tip grinding module, a fitting function is used, namely: The fitting function is derived from partial derivatives of a and b respectively: Solving the above equation gives the best estimate of the line parameters a and b, as shown below: The Tukey weight function is used as shown below: In the above formula, is the distance from the point to the line, is the set threshold; when Less than or equal to When these points are given weights ,so The smaller it is, the greater the weight; when Greater than When giving weight After obtaining the diameter measurement value, the PLC device will provide real-time feedback signals to the grinding wheel grinding equipment for ceramic splitting cutter grinding. When the end face diameter is lower than the set threshold, an end signal will be sent to end the grinding.

2. The method for automatically adjusting the concentricity of a ceramic splitting tool based on machine vision according to claim 1 is characterized in that: The visual imaging device and the rotary clamping device in the correction concentric module are coaxially arranged, and multiple frames of images are superimposed according to the rotation trajectory of the ceramic chopping knife to fit the rotation trajectory of the ceramic chopping knife and determine the image coordinates of its rotation center.

3. The method for automatically adjusting the concentricity of a ceramic splitting tool based on machine vision according to claim 1 is characterized in that: The axis of the visual imaging device and the axis of the rotary clamping device in the tip grinding module are arranged perpendicular to each other.

4. The method for automatically adjusting the concentricity of a ceramic splitting tool based on machine vision according to claim 1 is characterized in that: The visual imaging device, the rotary clamping device and the grinding wheel grinding device are all connected to the PLC device via a data transmission line.

Images