CN118424122A - Online film thickness detection method and system based on quality judgment standard - Google Patents

Abstract

The invention provides an online film thickness detection method and system based on a quality judgment standard, which relate to the field of film thickness detection, and the online film thickness detection method based on the quality judgment standard comprises the following steps: setting a quality judgment standard of film production based on a preset film production standard; respectively carrying out three-dimensional point cloud scanning on the upper surface and the lower surface of the film to be detected by using a laser scanner to respectively obtain upper point cloud data and lower point cloud data; respectively extracting surface profiles of the obtained upper point cloud data and lower point cloud data to obtain upper surface profile data and lower surface profile data; and respectively calculating the thickness of the film at different positions according to the upper surface profile data and the lower surface profile data, and evaluating the film based on the quality judgment standard. The invention can automatically evaluate the film, reduce the interference of human factors and improve the objectivity and accuracy of the detection result.

Description

An online film thickness detection method and system based on quality judgment criteria

Technical Field

The present invention relates to the field of film thickness detection, and in particular to an online film thickness detection method and system based on quality judgment criteria.

Background technique

In the display touch panel manufacturing industry, the demand for product performance makes the precise coating of multiple layers of thin films on the surface of the substrate particularly important. These films, including conductive films, anti-reflective layers or protective films, not only improve touch responsiveness and display quality, but also enhance the durability and environmental adaptability of the panel. For different types of touch panels, such as capacitive or resistive, the thickness of each layer of film must be precisely controlled to ensure compliance with specific technical and functional requirements; therefore, online film thickness detection technology plays a vital role in ensuring product quality; by real-time monitoring of the thickness of each layer of film, this technology can instantly identify any deviations in the production process, allowing instant adjustments to the manufacturing process, thereby significantly reducing the production of unqualified products. Online film thickness detection not only improves production efficiency, but also helps companies achieve cost-effectiveness by reducing material waste and improving product consistency. In addition, precise film thickness control is essential for the functionality and long-term stability of touch panels. For example, the thickness of the conductive film of a capacitive touch panel directly affects the sensitivity of the device and the user's interactive experience. Similarly, the proper application of anti-reflective and protective films can protect the device from scratches and external environmental damage, extending its service life.

At present, in the existing film thickness detection technology, although its automation and advancement have brought significant benefits, this existing film thickness detection technology also faces a series of defects. The existing technology needs to acquire images at multiple shooting angles, and this image detection relies on the stability and uniformity of the lighting and ultraviolet light source to ensure the image quality; light source fluctuations or uneven distribution will directly affect the quality of image acquisition, and further affect the measurement results of film thickness.

Currently, no effective solution has been proposed for the problems in the related technologies.

Summary of the invention

In view of this, and in response to the problems in the related art, the present invention provides an online film thickness detection method and system based on quality judgment standards to solve the above-mentioned problem that the film thickness detected by image depends on the stability and uniformity of the lighting and ultraviolet light source, and the fluctuation or uneven distribution of the light source will directly affect the quality of image acquisition.

In order to solve the above problems, the specific technical solutions adopted by the present invention are as follows:

According to one aspect of the present invention, an online film thickness detection method based on a quality judgment standard is provided, and the online film thickness detection method based on a quality judgment standard comprises the following steps:

S1. Based on the pre-set film production standards, set the quality judgment standards for film production;

S2, using a laser scanner to perform three-dimensional point cloud scanning on the upper and lower surfaces of the film to be inspected, respectively, to obtain upper point cloud data and lower point cloud data;

S3, extracting surface contours of the obtained upper point cloud data and lower point cloud data respectively to obtain upper surface contour data and lower surface contour data;

S4. Calculate the thickness of the film at different positions according to the upper surface profile data and the lower surface profile data, and evaluate the film based on the quality judgment standard.

Preferably, surface contour extraction is performed on the obtained upper point cloud data and the lower point cloud data respectively, and obtaining the upper surface contour data and the lower surface contour data comprises the following steps:

S31, preprocessing the upper point cloud data and the lower point cloud data respectively, wherein the preprocessing includes filtering and smoothing;

S32, respectively calculating the curvature value of each data point in the preprocessed upper point cloud data and the lower point cloud data;

S33, according to the curvature value of each data point, respectively determine the discrete degree of the preprocessed upper point cloud data and the lower point cloud data, and set the curvature threshold;

S34, extracting the film boundary line from the preprocessed upper point cloud data and the lower point cloud data respectively according to the set curvature threshold;

S35 , determining upper surface contour data and lower surface contour data according to the film boundary lines of the preprocessed upper point cloud data and lower point cloud data.

Preferably, respectively calculating the curvature value of each data point in the preprocessed upper point cloud data and the lower point cloud data comprises the following steps:

S321, for each data point in the preprocessed upper point cloud data and the lower point cloud data, calculate the Euclidean distance from the data point to all other points, and select M neighboring points closest to the data point;

S322, for each data point and its selected M neighboring points, obtain the normal vector of the data point by calculating the covariance matrix of the neighboring points;

S323, respectively calculating the angle between the normal vector of each data point and the normal vector of its neighboring points and calculating the position vector between each data point and its neighboring points, and determining the angle between the position vector and the normal vector of each data point;

S324, for each data point, calculating the normal curvature of each data point relative to each of its neighboring points using a normal curvature calculation formula;

S325. Based on the Euler formula, determine the functional relationship between the normal curvature and the principal curvature, and solve the first principal curvature and the second principal curvature of each data point by a least squares optimization method;

S326. Multiply the first principal curvature and the second principal curvature of each data point to obtain the curvature value of each data point.

Preferably, determining the discreteness of the preprocessed upper point cloud data and the lower point cloud data according to the curvature value of each data point, and setting the curvature threshold comprises the following steps:

S331, calculating the discrete value of each data point according to the curvature value of each data point in the preprocessed upper point cloud data and the lower point cloud data;

S332, respectively summing the discrete values of all data points in the preprocessed upper point cloud data and the lower point cloud data, and squaring the summed values to obtain first discreteness of the upper point cloud data and the lower point cloud data;

S333, respectively calculating the discrete average values of all data points in the preprocessed upper point cloud data and the lower point cloud data, and squaring the discrete average values to obtain the second discreteness of the upper point cloud data and the lower point cloud data;

S334. Compare the first discreteness and the second discreteness of the preprocessed upper point cloud data and the lower point cloud data respectively. If the first discreteness is smaller than the second discreteness, select the minimum curvature value of the data points in the preprocessed upper point cloud data and the lower point cloud data respectively as the curvature threshold; otherwise, select the average value of all data points in the preprocessed upper point cloud data and the lower point cloud data respectively as the curvature threshold.

Preferably, the calculation formula for calculating the discrete value of each data point is:

Where, _Fi represents the discrete value of data point i;

_Ki represents the curvature value of data point i;

max(K _s ) represents the maximum and minimum values of the curvature among all data points.

Preferably, according to the set curvature threshold, extracting the film boundary line from the preprocessed upper point cloud data and the lower point cloud data respectively comprises the following steps:

S341, traversing each data point in the preprocessed upper point cloud data and the lower point cloud data, and for each data point, checking whether its curvature value exceeds a set curvature threshold;

S342, taking data points whose curvature values exceed a threshold in the preprocessed upper point cloud data and lower point cloud data as boundary points;

S343. Use the minimum distance method to connect adjacent boundary points to obtain a continuous boundary line, and use it as the boundary line of the film.

Preferably, calculating the thickness of the film at different positions according to the upper surface profile data and the lower surface profile data, and evaluating the film based on the quality judgment standard comprises the following steps:

S41, aligning the upper surface contour data and the lower surface contour data in a preset coordinate system respectively;

S42, after the data are aligned, for each data point of the upper surface contour data, find the nearest data point in the corresponding lower surface contour data, and calculate the vertical distance between the two data point pairs;

S43, respectively comparing the vertical distance of each data point pair with the standard film thickness, and evaluating the quality of the film based on the comparison result.

Preferably, aligning the upper surface contour data and the lower surface contour data in a preset coordinate system to perform point cloud data alignment includes the following steps:

S411, obtaining the relative position relationship between two groups of laser scanners that collect upper surface profile data and lower surface profile data;

S412, converting the upper surface contour data and the lower surface contour data into a preset coordinate system respectively;

S413, performing point cloud data alignment on the upper surface contour data and the lower surface contour data according to the relative position relationship between the two groups of laser scanners.

Preferably, comparing the vertical distance of each data point pair with the standard film thickness, and evaluating the quality of the film based on the comparison result comprises the following steps:

S431, respectively calculating the difference between the vertical distance of each data point pair and the standard film thickness;

S432, comparing the difference with a preset error range, if the difference is greater than the preset error range, it is considered that the film thickness at the location of the data point pair does not meet the standard, otherwise, it is considered that the film thickness at the location of the data point pair meets the standard;

S433, counting the number of all pairs of data points that meet and do not meet the requirements, and evaluating the overall quality of the film based on the statistical results.

According to another aspect of the present invention, there is provided an online film thickness detection system based on a quality judgment standard, the online film thickness detection system based on a quality judgment standard comprising: a standard setting module, a data acquisition module, a contour extraction module and a quality assessment module, and the standard setting module, the data acquisition module, the contour extraction module and the quality assessment module are sequentially connected;

A standard setting module, used to set quality judgment standards for film production based on pre-set film production standards;

A data acquisition module is used to use a laser scanner to perform three-dimensional point cloud scanning on the upper and lower surfaces of the film to be inspected, respectively, to obtain upper point cloud data and lower point cloud data;

A contour extraction module is used to extract surface contours of the obtained upper point cloud data and lower point cloud data respectively to obtain upper surface contour data and lower surface contour data;

The quality assessment module is used to calculate the thickness of the film at different positions according to the upper surface profile data and the lower surface profile data, and to assess the film based on the quality judgment standard.

Compared with the prior art, the present invention provides an online film thickness detection method and system based on quality judgment criteria, which has the following beneficial effects:

(1) The present invention can obtain the thickness information of the film in real time during the production process through online detection, without waiting for the completion of production to perform offline detection, which greatly improves the production efficiency and makes the quality control in the production process more timely and accurate. The laser scanner is used for three-dimensional point cloud scanning without direct contact with the film, thereby avoiding possible physical damage or contamination. By extracting the surface contour and calculating the thickness of the point cloud data, the method can realize an automated and intelligent detection process; combined with the preset quality judgment standard, the film can be automatically evaluated, reducing the interference of human factors, and improving the objectivity and accuracy of the detection results.

(2) The present invention can remove noise and outliers in the point cloud data and improve the quality of the data through filtering and smoothing in the preprocessing step. By calculating the curvature value of each data point and extracting the film boundary line according to the curvature threshold, the surface contour of the film can be accurately identified, and the boundary between the film and the surrounding environment can be effectively distinguished to avoid misjudgment or omission. The curvature threshold is set according to the discrete degree of the point cloud data, so that the threshold setting is more reasonable and adaptive. By comparing the first discrete degree and the second discrete degree, a more appropriate threshold can be selected, thereby more accurately extracting the film boundary line.

(3) The present invention aligns the point cloud data of the upper surface contour data and the lower surface contour data in a preset coordinate system, thereby ensuring that the corresponding data points are accurately matched, and then obtaining an accurate vertical distance, that is, the thickness of the film. By comparing the vertical distance of each data point pair with the standard film thickness and evaluating the quality of the film based on the comparison result, the film thickness at different positions can be comprehensively and carefully inspected, which helps to improve the accuracy and efficiency of film thickness detection and provide a strong guarantee for quality control of film production.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

FIG1 is a flow chart of an online film thickness detection method based on a quality judgment standard according to an embodiment of the present invention;

FIG2 is a principle block diagram of an online film thickness detection system based on a quality judgment standard according to an embodiment of the present invention;

FIG. 3 is a schematic diagram of the structure of a computer device according to an embodiment of the present invention.

In the figure:

1. Standard setting module; 2. Data acquisition module; 3. Contour extraction module; 4. Quality assessment module.

Detailed ways

In order to enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this application.

According to an embodiment of the present invention, an online film thickness detection method and system based on a quality judgment standard are provided.

The present invention is further described in conjunction with the accompanying drawings and specific embodiments. As shown in FIG1 , according to one embodiment of the present invention, an online film thickness detection method based on a quality judgment standard is provided. The online film thickness detection method based on a quality judgment standard comprises the following steps:

S1. Based on the pre-set film production standards, set the quality judgment standards for film production;

It should be noted that the pre-set quality judgment standards include standard film thickness and error range; standard film thickness is the core indicator of film production, which represents the ideal thickness of the film and is usually determined based on product usage requirements, performance requirements, and production processes; the error range is an indicator to measure the fluctuation range of film thickness, which represents the allowable deviation between the actual film thickness and the standard film thickness. The setting of the error range needs to take into account factors such as the stability of the production process, equipment accuracy, and raw material quality to ensure that the fluctuation of film thickness can be controlled within an acceptable range during the actual production process.

S2, using a laser scanner to perform three-dimensional point cloud scanning on the upper and lower surfaces of the film to be inspected, respectively, to obtain upper point cloud data and lower point cloud data;

It should be noted that the three-dimensional point cloud scanning of the upper and lower surfaces of the film to be inspected is performed using two sets of laser scanners, and before scanning with the laser scanners, the positional relationship between the two sets of laser scanners needs to be determined.

S3, extracting surface contours of the obtained upper point cloud data and lower point cloud data respectively to obtain upper surface contour data and lower surface contour data;

As a preferred embodiment, surface contour extraction is performed on the obtained upper point cloud data and lower point cloud data respectively, and obtaining the upper surface contour data and the lower surface contour data includes the following steps:

S31, preprocessing the upper point cloud data and the lower point cloud data respectively, wherein the preprocessing includes filtering and smoothing;

It should be noted that filtering is mainly used to remove noise points in point cloud data; these noise points may come from errors in the scanning process, environmental interference or equipment instability; filtering can be achieved through statistical methods, distance-based methods or model-based methods.

Smoothing processing focuses on the overall shape and continuity of the point cloud data. Due to the accuracy limitations of the scanning equipment or the microscopic unevenness of the surface of the object being measured, the original point cloud data may have some fluctuations or mutations. Smoothing processing can make the point cloud data smoother and closer to the actual shape by weighted averaging of adjacent points, fitting surfaces or other mathematical methods.

S32, respectively calculating the curvature value of each data point in the preprocessed upper point cloud data and the lower point cloud data;

As a preferred implementation, respectively calculating the curvature value of each data point in the preprocessed upper point cloud data and the lower point cloud data includes the following steps:

S321, for each data point in the preprocessed upper point cloud data and the lower point cloud data, calculate the Euclidean distance from the data point to all other points, and select M neighboring points closest to the data point;

It should be noted that a target data point is selected from the preprocessed upper point cloud data or lower point cloud data. For the selected data point, the Euclidean distance from it to all other points in the point cloud is calculated. According to the calculated distance, the distances are sorted and the smallest M distances are selected.

S322, for each data point and its selected M neighboring points, obtain the normal vector of the data point by calculating the covariance matrix of the neighboring points;

It should be noted that, for each data point and its selected M neighboring points, obtaining the normal vector of the data point by calculating the covariance matrix of the neighboring points includes the following steps:

Calculate the coordinate mean of the data point and its M neighboring points; the mean is the average of the coordinates of all data points and is used to determine the center position of the local point cloud;

The covariance matrix is constructed using the mean and the coordinates of the local neighborhood points; the covariance matrix describes the directionality and diffusion of the point cloud in space;

Perform eigenvalue decomposition on the covariance matrix to find the corresponding eigenvalues and eigenvectors; the eigenvector represents the main direction of the data point set, and the size of the eigenvalue represents the degree of variation in that direction;

The eigenvector corresponding to the minimum eigenvalue is selected as the normal vector of the data point. The normal vector is usually the eigenvector corresponding to the minimum eigenvalue because it represents the direction in which the data point is least diffused, that is, the normal direction of the local surface.

S323, respectively calculating the angle between the normal vector of each data point and the normal vector of its neighboring points and calculating the position vector between each data point and its neighboring points, and determining the angle between the position vector and the normal vector of each data point;

It should be noted that for each data point and its neighborhood point, the angle between the normal vectors is calculated using the dot product and the modulus; the position vector represents the difference between the coordinates of the data point and the coordinates of the neighborhood point.

S324, for each data point, calculating the normal curvature of each data point relative to each of its neighboring points using a normal curvature calculation formula;

The calculation formula of normal curvature is:

Where G represents the normal curvature of data point A relative to its neighborhood point B;

β represents the angle between the normal vector of data point A and the normal vector of neighboring point B;

α represents the angle between the position vector of data point A relative to its neighborhood point B and the normal vector of data point A;

S325, based on the Euler formula, determine the functional relationship between the normal curvature and the principal curvature, and solve the first principal curvature and the second principal curvature of each data point by the least squares optimization method;

Specifically, the Euler formula is a basic formula that describes the relationship between the normal curvature of any point on a surface and its two principal curvatures (the first principal curvature k1 and the second principal curvature k2) at that point, specifically:

G＝k1cos ² (θ)+k2sin ² (θ);

In the formula, G represents the normal curvature of data point A relative to its neighborhood point B, k1 represents the first principal curvature, k2 represents the second principal curvature, and θ represents the angle between the tangent line of the normal section of data point A through neighborhood point B and the main direction;

Putting the Euler formula into the least squares framework, the goal is to minimize the error between the predicted normal curvature and the actual calculated normal curvature; and the generated least squares problem is as follows:

By solving this least squares problem form, the first principal curvature k1 and the second principal curvature k2 can be obtained.

S326. Multiply the first principal curvature and the second principal curvature of each data point to obtain the curvature value of each data point.

S33, according to the curvature value of each data point, respectively determine the discrete degree of the preprocessed upper point cloud data and the lower point cloud data, and set the curvature threshold;

As a preferred implementation, according to the curvature value of each data point, respectively determining the discrete degree of the preprocessed upper point cloud data and the lower point cloud data, and setting the curvature threshold comprises the following steps:

S331, calculating the discrete value of each data point according to the curvature value of each data point in the preprocessed upper point cloud data and the lower point cloud data;

Specifically, the calculation formula for calculating the discrete value of each data point is:

Where, _Fi represents the discrete value of data point i;

_Ki represents the curvature value of data point i;

max(K _s ) represents the maximum and minimum values of the curvature among all data points.

S332, respectively summing the discrete values of all data points in the preprocessed upper point cloud data and the lower point cloud data, and squaring the summed values to obtain first discreteness of the upper point cloud data and the lower point cloud data;

S333, respectively calculating the discrete average values of all data points in the preprocessed upper point cloud data and the lower point cloud data, and squaring the discrete average values to obtain the second discreteness of the upper point cloud data and the lower point cloud data;

S334. Compare the first discreteness and the second discreteness of the preprocessed upper point cloud data and the lower point cloud data respectively. If the first discreteness is smaller than the second discreteness, select the minimum curvature value of the data points in the preprocessed upper point cloud data and the lower point cloud data respectively as the curvature threshold; otherwise, select the average value of all data points in the preprocessed upper point cloud data and the lower point cloud data respectively as the curvature threshold.

S34, extracting the film boundary line from the preprocessed upper point cloud data and the lower point cloud data respectively according to the set curvature threshold;

As a preferred embodiment, according to the set curvature threshold, extracting the film boundary line from the preprocessed upper point cloud data and the lower point cloud data respectively includes the following steps:

S341, traversing each data point in the preprocessed upper point cloud data and the lower point cloud data, and for each data point, checking whether its curvature value exceeds a set curvature threshold;

S342, taking data points whose curvature values exceed a threshold in the preprocessed upper point cloud data and lower point cloud data as boundary points;

S343. Use the minimum distance method to connect adjacent boundary points to obtain a continuous boundary line, and use it as the boundary line of the film.

Specifically, the method of connecting adjacent boundary points using the minimum distance method to obtain a continuous boundary line, and using the continuous boundary line as the boundary line of the film includes the following steps:

Identify all boundary points whose curvature values exceed a set threshold and calculate the Euclidean distance for each pair of boundary points;

For each boundary point, find the other boundary point that is closest to it and create a line segment connecting the two points;

Connect these shortest line segments one by one to form a complete continuous boundary line.

S35 , determining upper surface contour data and lower surface contour data according to the film boundary lines of the preprocessed upper point cloud data and lower point cloud data.

It should be noted that, according to the film boundary line of the preprocessed upper point cloud data and lower point cloud data, the data within the film boundary line is used as surface contour data to obtain upper surface contour data and lower surface contour data respectively.

S4. Calculate the thickness of the film at different positions according to the upper surface profile data and the lower surface profile data, and evaluate the film based on the quality judgment standard.

As a preferred embodiment, according to the upper surface profile data and the lower surface profile data, respectively calculating the thickness of the film at different positions, and evaluating the film based on the quality judgment standard includes the following steps:

S41, aligning the upper surface contour data and the lower surface contour data in a preset coordinate system respectively;

As a preferred implementation, aligning the upper surface contour data and the lower surface contour data in a preset coordinate system for point cloud data includes the following steps:

S411, obtaining the relative position relationship between two groups of laser scanners that collect upper surface profile data and lower surface profile data;

It should be noted that the exact coordinate position of each scanner in the experiment or working environment should be recorded first, including their X, Y, and Z coordinates relative to a known reference point; the distance and angle between the scanners should be measured.

S412, converting the upper surface contour data and the lower surface contour data into a preset coordinate system respectively;

Specifically, first identify the coordinate system where the upper surface and lower surface contour data are currently located;

Determine the translation distance required in the X, Y, and Z directions from the origin coordinate system to the destination coordinate system.

Determine the angles required to rotate the profile data from the original coordinate system to the target coordinate system; including rotations around the X, Y, and Z axes;

Construct a homogeneous coordinate transformation matrix using the translation vector, rotation matrix, and scaling matrix;

Apply the transformation matrix to each point's coordinates (x, y, z) to transform them into the target coordinate system.

S413, performing point cloud data alignment on the upper surface contour data and the lower surface contour data according to the relative position relationship between the two groups of laser scanners.

Specifically, a transformation matrix is applied to one set of point cloud data so as to align it with the other set of point cloud data.

S42, after the data are aligned, for each data point of the upper surface contour data, find the nearest data point in the corresponding lower surface contour data, and calculate the vertical distance between the two data point pairs;

It should be noted that for each point in the upper surface contour data, the Euclidean distance is used to calculate the distance between the current upper surface point and all lower surface points; the minimum value is found from the calculated distances, and the corresponding lower surface point is the point closest to the current upper surface point, and the vertical distance between the two data point pairs is determined.

S43, respectively comparing the vertical distance of each data point pair with the standard film thickness, and evaluating the quality of the film based on the comparison result.

As a preferred embodiment, respectively comparing the vertical distance of each data point pair with the standard film thickness, and evaluating the quality of the film based on the comparison result comprises the following steps:

S431, respectively calculating the difference between the vertical distance of each data point pair and the standard film thickness;

S432, comparing the difference with a preset error range, if the difference is greater than the preset error range, it is considered that the film thickness at the location of the data point pair does not meet the standard, otherwise, it is considered that the film thickness at the location of the data point pair meets the standard;

S433, counting the number of all pairs of data points that meet and do not meet the requirements, and evaluating the overall quality of the film based on the statistical results.

For example, the vertical distance of each data point pair is compared with the standard film thickness, and the quality of the film is evaluated based on the comparison results. The specific implementation steps are:

Assume the following data: the standard film thickness is 5 microns, and the pre-set error range is ±1 micron;

The vertical distance between the upper surface point A and the lower surface point A' is 5.2 microns;

The vertical distance between the upper surface point B and the lower surface point B' is 4.8 microns;

The vertical distance between the upper surface point C and the lower surface point C' is 6.3 microns;

For data point pair A and A': difference = 5.2 microns - 5 microns = 0.2 microns;

Since the difference of 0.2 microns is within the error range of ±1 micron, the film thickness at the positions of data point pair A and A' meets the standard.

For data point pair B and B': difference = 4.8 microns - 5 microns = -0.2 microns;

Likewise, the difference of -0.2 microns is also within the error range of ±1 micron, so the film thickness at the locations of data point pair B and B' also meets the standard.

For data point pair C and C': difference = 6.3 microns - 5 microns = 1.3 microns;

Since the difference of 1.3 microns exceeds the error range of ±1 micron, the film thickness at the data point pair C and C' does not meet the standard.

Furthermore, suppose there are 100 data point pairs, 95 of which meet the criteria and 5 do not;

Based on the statistical results, the overall quality of the film can be evaluated. In this example, since the film thickness of the vast majority of data point pairs (95%) meets the standard, it can be considered that the overall quality of the film is good, although the film thickness of a few locations (5%) is beyond the error range.

As shown in FIG2 , according to another embodiment of the present invention, an online film thickness detection system based on a quality judgment standard is provided, and the online film thickness detection system based on a quality judgment standard comprises: a standard setting module 1, a data acquisition module 2, a contour extraction module 3 and a quality assessment module 4, and the standard setting module 1, the data acquisition module 2, the contour extraction module 3 and the quality assessment module 4 are connected in sequence;

A standard setting module 1, used for setting a quality judgment standard for film production based on a pre-set film production standard;

The data acquisition module 2 is used to use a laser scanner to perform three-dimensional point cloud scanning on the upper and lower surfaces of the film to be inspected, respectively, to obtain upper point cloud data and lower point cloud data;

The contour extraction module 3 is used to extract the surface contours of the obtained upper point cloud data and the lower point cloud data respectively, so as to obtain the upper surface contour data and the lower surface contour data;

The quality assessment module 4 is used to calculate the thickness of the film at different positions according to the upper surface profile data and the lower surface profile data, and to assess the film based on the quality judgment standard.

FIG3 shows an embodiment of a computer device of the present invention. The computer device may be a server, and the computer device includes a processor, a memory, and a network interface connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store static information and dynamic information data. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the steps in the above method embodiment are implemented.

Those skilled in the art will understand that the structure shown in FIG. 3 is merely a block diagram of a partial structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

In addition, the present invention also provides a computer device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiment when executing the computer program.

In addition, the present invention also provides a computer-readable storage medium having a computer program stored thereon, which implements the steps in the above method embodiment when executed by a processor. In summary, with the aid of the above technical solution of the present invention, the present invention can obtain the thickness information of the film in real time during the film production process through online detection, without waiting for offline detection after the production is completed, which greatly improves the production efficiency and makes the quality control in the production process more timely and accurate. The laser scanner is used for three-dimensional point cloud scanning without direct contact with the film, thereby avoiding possible physical damage or contamination. By extracting the surface contour and calculating the thickness of the point cloud data, the method can realize an automated and intelligent detection process; combined with the preset quality judgment standard, the film can be automatically evaluated, reducing the interference of human factors and improving the objectivity and accuracy of the detection results; the present invention can remove noise and outliers in the point cloud data through filtering and smoothing in the preprocessing step, thereby improving the quality of the data, and by calculating the curvature value of each data point and calculating the curvature value according to the curve The curvature threshold is used to extract the boundary line of the film, which can accurately identify the surface contour of the film, effectively distinguish the boundary between the film and the surrounding environment, avoid misjudgment or omission, and set the curvature threshold according to the discrete degree of the point cloud data, so that the setting of the threshold is more reasonable and adaptive. By comparing the first discrete degree and the second discrete degree, a more appropriate threshold can be selected to more accurately extract the boundary line of the film; the present invention aligns the point cloud data of the upper surface contour data and the lower surface contour data in a preset coordinate system, which can ensure that the corresponding data points are accurately matched, and then obtain the accurate vertical distance, that is, the thickness of the film; by comparing the vertical distance of each data point pair with the standard film thickness, and evaluating the quality of the film based on the comparison result, the film thickness of the film at different positions can be comprehensively and carefully inspected, which is helpful to improve the accuracy and efficiency of film thickness detection and provide a strong guarantee for the quality control of film production.

It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, optical storage, etc.) containing computer-usable program code.

The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims (10)

1. An online film thickness detection method based on a quality judgment standard, characterized in that the online film thickness detection method based on a quality judgment standard comprises the following steps: S1. Based on the pre-set film production standards, set the quality judgment standards for film production; S2, using a laser scanner to perform three-dimensional point cloud scanning on the upper and lower surfaces of the film to be inspected, respectively, to obtain upper point cloud data and lower point cloud data; S3, extracting surface contours of the obtained upper point cloud data and lower point cloud data respectively to obtain upper surface contour data and lower surface contour data; S4. Calculate the thickness of the film at different positions according to the upper surface profile data and the lower surface profile data, and evaluate the film based on the quality judgment standard. 2. According to the online film thickness detection method based on the quality judgment standard of claim 1, it is characterized in that the surface contour extraction is performed on the obtained upper point cloud data and the lower point cloud data respectively to obtain the upper surface contour data and the lower surface contour data, which comprises the following steps: S31, preprocessing the upper point cloud data and the lower point cloud data respectively, wherein the preprocessing includes filtering and smoothing; S32, respectively calculating the curvature value of each data point in the preprocessed upper point cloud data and the lower point cloud data; S33, according to the curvature value of each data point, respectively determine the discrete degree of the preprocessed upper point cloud data and the lower point cloud data, and set the curvature threshold; S34, extracting the film boundary line from the preprocessed upper point cloud data and the lower point cloud data respectively according to the set curvature threshold; S35 , determining upper surface contour data and lower surface contour data according to the film boundary lines of the preprocessed upper point cloud data and lower point cloud data. 3. The online film thickness detection method based on the quality judgment standard according to claim 2 is characterized in that the curvature value calculation of each data point in the pre-processed upper point cloud data and the lower point cloud data comprises the following steps: S321, for each data point in the preprocessed upper point cloud data and the lower point cloud data, calculate the Euclidean distance from the data point to all other points, and select M neighboring points closest to the data point; S322, for each data point and its selected M neighboring points, obtain the normal vector of the data point by calculating the covariance matrix of the neighboring points; S323, respectively calculating the angle between the normal vector of each data point and the normal vector of its neighboring points and calculating the position vector between each data point and its neighboring points, and determining the angle between the position vector and the normal vector of each data point; S324, for each data point, calculating the normal curvature of each data point relative to each of its neighboring points using a normal curvature calculation formula; S325, based on the Euler formula, determine the functional relationship between the normal curvature and the principal curvature, and solve the first principal curvature and the second principal curvature of each data point by the least squares optimization method; S326. Multiply the first principal curvature and the second principal curvature of each data point to obtain the curvature value of each data point. 4. The online film thickness detection method based on the quality judgment standard according to claim 2 is characterized in that the step of determining the discrete degree of the pre-processed upper point cloud data and the lower point cloud data according to the curvature value of each data point and setting the curvature threshold comprises the following steps: S331, calculating the discrete value of each data point according to the curvature value of each data point in the preprocessed upper point cloud data and the lower point cloud data; S332, respectively summing the discrete values of all data points in the preprocessed upper point cloud data and the lower point cloud data, and squaring the summed values to obtain first discreteness of the upper point cloud data and the lower point cloud data; S333, respectively calculating the discrete average values of all data points in the preprocessed upper point cloud data and the lower point cloud data, and squaring the discrete average values to obtain the second discreteness of the upper point cloud data and the lower point cloud data; S334. Compare the first discreteness and the second discreteness of the preprocessed upper point cloud data and the lower point cloud data respectively. If the first discreteness is smaller than the second discreteness, select the minimum curvature value of the data points in the preprocessed upper point cloud data and the lower point cloud data respectively as the curvature threshold; otherwise, select the average value of all data points in the preprocessed upper point cloud data and the lower point cloud data respectively as the curvature threshold. 5. The online film thickness detection method based on the quality judgment standard according to claim 4 is characterized in that the calculation formula for calculating the discrete value of each data point is: Where, _Fi represents the discrete value of data point i; _Ki represents the curvature value of data point i; max(K _s ) represents the maximum and minimum values of the curvature among all data points. 6. The online film thickness detection method based on the quality judgment standard according to claim 2 is characterized in that the step of extracting the film boundary line from the pre-processed upper point cloud data and the lower point cloud data according to the set curvature threshold comprises the following steps: S341, traversing each data point in the preprocessed upper point cloud data and the lower point cloud data, and for each data point, checking whether its curvature value exceeds a set curvature threshold; S342, taking data points whose curvature values exceed a threshold in the preprocessed upper point cloud data and lower point cloud data as boundary points; S343. Use the minimum distance method to connect adjacent boundary points to obtain a continuous boundary line, and use it as the boundary line of the film. 7. The online film thickness detection method based on the quality judgment standard according to claim 1 is characterized in that the step of calculating the thickness of the film at different positions according to the upper surface profile data and the lower surface profile data, and evaluating the film based on the quality judgment standard comprises the following steps: S41, aligning the upper surface contour data and the lower surface contour data in a preset coordinate system respectively; S42, after the data are aligned, for each data point of the upper surface contour data, find the nearest data point in the corresponding lower surface contour data, and calculate the vertical distance between the two data point pairs; S43, respectively comparing the vertical distance of each data point pair with the standard film thickness, and evaluating the quality of the film based on the comparison result. 8. The online film thickness detection method based on the quality judgment standard according to claim 7 is characterized in that the step of aligning the upper surface profile data and the lower surface profile data in a preset coordinate system comprises the following steps: S411, obtaining the relative position relationship between two groups of laser scanners that collect upper surface profile data and lower surface profile data; S412, converting the upper surface contour data and the lower surface contour data into a preset coordinate system respectively; S413, performing point cloud data alignment on the upper surface contour data and the lower surface contour data according to the relative position relationship between the two groups of laser scanners. 9. The method for online film thickness detection based on quality judgment criteria according to claim 7, characterized in that the step of comparing the vertical distance of each data point pair with the standard film thickness and evaluating the quality of the film based on the comparison result comprises the following steps: S431, respectively calculating the difference between the vertical distance of each data point pair and the standard film thickness; S432, comparing the difference with a preset error range, if the difference is greater than the preset error range, it is considered that the film thickness at the location of the data point pair does not meet the standard, otherwise, it is considered that the film thickness at the location of the data point pair meets the standard; S433, counting the number of all pairs of data points that meet and do not meet the requirements, and evaluating the overall quality of the film based on the statistical results. 10. An online film thickness detection system based on a quality judgment standard, used to implement the online film thickness detection method based on a quality judgment standard according to any one of claims 1 to 9, characterized in that the online film thickness detection system based on a quality judgment standard comprises: a standard setting module, a data acquisition module, a contour extraction module and a quality assessment module, and the standard setting module, the data acquisition module, the contour extraction module and the quality assessment module are connected in sequence; The standard setting module is used to set the quality judgment standard of film production based on the pre-set film production standard; The data acquisition module is used to use a laser scanner to perform three-dimensional point cloud scanning on the upper and lower surfaces of the film to be inspected, respectively, to obtain upper point cloud data and lower point cloud data; The contour extraction module is used to extract surface contours from the obtained upper point cloud data and lower point cloud data respectively to obtain upper surface contour data and lower surface contour data; The quality assessment module is used to calculate the thickness of the film at different positions according to the upper surface profile data and the lower surface profile data, and to assess the film based on the quality judgment standard.