Detection method and system for notebook computer shell production

Abstract

The invention discloses a detection method and system for notebook computer shell production, and relates to the technical field of computer shell production detection, and the method comprises the steps: obtaining the length of a detection scratch in real-time detection data of a notebook computer shell, determining a scratch classification interval to which the scratch belongs according to the length of the detection scratch, connecting the calibration coordinates of each related defect area block in the scratch classification interval to generate a corresponding inspection route, sequentially scanning the area blocks, quickly verifying defect high-incidence points, and dividing the notebook computer shell into a plurality of basic area blocks and special area blocks by establishing a two-dimensional coordinate system, according to the method, the scratch length range is determined, the scratch classification interval is established according to the scratch length range, the classification interval to which the scratch belongs is determined according to the real-time detection data, and then the corresponding detection route is generated, so that the targeted detection route avoids disordered scanning of the whole area, and only the high-incidence area where the scratch possibly exists is subjected to key detection; the unnecessary detection steps are greatly reduced, and the detection efficiency is remarkably improved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of computer shell production detection, and particularly relates to a notebook computer shell production detection method and system. BACKGROUND

[0002] The production and processing characteristics of notebook computer shells belong to mass production and multi-variety production. Due to high capacity allocation, situations such as die wear, die breakage and punch press abnormality occur after fine punching, causing scratches on notebook computer shells. However, the existing notebook computer shells need to undergo surface quality detection after production and manufacturing, and common detection methods include manual visual inspection or full-width detection based on image recognition. However, the traditional technology has the following problems: (1) The path is fixed, the traversal method is redundant, and the detection efficiency is low; (2) The complex structure of the defect high-risk area such as the corner, the power port and the like is not detected, and there is a risk of missing detection; (3) The defect recognition and detection path scheduling are disconnected, and dynamic detection optimization driven by data cannot be realized; once a scratch is detected, the conventional method is to recheck the entire shell, which causes waste of procedures. Therefore, a notebook computer shell production detection method and system are provided. SUMMARY

[0003] The purpose of the present application is to provide a notebook computer shell production detection method and system, which solves the technical problem that dynamic detection optimization driven by data cannot be realized, and once a scratch is detected, the conventional method is to recheck the entire shell.

[0004] A notebook computer shell production detection method and system, comprising the following steps: Step 1: A two-dimensional coordinate system is established according to the notebook computer shell, the notebook computer shell is evenly divided into a plurality of basic area blocks and special area blocks, and the calibration coordinates corresponding to each area block are obtained; Step 2: Analyze b historical scratch data of the notebook computer shell to obtain the scratch length range of the notebook computer shell, and establish a plurality of scratch classification intervals according to the scratch length range, b>4; Step 3: Analyze the historical scratch defect data corresponding to each scratch classification interval, and then obtain the related defect area blocks corresponding to each defect area block; Step 4: Obtain the detected scratch length in the real-time detection data of the notebook computer shell, determine the scratch classification interval to which the detected scratch length belongs, connect the calibration coordinates of each related defect area block in the scratch classification interval, generate a corresponding inspection route, and sequentially scan these area blocks to quickly verify the defect high-risk points.

[0005] As a further scheme of the present application, the specific way of uniformly dividing the notebook computer shell into a plurality of basic area blocks and special area blocks is as follows: The planar part of the notebook computer shell is uniformly divided into a plurality of basic area blocks, and the corners and interface parts of the notebook computer shell are taken as special area blocks.

[0006] As a further scheme of the present application, the specific way of obtaining the calibration coordinates corresponding to each area block is as follows: The center point coordinates of each basic area block are taken as the calibration coordinates of each basic area block. When the special area block is a polygon, the two-dimensional coordinates of each boundary point on the polygon are collected, and the average of the horizontal coordinates and the vertical coordinates in the two-dimensional coordinates of each boundary point on the polygon is taken as the calibration coordinates of the corresponding special area block. When the special area block is an arc, the circumscribed rectangle of the arc area is obtained first, and the coordinates of the intersection point of the diagonal lines of the circumscribed rectangle are taken as the calibration coordinates of the arc special area block. Then the calibration coordinates corresponding to each area block are obtained, and finally the calibration coordinates corresponding to each area block are marked as Ni(xi, yi) in the order from top to bottom and from left to right, where i represents different area blocks and also serves as the area block label corresponding to each area block, i = 1, 2, 3, …, a1, where a1 is the total number of area blocks, a1 is a positive integer, and a1 is greater than 2.

[0007] As a further scheme of the present application, the specific way of establishing a two-dimensional coordinate system according to the notebook computer shell is as follows: A two-dimensional coordinate system is established with the lower left corner of the notebook computer shell as the origin, and the X-axis is along the long side and the Y-axis is along the short side. The unit of the two-dimensional coordinate system is unified as millimeters.

[0008] As a further scheme of the present application, the specific way of establishing a plurality of scratch classification intervals according to the scratch length range is as follows: For each historical scratch data, the pixel coordinate point set of the scratch in the scratch data is obtained, and the total length of each scratch is obtained by accumulating the piecewise Euclidean distance. The maximum and minimum values in each total length are obtained, and the scratch length range is established according to the maximum and minimum values. The scratch length range is uniformly divided to establish a plurality of scratch classification intervals.

[0009] As a further scheme of the present application, the specific way of obtaining the related defect area block corresponding to each defect area block is as follows: S1: Randomly select one from each scratch classification interval as an analysis interval. S2: obtaining each involved area block corresponding to the analysis area from the plurality of scratch defect data of the analysis interval, and obtaining the involved times Jj corresponding to each involved area block from the plurality of scratch defect data of the analysis area block, wherein j is the involved area block corresponding to the analysis area block; the ratio between the involved times Jj corresponding to each involved area block and the total value of the involved times of each involved area block is taken as the correlation coefficient of each involved area corresponding to the analysis area block; the discrete value U and the mean value P of the correlation coefficient of each involved area are obtained, and the involved area with a correlation coefficient greater than the difference between the discrete value U and the mean value P is taken as the relevant defect area block of the analysis interval; S3: repeating steps S1 and S2 to obtain the relevant defect area block corresponding to each scratch classification interval.

[0010] As a further scheme of the present application: the specific way of generating the corresponding inspection route is: According to the real-time detection data, the real-time scratch data of the notebook computer shell is obtained, the real-time scratch data is input into step two, the detection scratch length in the real-time detection data is obtained, the detection scratch length is determined according to the detection scratch length, the calibration coordinates of each relevant defect area block of the corresponding scratch classification interval are connected according to the area block label order, and the corresponding inspection route is generated.

[0011] As a further scheme of the present application: the specific way of obtaining the circumscribed rectangle of the arc-shaped area is: The contour boundary point set of the arc-shaped area is obtained, the minimum value Xmin and the maximum value Xmax of the horizontal coordinates and the minimum value Ymin and the maximum value Ymax of the vertical coordinates are determined, and the minimum circumscribed rectangle completely surrounding the arc-shaped area is constructed, the average of the minimum value Xmin and the maximum value Xmax of the horizontal coordinates is taken as the horizontal coordinate of the intersection point coordinate of the angle line of the circumscribed rectangle, the average of the minimum value Ymin and the maximum value Ymax of the vertical coordinates is taken as the vertical coordinate of the intersection point coordinate of the angle line of the circumscribed rectangle, and the calibration coordinates of the arc-shaped special area block are obtained.

[0012] As a further scheme of the present application: the specific way of constructing the minimum circumscribed rectangle of the arc-shaped area is: A line perpendicular to the X-axis is constructed at X=Xmin and X=Xmax, and a line perpendicular to the X-axis is constructed at Y=Ymin and Y=Ymax, and the rectangle surrounded by the four lines is taken as the minimum circumscribed rectangle of the arc-shaped area.

[0013] A detection system for notebook computer shell production, specifically comprising: A calibration coordinate obtaining module, a two-dimensional coordinate system is established according to the notebook computer shell, the notebook computer shell is uniformly divided into a plurality of basic area blocks and special area blocks, and the calibration coordinates corresponding to each area block are obtained. The scratch classification interval establishing module obtains a scratch length range of the notebook computer shell, and establishes a plurality of scratch classification intervals according to the scratch length range; The related defect area block association module analyzes historical scratch defect data corresponding to each scratch classification interval respectively, and further obtains related defect area blocks corresponding to each defect area block respectively; The inspection route generating module obtains a detected scratch length in real-time detection data of the notebook computer shell, determines the scratch classification interval to which the detected scratch length belongs according to the detected scratch length, connects the calibration coordinates of each related defect area block of the scratch classification interval to which the detected scratch length belongs, and generates a corresponding inspection route.

[0014] Compared with the prior art, the present application has the following advantages: (1) The present application precisely calibrates special area blocks in the corners, interfaces and other places of the notebook computer shell which may have arc-shaped, polygonal or irregular shapes, through special geometric algorithms, such as taking the horizontal and vertical average values of the boundary point coordinates of the polygonal area as the calibration coordinates, and taking the coordinates of the intersection points of the angle lines determined by the minimum circumscribed rectangle of the arc-shaped area as the calibration coordinates, so as to ensure that these complex shape areas can be accurately identified and detected. At the same time, through analysis of historical scratch data, scratch-prone areas are determined, and these areas are focused on during real-time detection, effectively reducing the possibility of missed detection and improving product quality.

[0015] (2) Through analysis of a plurality of historical scratch data of the notebook computer shell, the scratch length range is obtained and the scratch classification intervals are established, and then the historical scratch defect data corresponding to each scratch classification interval is analyzed to obtain related defect area blocks corresponding to each defect area block respectively. During real-time detection, the classification interval to which the scratch length belongs is determined according to the real-time detection data, and then the calibration coordinates of the defect area blocks related to the classification interval are connected to generate a corresponding inspection route. This dynamic detection method based on historical data and real-time data can flexibly adjust the detection path according to the actual situation, realizes data-driven dynamic detection optimization, avoids the waste of procedures caused by re-inspecting the entire shell after detecting a scratch in the conventional method, and improves the scientificity and rationality of detection; (3) The present application establishes a two-dimensional coordinate system, divides the notebook computer shell into a plurality of basic area blocks and special area blocks, and establishes a scratch classification interval according to the scratch length range, and then determines the classification interval of the scratch according to the real-time detection data, and generates a corresponding test route. This targeted detection route avoids unordered scanning of the entire area, and only focuses on detecting high-risk areas where scratches may exist, greatly reducing unnecessary detection steps and significantly improving detection efficiency. For example, in actual production, the entire shell may need to be scanned for a long time, but after using the present scheme, only specific areas need to be scanned, and the detection time can be greatly shortened. BRIEF DESCRIPTION OF DRAWINGS

[0016] Figure 1 The figure is a schematic diagram of the method framework structure of the present application; Figure 2 The figure is a schematic diagram of the system framework structure of the present application. DETAILED DESCRIPTION

[0017] The technical solutions of the present application will be described below in conjunction with embodiments. Obviously, the described embodiments are only a part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0018] Embodiment one: please refer to Figure 1 The present application provides a detection method for notebook computer shell production, comprising the following steps: Step one: according to the notebook computer shell, a two-dimensional coordinate system is established, the notebook computer shell is evenly divided into a plurality of basic area blocks and special area blocks, and the calibration coordinates of each area block are obtained, and they are bound one by one with each area block; The specific way of establishing a two-dimensional coordinate system according to the notebook computer shell is: The left lower corner of the notebook computer shell is taken as the origin, a two-dimensional coordinate system is established, the X axis is along the long side, and the Y axis is along the short side, that is, when the notebook computer shell is placed, the physical vertex of the left lower corner is taken as the origin. In the process of setting the origin, the positioning hole or geometric vertex of the shell edge can be calibrated to ensure the position fixed in batch detection, and the unit of the two-dimensional coordinate system is unified as millimeter; The specific way of obtaining the calibration coordinates of each area block is: The planar part of the notebook computer shell is evenly divided into a plurality of basic area blocks, and the center point coordinates of each basic area block are taken as the calibration coordinates of each basic area block; The corners, ports, and other parts of the laptop casing that may be curved, polygonal, or irregular in shape are designated as special areas. When the special area is a polygon, such as the power interface area, the rectangular area of ​​the USB interface, the multi-interface cluster area, the complex corner transition area, etc., the two-dimensional coordinates of each boundary point on the polygon are collected by the high-definition image or CAD model of the shell processed by the edge detection algorithm, and the average of the horizontal and vertical coordinates of each boundary point on the polygon is used as the calibration coordinates of the corresponding special area. For example, if the two-dimensional coordinates of each boundary point on the polygon are (280, 20), (320, 20), (320, 40), and (280, 40), then the mean values ​​of the x-coordinate and y-coordinate of each boundary point on the polygon are Xp = (280+320+320+280) / 4 = 300 and Yp = (20+20+40+40) / 4 = 30, then the calibrated coordinates of the special region block of the polygon are (300, 30). When a special region is arc-shaped, such as a rounded transition area at the corner, the first step is to obtain the bounding rectangle of the arc-shaped region. That is, the boundary of the arc-shaped region is defined by the minimum bounding rectangle, which is defined as the minimum bounding rectangle completely enclosing the arc-shaped region and is parallel to the X-axis and Y-axis of the two-dimensional coordinate system established in step one. The specific method is as follows: edge detection processing is performed on the arc-shaped area in the high-definition image of the laptop shell (such as using the Canny operator), or the set of contour boundary points of the arc-shaped area is directly obtained from the CAD model. These are existing and mature technologies, so they will not be elaborated on here. All coordinates are normalized to the established two-dimensional coordinate system. The minimum and maximum values ​​of the horizontal coordinates Xmin and Ymax, and the minimum and maximum values ​​of the vertical coordinates Ymin and Ymax are determined in the two-dimensional coordinate system. The minimum bounding rectangle that completely surrounds the arc-shaped area is constructed in this way. The average value of the minimum horizontal coordinate Xmin and the maximum value Xmax is used as the horizontal coordinate Xc of the intersection of the corners of the bounding rectangle, and the average value of the minimum and maximum vertical coordinates Ymin and Ymax is used as the vertical coordinate Yc of the intersection of the corners of the bounding rectangle. Thus, the calibration coordinates (Xc, Yc) of the arc-shaped special area block are obtained. The specific method for constructing the minimum bounding rectangle that completely encloses the arc-shaped region is as follows: Determine the minimum x-coordinate (Xmin) and maximum x-coordinate (Xmax) and the minimum y-coordinate (Ymin) and maximum y-coordinate (Ymax) in the two-dimensional coordinate system. Once Xmin, Xmax, Ymin, and Ymax are determined, a line perpendicular to the X-axis is constructed at X=Xmin and X=Xmax, and a line perpendicular to the X-axis is constructed at Y=Ymin and Y=Ymax. The rectangle formed by these four lines is the smallest bounding rectangle that completely encloses the arc-shaped region. This is because it is determined by the coordinates of the leftmost, rightmost, bottommost, and topmost points of the arc-shaped region. Therefore, it must be able to enclose all points and is the smallest rectangle with its sides parallel to the coordinate axes. For example, if the circumscribed rectangle of the arc-shaped special region has Xmin=347, Xmax=350, Ymin=247, and Ymax=250, then the coordinates of the intersection of the corners of the circumscribed rectangle are (Xc, Yc): Xc=(347+350) / 2=348.5, Yc=(247+250) / 2=248.5, that is, the calibrated coordinates of the arc-shaped special region are (348.5, 248.5). The system standardizes the calibration of complex edge and corner regions such as arcs and polygons, using the average of boundary points or the intersection of the diagonals of the circumscribed rectangle as calibration coordinates. This allows irregular structures to be incorporated into the unified path generation system, improving the system's structural adaptability.

[0019] In this way, even irregular areas such as arcs can be assigned a precise and unique geometric center point as their calibration coordinates, which facilitates management, positioning and data analysis throughout the detection system. The calibration coordinates corresponding to the basic region block and the special region block are obtained through the above method. Finally, the calibration coordinates corresponding to each region block are marked as Ni(xi, yi) in order from top to bottom and from left to right. Here, i represents different region blocks and also serves as the region block number corresponding to each region block. i = 1, 2, 3, ..., a1, where a1 is the total number of region blocks, a1 is a positive integer, and a1 is greater than 2. By establishing a standard two-dimensional coordinate system with the lower left corner as the origin, and dividing the laptop shell into basic area blocks and special area blocks, the shell plane is divided into regular basic area blocks, while complex areas such as corners and interfaces are marked as special area blocks. This effectively improves the spatial organization of the inspection area, achieves the unification of the area data structure, facilitates subsequent defect location and path scheduling, calculates the calibration coordinates through the center point or the circumscribed rectangle, and the special area calibration algorithm (such as the circumscribed rectangle method) adapts to complex shapes, avoids manual calibration errors, unifies the coordinate system and calibration process, and supports the repeatability of batch inspection.

[0020] Step 2: Obtain b historical scratch data points for the laptop casing and analyze them. Based on the analysis results, determine the scratch length range of the laptop casing and establish scratch classification intervals based on the scratch length range. The specific method is as follows: For each historical scratch data, obtain the set of pixel coordinates of the scratch in the scratch data, and use the segmented Euclidean distance to accumulate to obtain the total length of each scratch. Obtain the maximum and minimum values ​​of each total length, and establish the scratch length range based on the maximum and minimum values ​​of the total length. Divide the scratch length range evenly into multiple scratch classification intervals. It should be noted that before performing calculations, pixel coordinates need to be multiplied by the physical distance conversion factor of pixels (e.g., 1 pixel = 0.05 mm) to convert the pixel coordinates into millimeter units, which facilitates subsequent calculations. For example, when the set of pixel coordinates of the scratches in the scratch data is {(x1, y1), (x2, y2), (x3, y3), ..., (xn, yn)}, where n represents different pixels, n = 1, 2, 3, ..., a2, where a2 is the total number of pixels, a2 is a positive integer, and a2 is greater than 2; Through the formula: Calculate the scratch length L1 corresponding to the scratch, where (xi, yi) is any pixel coordinate in the set of pixel coordinate points; Using the above calculation method, the scratch length Lc corresponding to each of the b historical scratch data is calculated, where c refers to any one of the b scratch lengths, c=1, 2, 3, ..., b, b≥4; Obtain the maximum value Lmax and the minimum value Lmin in Lc, and establish the scratch length range [Lmin, Lmax] to evenly divide it into multiple scratch classification intervals, such as [Lmin, L1), [L1, L2)...(Lr, Lmax], where Lr is any value in the established scratch length range [Lmin, Lmax]. By collecting historical scratch data and calculating its physical length, multiple scratch length classification intervals are established, enabling the system to quickly locate potentially high-risk areas based on the scratch length detected in real time, effectively improving the system's response speed and accuracy to defect types.

[0021] Step 3: Obtain multiple historical scratch defect data corresponding to the scratch classification intervals, analyze them, and then obtain the relevant defect area blocks corresponding to each defect area block. The specific method is as follows: S1: Randomly select one of the scratch classification intervals as the analysis interval; S2: Obtain each involved area block j corresponding to the analysis area from multiple scratch defect data in the analysis interval, and obtain the number of times each involved area block is involved from multiple scratch defect data of the analysis area block, and mark them as Jj, where j is the involved area block corresponding to the analysis area block; The ratio between the number of times Jj involved in each involved region block and the total number of times involved in each involved region block is used as the correlation coefficient for each involved region in the analysis region block. Obtain the discrete value U and mean P of the correlation coefficient corresponding to each involved area. The involved areas with a correlation coefficient greater than the difference between the discrete value U and the mean P are taken as the relevant defect area blocks of the analysis interval, and the relevant defect area blocks are bound to the analysis interval. S3: Repeat steps S1 and S2 to obtain the relevant defect area blocks corresponding to each scratch classification interval; By analyzing multiple historical scratch data of laptop casings, the scratch length range is obtained and scratch classification intervals are established. Then, the historical scratch defect data corresponding to each scratch classification interval is analyzed to obtain the relevant defect area blocks corresponding to each defect area block. During real-time detection, the classification interval to which the scratch length belongs is determined based on the real-time detection data. Then, the calibration coordinates of the defect area blocks related to the classification interval are connected to generate the corresponding inspection route. This dynamic detection method based on historical and real-time data can flexibly adjust the detection path according to the actual situation, realizing data-driven dynamic detection optimization.

[0022] Randomly select classification intervals, count the number of scratches in the affected area blocks, calculate the correlation coefficient (number of scratches / total value), and screen areas with a higher frequency than the difference between the discrete value and the mean as high-incidence areas. By statistically correlating the scratch distribution frequency with the area blocks, establish a set of related defect area blocks under each interval. Then, by calculating the correlation coefficient of each area block and combining it with the mean and discrete value, select key detection areas, effectively avoid resource dispersion, reduce false detections, identify high-risk defect areas (such as power interfaces), and reduce the waste of detection resources in low-risk areas.

[0023] Step 4: When a new laptop casing needs to be inspected, the previously established data and model will be used to generate a corresponding inspection route, obtain real-time inspection data of the laptop casing, obtain real-time scratch data of the laptop casing based on the real-time inspection data, input the real-time scratch data into Step 2, obtain the detected scratch length in the real-time inspection data, determine the scratch classification interval to which it belongs based on the detected scratch length, connect the calibration coordinates of each relevant defect area block in the scratch classification interval according to the area block number sequence to generate a corresponding inspection route, scan these area blocks in sequence according to the inspection route, quickly verify the high-incidence point of defects, significantly improve the inspection accuracy and efficiency, and are suitable for the quality control scenario of high-precision consumer electronic casings, avoiding the omission of scratch defect areas in the inspection; Based on the relevant area blocks associated with the classification interval of the real-time scratch, the system automatically extracts the coordinates of each area and generates detection paths by sorting the area block numbers or using the shortest path principle (such as the TSP algorithm), thus realizing "defect-oriented path planning" and significantly improving path efficiency and coverage.

[0024] Example 2 Please see Figure 2 As shown, this embodiment also provides an inspection system for the production of laptop casings. This system applies the aforementioned inspection method for the production of laptop casings, specifically including: The calibration coordinate acquisition module establishes a two-dimensional coordinate system with the lower left corner of the laptop shell as the origin. The X-axis is along the long side and the Y-axis is along the short side. The unit of the two coordinate systems is uniformly millimeters. The coordinates of the center point of each basic area block are used as the calibration coordinates of each basic area block. When the special region is a polygon, the two-dimensional coordinates of each boundary point on the polygon are collected, and the average of the x-coordinates and y-coordinates of each boundary point on the polygon is used as the calibration coordinates of the corresponding special region. When the special region is an arc, the set of contour boundary points of the arc region is first obtained, and its minimum x-coordinate Xmin and maximum xmax and minimum y-coordinate Ymin and maximum ymax are determined. The minimum bounding rectangle that completely surrounds the arc region is constructed in this way. The average of the minimum x-coordinate Xmin and maximum xmax is used as the x-coordinate of the intersection of the corners of the bounding rectangle, and the average of the minimum y-coordinate Ymin and maximum ymax is used as the y-coordinate of the intersection of the corners of the bounding rectangle. Thus, the calibration coordinates of the arc-shaped special region are obtained, and the calibration coordinates corresponding to the basic region and the special region are obtained respectively. Finally, the calibration coordinates corresponding to each region are marked as Ni(xi, yi) in order from top to bottom and from left to right. The scratch classification interval establishment module obtains the scratch length range of the laptop shell and establishes multiple scratch classification intervals based on the scratch length range; The related defect area block association module analyzes the historical scratch defect data corresponding to each scratch classification interval to obtain the related defect area blocks corresponding to each defect area block. The specific method for obtaining the related defect area blocks corresponding to each defect area block is as follows: S1: Randomly select one of the scratch classification intervals as the analysis interval; S2: Obtain each involved area block j corresponding to the analysis area from multiple scratch defect data in the analysis interval. At the same time, obtain the number of involvements Jj corresponding to each involved area block from multiple scratch defect data in the analysis area block, where j is the involved area block corresponding to the analysis area block. The ratio between the number of involvements Jj corresponding to each involved area block and the total number of involvements of each involved area block is used as the correlation coefficient corresponding to each involved area in the analysis area block. Obtain the discrete value U and mean P of the correlation coefficient corresponding to each involved area. The involved area with a correlation coefficient greater than the difference between the discrete value U and the mean P is taken as the relevant defect area block of the analysis interval. S3: Repeat steps S1 and S2 to obtain the relevant defect area blocks corresponding to each scratch classification interval; The inspection route generation module obtains the length of detected scratches from the real-time inspection data of the laptop shell, determines the scratch classification interval to which the scratch belongs based on the length of the detected scratch, and connects the calibration coordinates of each relevant defect area block in the scratch classification interval to generate the corresponding inspection route.

[0025] By establishing a two-dimensional coordinate system, the laptop casing is divided into multiple basic and special areas. Scratch classification intervals are established based on scratch length ranges, and real-time detection data determines the corresponding classification interval, thus generating a corresponding inspection route. This targeted inspection route avoids disordered scanning of the entire area, focusing only on high-risk areas for scratches, significantly reducing unnecessary inspection steps and greatly improving efficiency. For example, in actual production, a full scan of the entire casing might have taken a long time, but with this solution, only specific areas need to be scanned, drastically reducing inspection time.

[0026] Example 3 As a third embodiment of the present invention, in specific implementation, compared with embodiments one and two, the technical solution of this embodiment is to combine the solutions of embodiments one and two.

[0027] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters and thresholds in the formulas are set by those skilled in the art according to the actual situation.

[0028] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A testing method for laptop casing production, characterized in that, Includes the following steps: Step 1: Establish a two-dimensional coordinate system based on the laptop shell, divide the laptop shell evenly into multiple basic area blocks and special area blocks, and obtain the calibration coordinates corresponding to each area block; Step 2: Analyze b historical scratch data of the laptop shell to obtain the scratch length range of the laptop shell, and establish multiple scratch classification intervals based on the scratch length range, where b≥4; Step 3: Analyze the historical scratch defect data corresponding to each scratch classification interval to obtain the relevant defect area blocks corresponding to each defect area block; Step 4: Obtain the length of the detected scratches from the real-time inspection data of the laptop casing. Determine the scratch classification interval to which the scratch belongs based on the scratch length. Connect the calibration coordinates of each relevant defect area block in the scratch classification interval to generate the corresponding inspection route. Scan these area blocks in sequence to quickly verify the high-incidence points of defects.

2. The testing method for producing a laptop casing according to claim 1, characterized in that, The specific method for evenly dividing the laptop casing into multiple basic and special areas is as follows: The flat part of the laptop casing is evenly divided into multiple basic areas, and the corners, ports, and other curved or polygonal areas of the laptop casing are designated as special areas.

3. The testing method for laptop casing production according to claim 2, characterized in that, The specific method for obtaining the calibration coordinates corresponding to each region block is as follows: The coordinates of the center point of each basic region block are used as the calibration coordinates of each basic region block; When the special region block is a polygon, the two-dimensional coordinates of each boundary point on the polygon are collected, and the average of the x and y coordinates of each boundary point on the polygon is used as the calibration coordinates of the corresponding special region block. When the special region block is arc-shaped, the circumscribed rectangle of the arc-shaped region is obtained first, and the coordinates of the intersection of the diagonals of the circumscribed rectangle are used as the calibration coordinates of the arc-shaped special region block. Then, the calibration coordinates corresponding to the basic region block and the special region block are obtained respectively. Finally, the calibration coordinates corresponding to each region block are marked as Ni(xi, yi) in order from top to bottom and from left to right, where i represents different regions blocks and also serves as the region block number corresponding to each region block. i = 1, 2, 3, ..., a1, where a1 is the total number of regions blocks, a1 is a positive integer, and a1 is greater than 2.

4. The testing method for producing a laptop casing according to claim 1, characterized in that, The specific method for establishing a two-dimensional coordinate system based on the laptop casing is as follows: Establish a two-dimensional coordinate system with the lower left corner of the laptop casing as the origin. The X-axis is along the long side and the Y-axis is along the short side. The unit of the two coordinate systems is millimeters.

5. The testing method for producing a laptop casing according to claim 3, characterized in that, The specific method for establishing multiple scratch classification intervals based on scratch length range is as follows: For each historical scratch data, obtain the set of pixel coordinates of the scratch in the scratch data, and use the segmented Euclidean distance to accumulate to obtain the total length of each scratch. Obtain the maximum and minimum values ​​of each total length, and establish the scratch length range based on the maximum and minimum values ​​of the total length. Then, uniformly divide the scratch length range to establish multiple scratch classification intervals.

6. The testing method for producing a laptop casing according to claim 5, characterized in that, The specific method for obtaining the corresponding defect region blocks for each defect region block is as follows: S1: Randomly select one of the scratch classification intervals as the analysis interval; S2: Obtain each involved area block j corresponding to the analysis area from multiple scratch defect data in the analysis interval. At the same time, obtain the number of involvements Jj corresponding to each involved area block from multiple scratch defect data in the analysis area block, where j is the involved area block corresponding to the analysis area block. The ratio between the number of involvements Jj corresponding to each involved area block and the total number of involvements of each involved area block is used as the correlation coefficient corresponding to each involved area in the analysis area block. Obtain the discrete value U and mean P of the correlation coefficient corresponding to each involved area. The involved area with a correlation coefficient greater than the difference between the discrete value U and the mean P is taken as the relevant defect area block of the analysis interval. S3: Repeat steps S1 and S2 to obtain the relevant defect area blocks corresponding to each scratch classification interval.

7. The testing method for producing a laptop casing according to claim 6, characterized in that, The specific method for generating the corresponding inspection route is as follows: Real-time scratch data of the laptop casing is obtained based on real-time detection data. The real-time scratch data is input into step two to obtain the detected scratch length in the real-time detection data. The scratch classification interval to which it belongs is determined based on the detected scratch length. The calibration coordinates of each relevant defect area block in the scratch classification interval are connected according to the area block number order to generate the corresponding inspection route.

8. The testing method for producing a laptop casing according to claim 3, characterized in that, The specific method for obtaining the bounding rectangle of the arc-shaped region is as follows: Obtain the set of boundary points of the arc-shaped region, determine its minimum x-coordinate Xmin and maximum xmax, and minimum y-coordinate Ymin and maximum ymax. Construct the minimum bounding rectangle that completely encloses the arc-shaped region. Use the average of the minimum x-coordinate Xmin and maximum xmax as the x-coordinate of the intersection of the corners of the bounding rectangle, and use the average of the minimum y-coordinate Ymin and maximum ymax as the y-coordinate of the intersection of the corners of the bounding rectangle. This will give you the calibration coordinates of the arc-shaped special region block.

9. The testing method for producing a laptop casing according to claim 8, characterized in that, The specific method for constructing the minimum bounding rectangle of the arc-shaped region is as follows: Construct a line perpendicular to the X-axis at X=Xmin and X=Xmax respectively, and construct a line perpendicular to the X-axis at Y=Ymin and Y=Ymax respectively. The rectangle enclosed by these four lines serves as the minimum bounding rectangle of the arc-shaped region.

10. A testing system for manufacturing laptop casings, characterized in that, The system applies the inspection method for manufacturing a laptop casing as described in any one of claims 1-9, specifically including: The calibration coordinate acquisition module establishes a two-dimensional coordinate system based on the laptop shell, divides the laptop shell into multiple basic area blocks and special area blocks, and obtains the calibration coordinates corresponding to each area block. The scratch classification interval establishment module obtains the scratch length range of the laptop shell and establishes multiple scratch classification intervals based on the scratch length range; The related defect area block association module analyzes the historical scratch defect data corresponding to each scratch classification interval, and then obtains the related defect area blocks corresponding to each defect area block. The inspection route generation module obtains the length of detected scratches from the real-time inspection data of the laptop shell, determines the scratch classification interval to which the scratch belongs based on the length of the detected scratch, and connects the calibration coordinates of each relevant defect area block in the scratch classification interval to generate the corresponding inspection route.

Images