3C product computer closed-loop control method based on multi-dimensional data analysis

Abstract

The invention discloses a computer closed-loop control method for 3C products based on multi-dimensional data analysis, and belongs to the technical field of computer control in the design industrial process. According to the method, intelligent control over automatic labeling of the 3C products is achieved through five steps. The method comprises the following steps: 1, obtaining a product specification and production line information, determining a labeling surface, and matching a 3C size by combining the size; 2, scanning and identifying a product labeling point based on specification information, driving a laser transmitter to project a visible laser frame, calibrating the labeling point in real time, and ensuring the position accuracy; 3, combining the position of the labeling point and production line information to obtain the necessary residence time of the product to guarantee the completion of the operation; fourthly, labeling is conducted within the staying duration, the single-time quality is detected in real time, and the success rate within the time period is counted at intervals and compared with a threshold value; fifthly, if the success rate is lower than a threshold value, the residence time is automatically optimized, and parameters are reconfigured; and if the parameters are higher than the threshold value, current parameter operation is kept, self-adaptive adjustment is achieved, and the efficient and high-quality labeling requirement is met.

Description

Technical Field

[0001] This invention relates to the field of industrial process computer control technology, and more specifically, to a closed-loop control method for 3C products based on multidimensional data analysis. Background Technology

[0002] Traditional labeling systems rely on sensor-based triggering processes. Initial equipment debugging and parameter pre-setting are crucial to ensure precise labeling actions. First, the sensor is fixed at a pre-defined detection position on the production line conveyor belt, ensuring an unobstructed detection path and stable signal capture. Simultaneously, the labeling machine is fixed so the labeling head aligns with the designated labeling point on the conveyor belt, ensuring correct labeling direction and position. Then, the sensor's sensitivity and detection mode are adjusted based on the product's physical characteristics to avoid missed detections or false triggers due to product variations. Key parameters such as specifications, delay time, and labeling pressure are entered into the labeling machine control system. When a product flows through the sensor's detection area on the conveyor belt, the sensor captures the product signal and immediately transmits a trigger signal to the labeling machine control system. Upon receiving the signal, the system initiates the process after the pre-defined delay. The labeling process involves the labeling machine peeling and attaching the label precisely to the designated position on the product according to preset parameters. However, in actual use, it still has some drawbacks, such as: 1. Reliance on rigid positioning, resulting in low flexibility and intelligence: Existing methods heavily rely on rigid hardware such as precision fixtures and preset mechanical coordinates for positioning. Once the product model is changed, the machine must be stopped and redesigned, which cannot adapt to the flexible production needs of small batches and multiple varieties; 2. Labeling quality cannot be guaranteed in real time: Whether there are problems such as skewed labels, bubbles, or missing labels can only be detected by manual sampling at subsequent workstations or by separate offline testing equipment; 3. Static system parameters, lacking self-optimization capabilities: All parameters of the existing system are preset and fixed. When there are fluctuations in the production line rhythm, the system cannot sense them or adjust automatically, requiring post-event intervention and debugging. Summary of the Invention

[0003] To overcome the aforementioned deficiencies of the prior art, this invention provides a closed-loop control method for 3C product computers based on multidimensional data analysis, which addresses the problems mentioned in the background art through the following solutions: S1. Intelligent surface matching: The system obtains product manual information and production line information, determines the product surface based on the product manual information, and matches the 3C specifications and the size of the labeling roller according to the size of the product surface; S2, Visual Laser Frame Calibration: Based on the product manual information collected through digital information processing, the point position is determined, and the laser emitter is driven to project the visible laser frame to calibrate the point in real time. S3. Workstation dwell time calculation: Calculate the necessary dwell time of the product at the workstation based on the point and production line information; S4. Quality and Success Rate Detection: Operate the product within the necessary dwell time and detect the quality of each operation in real time. Calculate the success rate within this time period at intervals and compare it with the set success rate threshold. S5. Dynamic production line adjustment: If the success rate is detected to be lower than the set threshold, the system will automatically adjust the station dwell time and rematch the pressure roller. If the success rate is maintained above the threshold, the current parameters will be maintained and the system will continue to operate.

[0004] Preferably, among all the marking wheels that simultaneously satisfy the conditions of wheel surface length > widest distance and wheel surface width > narrowest distance, the marking wheel with the smallest size is selected.

[0005] Preferably, the labeling point is determined only once, and there is no difference in the labeling points of products of the same model within the same batch, maintaining complete consistency.

[0006] Preferably, the labeling success rate is calculated every hour and compared with the set labeling success rate threshold. If the labeling success rate is detected to be lower than the set threshold, the system automatically adjusts the dwell time of the labeling station and re-matches the labeling roller. If the labeling success rate remains above the threshold, the current parameters are maintained and the system continues to operate.

[0007] The technical effects and advantages of this invention are as follows: 1. High-precision positioning and guidance: Utilizes digital information processing to automatically identify the product labeling surface and labeling point, and drives a laser emitter to project a visible frame line to calibrate the labeling point in real time, improving the labeling position accuracy and operational visibility; 2. Intelligent labeling quality judgment: The vision system detects the adhesion coverage of the labeling to the product surface within the visible laser-selected area in real time, accurately judging whether a single labeling is successful, and ensuring that the quality inspection is objective and reliable; 3. Adaptive labeling rhythm optimization: The system can dynamically calculate the reasonable dwell time of the labeling station based on the production line operation status and labeling point location, and count the labeling success rate within the interval period; when the success rate is lower than the set threshold, the labeling process is automatically optimized. Attached Figure Description

[0008] Figure 1 This is a schematic diagram of the overall structure of the present invention.

[0009] Figure 2 This is a schematic diagram of the labeling surface selection process of the present invention.

[0010] Figure 3 This is a schematic diagram of the labeling quality inspection process of the present invention. Detailed Implementation

[0011] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0012] like Figure 1 The method shown is a closed-loop control method for 3C products based on multidimensional data analysis, including intelligent matching of labeling surfaces, calibration of labeling surfaces with visible laser frames, calculation of dwell time at labeling stations, detection of labeling quality and success rate, and dynamic adjustment of the production line.

[0013] like Figure 2 The method shown is a closed-loop control method for 3C products based on multidimensional data analysis. It extracts the surface features of the product, excludes functional surfaces, covered and obstructed surfaces and easily detachable surfaces. If there are no remaining surfaces, the labeling surface is manually selected. If there are remaining surfaces, the labeling surface is selected from the remaining surfaces.

[0014] like Figure 3 The method shown is a closed-loop control method for 3C products based on multidimensional data analysis. It projects a laser into the area within a visible laser frame, determines whether the area within the frame is covered based on the reflected signal, and determines that the pasting is successful if the coverage rate meets the threshold.

[0015] S1. Intelligent surface matching: The system obtains product manual information and production line information, determines the product surface based on the product manual information, and matches the 3C specifications and the size of the labeling roller according to the size of the product surface.

[0016] The labeling surface is determined based on the product instruction manual information. The product surface characteristics are obtained from the product instruction manual information, and functional product surfaces, covering and obstructing surfaces, and easily detachable surfaces are excluded in sequence. The remaining surfaces are considered valid surfaces, and the plane with the largest area among the valid surfaces is selected as the labeling surface for 3C products.

[0017] Based on the product manual, the functional product surface is defined as the physical surface with the largest proportion of components that enable the product's functional operation, as specified in the manual. Covering / obstructing surfaces are those permanently or periodically covered or obstructed by other components during the product's complete assembly or normal use period, or surfaces that are themselves movable. Easily detachable surfaces are those whose material properties, surface treatment processes, or usage environments, as described in the manual, would significantly reduce adhesive adhesion, making long-term secure bonding impossible. All other surfaces are considered valid surfaces. The area of ​​each valid surface is identified based on digital information processing, and the surface with the largest area is selected as the labeling surface. If no surface can be selected after excluding functional product surfaces, covering / obstructing surfaces, and easily detachable surfaces, the labeling surface is manually selected.

[0018] The 3C standard is determined based on the area of ​​the label surface, and the 3C adhesion coefficient is calculated. The 3C bonding coefficient is limited to a certain range to obtain the 3C specification that matches the 3C certification area. In this example, a 3C bonding coefficient of 20% to 50% is selected. If the 3C bonding coefficient is too small, the 3C information will be difficult to read. To adapt to the small area, the font or icons will be reduced in size, and the key content will be difficult to identify. If the 3C bonding coefficient is too large, it will result in cost waste and increase production costs and pasting time. The 3C specification with the smallest 3C bonding coefficient among all those that meet the requirements is selected as the 3C specification for this production.

[0019] The appropriate marking wheel should be matched to the 3C size determined by the 3C specification area. The wheel surface length of the marking wheel should be greater than the maximum lateral distance between any two points on the outer perimeter to ensure that the lateral range can be completely covered when the wheel rolls, without any edge missed areas. The wheel surface width of the marking wheel should be greater than the maximum longitudinal distance between any two points on the outer perimeter to avoid local unpressurized longitudinal areas due to insufficient wheel width, which may cause bubbles or wrinkles. Among all marking wheels that simultaneously meet the requirements of wheel surface length > maximum distance and wheel surface width > minimum distance, the smallest marking wheel should be selected.

[0020] S2, Visual Laser Frame Calibration: Based on digital information processing and the product manual information collected, the point is determined, and the laser emitter is driven to project the visual laser frame to calibrate the point in real time.

[0021] The labeling locations are determined based on digital information processing. An industrial camera is used to capture images of the labeling surface, and digital information processing is used to exclude areas containing functional components, text, or trademarks, uneven areas, and areas with low adhesion.

[0022] The area containing functional components, text, or trademarks exhibits abrupt color changes or a clear geometric outline. Based on grayscale contrast exclusion, the captured image of the label surface is converted into a pixel image. The original color pixel image is then grayscale-converted, converting the color information of each pixel to grayscale to obtain the grayscale value I(x, y) for each pixel, where (x, y) represents the pixel in the x-th row and y-th column. Using the Canny edge detection algorithm, the grayscale value I(x, y) is input and convolved with a two-dimensional Gaussian kernel G(x, y) to obtain smoothed pixels. The formula for calculating the two-dimensional Gaussian function is as follows: Calculate the gradient of the smoothed pixel in the horizontal and vertical directions, using the Sobel operator to calculate the partial derivatives, and the directional gradient G. x G is used to detect edges in the x-direction. x =S x ·I s (x, y), where the Sobel kernel directional gradient G yUsed to detect edges in the horizontal y direction, G y =S y ·I s (x, y), where the Sobel kernel , for each pixel point (x, y), we can calculate its gradient magnitude M(x, y) and gradient direction θ(x, y); M(x, y) = sqrt(G x 2 +G y 2 ) ， Can be approximately considered , , the angle range returned by the arctan2 function is [-π, π]; classify the gradient direction θ(x, y) of the current point into one of the four main directions: horizontal, diagonal, vertical, and anti-diagonal. In this example, calculate along the diagonal direction. Along this gradient direction, compare the gradient magnitude M(x, y) of the current point (x, y) with the gradient magnitudes of its two adjacent points in the positive and negative directions. If M(x, y) is greater than or equal to the magnitudes of its two adjacent points along the gradient direction, retain the magnitude of this point; otherwise, set its magnitude to zero. The refined gradient magnitude is denoted as N(x, y). Set a high threshold H and a low threshold L. If N(x, y) > H, it is a strong edge pixel; if L < N(x, y) ≤ H, it is a weak edge pixel; if N(x, y) ≤ L, it is a non-edge pixel. Retain all strong edge pixels and only retain the weak edge pixels connected to the strong edge pixels. Finally, obtain the edge pixel set, and define the edge binary image based on this: , if the pixel point (x, y) belongs to the edge pixel set E(x, y) = 1, otherwise, E(x, y) = 0.

[0023] For each pixel point (x, y) in the edge binary image E(x, y), perform the following calculations. Determine the n×n neighborhood centered on (x, y), and count the number of all edge images in this neighborhood. In this example, n is taken as 3, so the total number of edge pixels in the neighborhood , calculate the edge density , 9 is the number of pixels in the 3×3 neighborhood; set a threshold W, and judge whether the edge density satisfies D > W. If it is satisfied, this pixel belongs to the pixels in the edge-dense area; if it is not satisfied, this pixel belongs to the pixels in the non-functional area; the area where functional components or text or trademarks are located is composed of the contours formed by connected edge-dense area pixels, and is jointly composed of the contours and the space enclosed by the contours.

[0024] Non-flat areas have regular or irregular textures. The method for determining this is to emit a laser line onto the object's surface, capture the shape of the reflected laser line with a camera, and use triangulation to calculate the 3D contour points at the location of the laser line. The object is then moved to obtain the 3D contour points of the entire surface. After obtaining the 3D contour point data, the standard deviation of the height of all points is calculated. The smaller the standard deviation, the flatter the surface; the larger the standard deviation, the greater the surface undulation. A threshold is set for the standard deviation, and surfaces with a standard deviation greater than or equal to the threshold are judged as non-flat areas.

[0025] After the camera captures an image of the reflected laser line on the object's surface, the pixel coordinates of the camera's imaging plane are obtained through image processing algorithms, denoted as (u i v i) Let i be the i-th contour point on a single laser line, where i = 1, 2, ..., N, and N is the number of contour points on a single laser line. First, convert the pixel coordinates to physical coordinates on the camera imaging plane, using the camera principal point coordinates (u0, v0) as the origin. The camera principal point coordinates are the pixel coordinates of the intersection of the camera optical axis and the imaging plane, i.e., the pixel plane origin offset in mm. Physical coordinates along the u-axis: X img =(u i −u0)×α, Physical coordinates along the v-axis: Y img =(v i −v0)×β, Where α and β are the camera pixel scale factors, representing the actual physical length corresponding to 1 pixel on the imaging plane. α is the camera pixel scale factor along the u-axis, and β is the camera pixel scale factor along the v-axis. A world coordinate system is established based on the production line. The product's movement direction on the production line is the Y-axis, the plane perpendicular to the production line is the Z-axis, and the axis perpendicular to the plane formed by Y and Z is the X-axis. The product moves along either the X-axis or the Y-axis. In this example, the product moves along the Y-axis, i.e., the movement direction is perpendicular to the laser line length direction, thus converting the physical coordinates into world coordinates. The calculation method is as follows. Y i =Y img In a single scan, all points have the same Y-coordinate, which is provided by the mobile platform's positioning. img Calculated from physical coordinates, X i =k x ×X img i+bx, X img Calculated from physical coordinates, where i is the i-th contour point on a single laser line, and k x bx is the calibration coefficient in the X direction, which is determined by the calibration process.

[0026] Based on parameters such as the angle θ between the laser plane and the camera optical axis, and the camera focal length f, the height Z is derived using trigonometric relationships.i First, calculate the ray direction vector from the camera's optical center to any point on the laser line. The coordinates of the camera's optical center in the world coordinate system are (0, 0, H), where H is the perpendicular distance from the camera's optical center to the product placement plane. Then, the projection of the ray direction vector from the camera to any point on the laser line onto the imaging plane satisfies: Where f is the camera focal length, and L is the horizontal distance from the camera's optical center to any point on the laser line in the XZ plane. This simplifies to L≈H−Z i The laser plane satisfies the equation θ is the angle between the laser plane emitted by the laser emitter and the camera's optical axis, i.e., the angle from the camera to the central axis of the object. Substituting this into X... i The expression is then rearranged to obtain the final height Z. i Calculation formula Control the product to move at a constant speed along the Y-axis of the world coordinate system, with a step size of ΔY, determined by the required measurement accuracy. Repeat the Z-axis movement for each step. i The calculation obtains all 3D contour points (X) of the laser line at that location. ij Y ij Z ij ), where j=1, 2, ..., M, M is the number of movement steps; finally, the 3D contour point cloud data of the entire object surface is obtained, and the height values ​​of all points constitute the height dataset {Z ij |i=1,…,N,j=1,…,M}, where N is the number of contour points on a single laser line.

[0027] By calculating the height dataset {Z ij The standard deviation quantifies the degree of surface unevenness; the larger the standard deviation, the more uneven the surface. The mean Z represents the reference height of the object's surface, calculated using the following formula: Calculate the standard deviation σZ of the height data. The standard deviation σZ reflects the degree of dispersion of all height values ​​relative to the average value Z. The greater the dispersion, the more obvious the surface undulation. Set a flatness threshold σth, in mm. σth is determined by actual application requirements and needs to be calibrated through experiments or industry standards. If the calculated surface height standard deviation σZ ≥ σth, the surface is determined to be a non-flat area; if σZ < σth, it is determined to be a flat surface.

[0028] Based on the information in the instruction manual, areas with low adhesion are identified, and areas with coatings are identified as areas with low adhesion.

[0029] The remaining area is the candidate area. If the candidate area has a regular shape, the center point of the smallest bounding rectangle is used as the labeling point. If the area has an irregular shape, the geometric centroid of the area is used as the labeling point. When performing the labeling operation, ensure that the labeling point is precisely aligned with the center. A visible laser frame is projected with the labeling point as the center. The visible laser frame is a visual representation of the 3C outline. The shape and size of the visible laser frame completely match the outline of the selected 3C specification. The determination of the labeling point is calculated only once. There is no difference in the labeling points of products of the same model in the same batch, and they are completely consistent.

[0030] S3. Workstation Dwell Time Calculation: Based on the point and production line information, calculate the necessary dwell time of the product at the workstation; the formula for calculating the necessary dwell time is as follows: Where t1 is the product flipping and alignment time, t2 is the bonding operation time, t3 is the labeling quality inspection time, and t4 is the production cycle redundancy time; the time required to flip and adjust the product to ensure that the labeling surface is facing the labeling machine and perpendicular to the production line is the product flipping and alignment time, calculated using the following formula: Where θ is the required product flipping angle in degrees, and ω is the rated angular velocity of the machine flipping the product in degrees per second; the total time for the peeling, conveying, and bonding process to the product surface is the bonding operation time, calculated using the following formula: Where L is the length of a single sheet in mm, v1 is the conveying speed of the peeling machine in mm / s, d is the effective pressing stroke of the pressing machine in mm, v2 is the rated pressing speed of the pressing machine in mm / s, and 0.2 is the time set in this example for conveying the product surface in seconds; the time spent detecting labeling quality based on digital information processing is the labeling quality inspection time; the buffer time reserved to cope with production line fluctuations is the production cycle redundancy time; the labeling quality inspection time and the production cycle redundancy time are empirical values ​​determined by statistical analysis and practical verification based on historical data accumulated from production line operation; the production line information, including the required product flipping angle, the rated angular velocity of the equipment flipping machine, the conveying speed of the peeling machine, the effective pressing stroke of the pressing machine, and the rated pressing speed of the pressing machine, is obtained by the intelligent matching step of the labeling surface.

[0031] S4. Quality and Success Rate Detection: Operate the product within the necessary dwell time and detect the quality of each operation in real time. Calculate the success rate within this time period at intervals and compare it with the set success rate threshold.

[0032] The labeling quality inspection method is as follows: After the labeling operation is completed, the visible laser-selected area is divided into several grid areas and a laser is projected. If the reflected signal intensity within a grid area is I0, then that grid area is covered; if the reflected signal intensity within a grid area is I, then that grid area is not covered. The coverage area within the visible laser-selected area is calculated, and the coverage area is equal to the area occupied by the grid with a reflected signal intensity of I0. The coverage rate is then calculated. If the coverage rate is greater than or equal to the set threshold, the pasting is successful; if the coverage rate is less than the set threshold, the pasting is deemed unqualified.

[0033] Before testing, parameters are calibrated through sample testing to provide a benchmark for subsequent calculations. For n products, lasers are projected under the same testing environment, reflection signals are collected and averaged, and the average value is the standard reflection intensity I0. For n unlabeled products, lasers are projected onto the visible laser-selected area under the same environment, reflection signals are collected and averaged, and the average value is the product surface reflection intensity I.

[0034] Divide the visible laser-selected area into N equal grid regions, denoted as A. The grid area must be determined based on the maximum allowable missing area; the area of ​​a single grid cannot exceed the maximum allowable missing area. Maximum allowable missing area = visible laser-selected area area × (1 - set acceptable coverage rate). In this example, the acceptable coverage rate is set to 95%. Project a laser onto each grid region and measure the reflected signal intensity. Determine if each grid is covered based on the reflected signal intensity: if the reflected signal intensity is I0, the grid is covered; if the reflected signal intensity is I, the grid is uncovered. Count the number of grids with a reflected signal intensity of I0, denoted as M. The total area S of the visible laser-selected area is equal to the sum of the areas of all grids. Calculate the coverage rate: calculate the coverage rate based on the covered area and the total area. If the coverage rate is greater than or equal to the threshold, the pasting is considered successful. In this example, the threshold is set to 97%, which means that products whose area occupies 97% or more of the area selected by the visible laser are successfully pasted.

[0035] The labeling success rate is the proportion of products that are successfully labeled within a certain period of time out of the total number of labeled products. In this example, the labeling success rate is tested every hour, and the proportion of the number of products that are successfully labeled within one hour out of the total number of products labeled within one hour is calculated.

[0036] S5. Dynamic production line adjustment: If the success rate is detected to be lower than the set threshold, the system will automatically adjust the station dwell time and rematch the pressure roller. If the success rate is maintained above the threshold, the current parameters will be maintained and the system will continue to operate.

[0037] Secondly: The accompanying drawings of the embodiments disclosed in this invention only involve the structures involved in the embodiments disclosed in this invention. Other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of this invention can be combined with each other. In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A closed-loop control method for 3C products based on multidimensional data analysis, characterized in that, include: S1. Intelligent surface matching: The system obtains product manual information and production line information, determines the product surface based on the product manual information, and matches the 3C specifications and the size of the labeling roller according to the size of the product surface; S2, Visual Laser Frame Calibration: Based on the product manual information collected through digital information processing, the point position is determined, and the laser emitter is driven to project the visible laser frame to calibrate the point in real time. S3. Workstation dwell time calculation: Calculate the necessary dwell time of the product at the workstation based on the point and production line information; S4. Quality and Success Rate Detection: Operate the product within the necessary dwell time and detect the quality of each operation in real time. Calculate the success rate within this time period at intervals and compare it with the set success rate threshold. S5. Dynamic production line adjustment: If the success rate is detected to be lower than the set threshold, the system will automatically adjust the station dwell time and rematch the pressure roller. If the success rate is maintained above the threshold, the current parameters will be maintained and the system will continue to operate.

2. The closed-loop control method for 3C product computers based on multidimensional data analysis according to claim 1, characterized in that: The product labeling surface is determined based on the product instruction manual information. The product surface characteristics are obtained from the product instruction manual information, and functional product surfaces, covering and obstructing surfaces, and easily detachable surfaces are excluded in sequence. The remaining surfaces are considered valid surfaces, and the plane with the largest area among the valid surfaces is selected as the 3C labeling surface.

3. The closed-loop control method for 3C product computers based on multidimensional data analysis according to claim 2, characterized in that: The 3C specifications are determined based on the area of ​​the labeling surface, and the 3C adhesion coefficient is calculated. By limiting the range of the 3C bonding coefficient, the 3C specification that matches the 3C area is obtained.

4. The closed-loop control method for 3C product computers based on multidimensional data analysis according to claim 1, characterized in that: The labeling points are determined based on digital information processing. An industrial camera is used to capture an image of the labeling surface. Digital information processing is used to exclude areas containing functional components, text, or trademarks, uneven areas, and areas with low adhesion. The remaining areas are candidate areas. If the candidate area has a regular shape, the center point of the smallest bounding rectangle is used as the labeling point. If the area has an irregular shape, the geometric centroid of the area is used as the labeling point. When performing the labeling operation, it is ensured that the labeling point is precisely aligned with the center.

5. The closed-loop control method for 3C product computers based on multidimensional data analysis according to claim 1, characterized in that: The visible laser frame is a visual representation of the 3C's outline, meaning that the shape and size of the visible laser frame perfectly match the outline of the selected 3C product.

6. The closed-loop control method for 3C product computers based on multidimensional data analysis according to claim 1, characterized in that: The formula for calculating the necessary stay duration is as follows: Where t1 is the product flipping and alignment time, t2 is the bonding operation time, t3 is the labeling quality inspection time, and t4 is the production cycle redundancy time.

7. The closed-loop control method for 3C product computers based on multidimensional data analysis according to claim 1, characterized in that: The labeling quality detection method is as follows: After the labeling operation is completed, the visible laser-selected area is divided into several grid areas and a laser is projected. If the reflected signal intensity within a grid area is I0, then the grid area is covered; if the reflected signal intensity within a grid area is I, then the grid area is not covered. The coverage area within the visible laser-selected area is calculated, and the coverage area is equal to the area occupied by the grid with a reflected signal intensity of I0. The coverage rate is then calculated. If the coverage rate is greater than or equal to the set threshold, the pasting is successful; if the coverage rate is less than the set threshold, the pasting is deemed unqualified.

8. The closed-loop control method for 3C product computers based on multidimensional data analysis according to claim 1, characterized in that: The labeling success rate is the percentage of products that were successfully labeled within a certain period of time out of the total number of labeled products.

Images