A printing method for carbon oil PCB board

Abstract

This application relates to a method for printing carbon ink-coated PCBs. The method involves capturing an image of the printed ink pattern on the PCB using a camera, and then analyzing the image using deep learning-based computer vision technology to extract edge information and identify deep structural features of the printed pattern, thereby intelligently identifying defects in the printed pattern. This method enables rapid and accurate detection of printing defects, thereby improving the production efficiency and product quality of carbon ink-coated PCBs.

Description

Technical Field

[0001] The present application relates to the technical field of carbon oil PCB boards, and in particular to a printing method for carbon oil PCB boards. Background Art

[0002] Carbon oil PCB board is a printed circuit board coated with carbon-based conductive ink (carbon ink). After curing, the carbon ink forms a PCB together with the conductive pattern of the carbon film. It is mainly used in scenarios such as remote control, RF shielding and industrial engine control.

[0003] In the manufacturing process of carbon ink PCBs, the accurate formation of the ink printing pattern is a key factor affecting product performance and yield. However, various factors in the printing process, such as printing pressure, speed, ambient humidity, and ink fluidity, can cause printing defects such as pattern missing, overlap, or discontinuous conductive paths, which can seriously affect the performance and reliability of carbon ink PCBs.

[0004] In the existing technology, printing defect detection is usually carried out by manual visual inspection and random sampling. However, this method is not only inefficient, but also has limited recognition accuracy. It is insufficient to detect certain complex or minor defects and cannot meet the needs of high-quality, large-scale production.

[0005] Therefore, in order to ensure the performance and reliability of carbon oil PCB boards, an optimized carbon oil PCB printing method is expected. Summary of the Invention

[0006] This summary is provided to briefly introduce concepts that will be described in detail in the detailed description below. This summary is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0007] In the first aspect, the present application provides a method for printing a carbon oil PCB board, the method comprising: fully stirring the carbon ink to achieve the desired viscosity; curing the solder resist on the PCB substrate, and preparing the carbon ink pattern to be printed, and then installing it on a screen printing machine; preparing a screen, and installing it on the screen printing machine, sealing the screen frame and the non-graphic area on the screen with glue, wherein the screen tension is 20 to 30 N / cm; adjusting the screen spacing and scraper stroke to ensure that the scraper stroke can cover the graphic area on the screen during screen printing, wherein the angle of the scraper when scraping is 45 to 60 degrees. Angle; adjusting the relative position of the screen so that the graphic area on the screen is aligned with the carbon ink pattern to be printed on the PCB board; pouring the prepared carbon ink on the non-graphic area of ​​the screen, and scraping the carbon ink onto the PCB board with a scraper to obtain a carbon oil printed PCB board; placing the carbon oil printed PCB board in an oven to bake to obtain a solidified carbon oil PCB board; performing a printing effect test on the solidified carbon oil PCB board to identify whether there are printing defects, wherein the printing effect test on the solidified carbon oil PCB board to identify whether there are printing defects includes:

[0008] Acquire an ink printing pattern effect image captured by a camera;

[0009] Extracting pattern structure features of the ink printing pattern effect image to obtain an ink printing pattern structure feature map;

[0010] Performing feature autocorrelation enhancement on the ink printing pattern structure feature map to obtain an enhanced ink printing pattern structure feature map;

[0011] Based on the structural characteristic map of the enhanced ink printing pattern, it is determined whether there is a printing defect.

[0012] Optionally, extracting the pattern structure features of the ink printing pattern effect image to obtain an ink printing pattern structure feature map includes: extracting edge information of the ink printing pattern effect image to obtain an ink printing pattern edge detection image; and performing pattern structure feature extraction on the ink printing pattern edge detection image to obtain an ink printing pattern structure feature map.

[0013] Optionally, extracting edge information of the ink printing pattern effect image to obtain an ink printing pattern edge detection image includes: performing image denoising and image grayscale processing on the ink printing pattern effect image to obtain an ink printing pattern grayscale image; and performing edge detection on the ink printing pattern grayscale image using a Gabor filter to obtain the ink printing pattern edge detection image.

[0014] Optionally, pattern structure feature extraction is performed on the ink printing pattern edge detection image to obtain an ink printing pattern structure feature map, including: inputting the ink printing pattern edge detection image into a pattern structure feature extractor based on a void convolutional neural network model to obtain the ink printing pattern structure feature map.

[0015] Optionally, the ink printing pattern structure feature map is subjected to feature autocorrelation enhancement to obtain an enhanced ink printing pattern structure feature map, comprising: inputting the ink printing pattern structure feature map into a feature space structure preserving self-attention enhancement module based on cross-channel intersection to obtain the enhanced ink printing pattern structure feature map.

[0016] Optionally, the ink printing pattern structure feature map is input into a feature space structure preserving self-attention enhancement module based on cross-channel intersection to obtain the enhanced ink printing pattern structure feature map, including: performing layer normalization on the ink printing pattern structure feature map to obtain a normalized ink printing pattern structure feature map; performing point convolution processing on the normalized ink printing pattern structure feature map to obtain an ink printing pattern structure channel context association representation feature map; performing convolution encoding on the ink printing pattern structure channel context association representation feature map to obtain an ink printing pattern structure space context association representation feature map; performing channel-space global interactive attention fusion on the ink printing pattern structure channel context association representation feature map and the ink printing pattern structure space context association representation feature map to obtain the enhanced ink printing pattern structure feature map.

[0017] Optionally, the ink printing pattern structure channel context association representation feature map and the ink printing pattern structure space context association representation feature map are subjected to channel-space global interactive attention fusion to obtain the enhanced ink printing pattern structure feature map, including: copying the ink printing pattern structure space context association representation feature map to obtain a backup ink printing pattern structure space context association representation feature map; reshaping the ink printing pattern structure channel context association representation feature map, the ink printing pattern structure space context association representation feature map and the backup ink printing pattern structure space context association representation feature map to obtain an ink printing pattern structure channel context association representation feature matrix, an ink printing pattern structure space context association representation feature matrix and A backup ink printing pattern structure space context association representation feature matrix; calculating the cross-channel cross covariance matrix between the ink printing pattern structure channel context association representation feature matrix and the ink printing pattern structure space context association representation feature matrix; using the Softmax function to activate the cross-channel cross covariance matrix to obtain the ink printing pattern structure feature global interaction attention matrix; calculating the product between the backup ink printing pattern structure space context association representation feature matrix and the ink printing pattern structure feature global interaction attention matrix to obtain the attention enhancement ink printing pattern structure feature representation matrix; performing feature shape reshaping on the attention enhancement ink printing pattern structure feature representation matrix to obtain the enhanced ink printing pattern structure feature map.

[0018] Optionally, determining whether there is a printing defect based on the enhanced ink printing pattern structural feature map includes: inputting the enhanced ink printing pattern structural feature map into a classifier-based defect detector to obtain a detection result, wherein the detection result is used to indicate whether there is a printing defect.

[0019] This technical solution uses a camera to capture images of the printed ink pattern on a PCB. Deep learning-based computer vision technology then analyzes these images, extracting edge information and revealing the pattern's underlying structural features. This allows for intelligent identification of defects. This approach enables rapid and accurate detection of printing defects, improving production efficiency and quality of carbon ink-coated PCBs.

[0020] Other features and advantages of the present application will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The above and other features, advantages and aspects of the embodiments of the present application will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale. In the drawings:

[0022] Figure 1 The figure is a flow chart showing a method for printing a carbon oil PCB board according to an exemplary embodiment.

[0023] Figure 2 is based on Figure 1 The illustrated embodiment shows a flow chart of step S108 of a method for printing a carbon oil PCB board.

[0024] Figure 3 The figure is a block diagram of a carbon oil PCB printing system according to an exemplary embodiment.

[0025] Figure 4 It is a block diagram of an electronic device according to an exemplary embodiment.

[0026] Figure 5 This is a diagram showing an application scenario of a carbon oil PCB printing method according to an exemplary embodiment. DETAILED DESCRIPTION

[0027] The following describes embodiments of the present application in more detail with reference to the accompanying drawings. Although certain embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be construed as limited to the embodiments described herein. Instead, these embodiments are provided to provide a more thorough and complete understanding of the present application. It should be understood that the drawings and embodiments of the present application are for illustrative purposes only and are not intended to limit the scope of protection of the present application.

[0028] It should be understood that the various steps described in the method embodiments of the present application can be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present application is not limited in this respect.

[0029] As used herein, the term "including" and its variations are open-ended, i.e., "including but not limited to." The term "based on" means "based, at least in part, on." The term "one embodiment" means "at least one embodiment," the term "another embodiment" means "at least one additional embodiment," and the term "some embodiments" means "at least some embodiments." Other terms are defined in the following description.

[0030] It should be noted that the concepts of "first" and "second" mentioned in this application are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0031] It should be noted that the modifications of "one" and "multiple" mentioned in this application are illustrative rather than restrictive. Those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more".

[0032] The names of the messages or information exchanged between multiple devices in the embodiments of the present application are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0033] The specific implementation of this application is described in detail below with reference to the accompanying drawings.

[0034] Figure 1 The figure is a flow chart showing a method for printing a carbon oil PCB board according to an exemplary embodiment. Figure 2 is based on Figure 1 The embodiment shown is a flow chart of step S108 of a carbon oil PCB printing method. Figure 1 and Figure 2 As shown, the method includes:

[0035] Step S101: fully stir the carbon ink to achieve the desired viscosity;

[0036] Step S102: curing the solder resist on the PCB substrate, preparing the carbon ink pattern to be printed, and then installing it on the screen printer;

[0037] Step S103: making a screen and installing it on the screen printing machine, sealing the screen frame and the non-graphic area on the screen with glue, wherein the screen tension is 20-30 N / cm;

[0038] Step S104, adjusting the screen spacing and the scraper stroke to ensure that the scraper stroke can cover the graphic area on the screen during screen printing, wherein the scraper scrapes at an angle of 45 to 60 degrees;

[0039] Step S105: adjusting the relative position of the screen so that the pattern area on the screen is aligned with the carbon ink pattern to be printed on the PCB;

[0040] Step S106: Pour the prepared carbon ink onto the non-graphic area of ​​the screen, and use a scraper to print the carbon ink onto the PCB to obtain a carbon ink printed PCB.

[0041] Step S107: placing the carbon oil printed PCB board in an oven and baking it to obtain a cured carbon oil printed PCB board;

[0042] Step S108, performing a printing effect test on the cured carbon oil PCB board to identify whether there are printing defects, wherein step S108, performing a printing effect test on the cured carbon oil PCB board to identify whether there are printing defects, includes:

[0043] Step S1081: Acquire an ink printing pattern effect image captured by a camera;

[0044] Step S1082: extracting pattern structure features of the ink printing pattern effect image to obtain an ink printing pattern structure feature map;

[0045] Step S1083, performing feature autocorrelation enhancement on the ink printing pattern structure feature map to obtain an enhanced ink printing pattern structure feature map;

[0046] Step S1084: Determine whether there are printing defects based on the enhanced ink printing pattern structure characteristic map.

[0047] To address the above technical issues, the present application proposes a method for capturing images of the ink-printed pattern on a PCB using a camera. This method then employs deep learning-based computer vision technology to analyze these images, extracting edge information and identifying deep structural features of the printed pattern. This allows for intelligent identification of defects in the printed pattern. This method enables rapid and accurate detection of printing defects, thereby improving the production efficiency and quality of carbon-ink-printed PCBs.

[0048] Understandably, to ensure that the ink-printed patterns on PCBs meet high standards, advanced quality inspection techniques are essential. This approach leverages deep learning and computer vision technologies to efficiently analyze and identify defects in PCB ink-printed patterns. High-resolution cameras capture images of the PCBs, capturing every detail of the ink-printed patterns. The core of the deep learning model is a neural network, which automatically learns features within images and abstracts them into useful information. Deep learning helps the model identify structural features of the printed pattern that may be imperceptible to human vision. By analyzing these features, the deep learning model intelligently identifies printing defects. Compared to traditional inspection methods, deep learning-based inspection is not only faster but also more accurate. It can monitor PCB quality in real time during production, identifying and correcting problems promptly and preventing substandard products from entering the market.

[0049] As the technology continues to advance, its performance can be continuously optimized through continuous learning to adapt to different PCB board types and printed patterns. Furthermore, this method can be easily integrated into existing production lines, working in conjunction with other automated equipment to achieve fully automated quality control. In practical applications, this method can significantly improve PCB production efficiency and product quality. By quickly and accurately detecting printing defects, the scrap rate in the production process can be significantly reduced, while also improving product reliability and durability.

[0050] Based on this, in the technical solution of this application, first, an image of the ink printing pattern is acquired by a camera. It should be understood that the camera, as a non-contact image acquisition device, can capture the state of the ink printing pattern in real time without damaging or contaminating the PCB board, allowing print quality inspection without interrupting the production process.

[0051] In one embodiment of the present application, pattern structure features of the ink printing pattern effect image are extracted to obtain an ink printing pattern structure feature map, including: extracting edge information of the ink printing pattern effect image to obtain an ink printing pattern edge detection image; performing pattern structure feature extraction on the ink printing pattern edge detection image to obtain an ink printing pattern structure feature map.

[0052] Next, considering that the ink printing pattern effect image may be interfered by factors such as equipment noise and environmental noise during the acquisition process, resulting in reduced image quality. Therefore, in order to improve the accuracy of subsequent image analysis, in the technical solution of the present application, the ink printing pattern effect image is further subjected to image denoising to reduce or eliminate image noise, improve the signal-to-noise ratio of the image, and make the image clearer and cleaner. In the embodiments of the present application, methods such as median filter and wavelet denoising can be used for image denoising. At the same time, considering that in printing quality inspection, the edge contour information of the printed pattern is the key to defect identification, therefore, in order to improve the extraction effect of the edge information of the printed pattern, the present application further performs grayscale conversion on the denoised ink printing pattern effect image to simplify the color complexity of the image, highlight the edge features of the image, and generate an ink printing pattern grayscale image to provide more accurate input for subsequent defect detection.

[0053] Next, edge detection is performed on the grayscale image of the ink printed pattern using a Gabor filter to obtain an edge-detected image of the ink printed pattern. It should be understood that the Gabor filter is a commonly used edge detection tool in image processing that can effectively capture edge and texture information in an image. Filtering the grayscale image of the ink printed pattern using a Gabor filter can enhance the response of the printed pattern edge in the image, making the pattern outline more prominent and facilitating subsequent defect identification.

[0054] In one embodiment of the present application, edge information of the ink printing pattern effect image is extracted to obtain an ink printing pattern edge detection image, including: performing image denoising and image grayscale processing on the ink printing pattern effect image to obtain an ink printing pattern grayscale image; and performing edge detection on the ink printing pattern grayscale image using a Gabor filter to obtain the ink printing pattern edge detection image.

[0055] Furthermore, in order to further extract the deep structural features of the ink printing pattern, based on the ink printing pattern edge detection image, this application further uses a pattern structure feature extractor based on a dilated convolutional neural network model to perform deep feature mining. Dilated convolution can expand the receptive field without increasing computational complexity, effectively capturing large-scale structural information in the ink printing pattern edge detection image, and helping to identify the global structure and potential defects of the printed pattern, such as line continuity and shape integrity, thereby obtaining an ink printing pattern structural feature map.

[0056] In one embodiment of the present application, pattern structure feature extraction is performed on the ink printing pattern edge detection image to obtain an ink printing pattern structure feature map, including: inputting the ink printing pattern edge detection image into a pattern structure feature extractor based on a void convolutional neural network model to obtain the ink printing pattern structure feature map.

[0057] Secondly, in order to further enhance the representation ability of the ink printing pattern structure feature map, the present application introduces a feature space structure preservation self-attention enhancement module based on cross-channel cross-channel cross-over to perform feature autocorrelation enhancement on the ink printing pattern structure feature map, and enhances the feature association between different channels in the feature map while retaining its spatial context information to enhance the structural feature representation of the ink printing pattern. Specifically, the module first performs layer normalization on the ink printing pattern structure feature map to eliminate the scale difference between layers and ensure the stability of feature processing. Then, multi-layer convolution operations are used to capture the channel context association and spatial structure information of the feature map, and its channel context association information is used as a query, and the spatial structure information is used as the key and value. Based on the self-attention mechanism, feature cross-channel global association interaction is performed, thereby retaining the spatial structure of the feature map while fusing the channel association information between feature structures in units of feature space structure, enhancing the expression ability of the feature map, and generating an enhanced ink printing pattern structure feature map.

[0058] In one embodiment of the present application, the ink printing pattern structure feature map is subjected to feature autocorrelation enhancement to obtain an enhanced ink printing pattern structure feature map, comprising: inputting the ink printing pattern structure feature map into a feature space structure preserving self-attention enhancement module based on cross-channel intersection to obtain the enhanced ink printing pattern structure feature map.

[0059] Furthermore, in one embodiment of the present application, the ink printing pattern structure feature map is input into a feature space structure preserving self-attention enhancement module based on cross-channel intersection to obtain the enhanced ink printing pattern structure feature map, including: performing layer normalization on the ink printing pattern structure feature map to obtain a normalized ink printing pattern structure feature map; performing point convolution processing on the normalized ink printing pattern structure feature map to obtain an ink printing pattern structure channel context association representation feature map; performing convolution encoding on the ink printing pattern structure channel context association representation feature map to obtain an ink printing pattern structure space context association representation feature map; performing channel-space global interactive attention fusion on the ink printing pattern structure channel context association representation feature map and the ink printing pattern structure space context association representation feature map to obtain the enhanced ink printing pattern structure feature map.

[0060] Furthermore, in one embodiment of the present application, the ink printing pattern structure channel context association representation feature map and the ink printing pattern structure space context association representation feature map are subjected to channel-space global interactive attention fusion to obtain the enhanced ink printing pattern structure feature map, including: copying the ink printing pattern structure space context association representation feature map to obtain a backup ink printing pattern structure space context association representation feature map; reshaping the ink printing pattern structure channel context association representation feature map, the ink printing pattern structure space context association representation feature map and the backup ink printing pattern structure space context association representation feature map to obtain an ink printing pattern structure channel context association representation feature matrix, an ink printing pattern structure space context association representation feature map and a backup ink printing pattern structure space context association representation feature map. Representation feature matrix and backup ink printing pattern structure space context association representation feature matrix; calculate the cross-channel cross covariance matrix between the ink printing pattern structure channel context association representation feature matrix and the ink printing pattern structure space context association representation feature matrix; use Softmax function to activate the cross-channel cross covariance matrix to obtain the ink printing pattern structure feature global interaction attention matrix; calculate the product between the backup ink printing pattern structure space context association representation feature matrix and the ink printing pattern structure feature global interaction attention matrix to obtain the attention enhancement ink printing pattern structure feature representation matrix; perform feature shape reshaping on the attention enhancement ink printing pattern structure feature representation matrix to obtain the enhanced ink printing pattern structure feature map.

[0061] Specifically, the ink printing pattern structure feature map is processed using the following autocorrelation attention enhancement formula to obtain the enhanced ink printing pattern structure feature map, wherein the autocorrelation attention enhancement formula is:

[0062] F ln =Layer Normalization(F i )

[0063] F Q =Conv 1×1 (F ln )

[0064] F K =Conv 3×3 (Conv 1×1 (F ln ))

[0065] F V =Copy(F K )

[0066] M Q =Reshape(FQ )

[0067] M K =Reshape(F K )

[0068] M V =Reshape(F V )

[0069]

[0070] Among them, F i represents the structural characteristic map of the ink printing pattern, Layer Normalization (·) represents the layer normalization operation, F ln Represents the normalized ink printing pattern structure feature map, Conv 1×1 represents point convolution, F Q Represents the ink printing pattern structure channel context association representation feature map, Conv 3×3 Indicates the convolution processing based on 3×3 convolution kernel, F K represents the ink printing pattern structure space context association representation feature map, Copy(·) represents the copy operation, F V represents the backup ink printing pattern structure space context association representation feature map, reshape(·) represents the feature shape reshaping, M Q 、M K and M V They represent the ink printing pattern structure channel context association representation feature matrix, the ink printing pattern structure space context association representation feature matrix and the backup ink printing pattern structure space context association representation feature matrix, M a represents the cross-channel cross covariance matrix, θ is the scaling factor, softmax represents the normalized exponential function, Represents matrix multiplication operation, F a A diagram showing the structural characteristics of the enhanced ink printing pattern.

[0071] Next, the enhanced ink printing pattern structural feature map is input into a classifier-based defect detector to obtain a detection result, which is used to indicate whether there is a printing defect. In the technical solution of the present application, the classifier-based defect detector is trained using a large amount of sample data with known defects and no defects. By continuously optimizing its internal parameters, it can accurately distinguish whether the ink printing pattern is defective. In other words, when the enhanced ink printing pattern structural feature map is input into the trained defect detector, the defect detector can accurately determine whether there is a printing defect based on its learned classification rules, so that production personnel can promptly discover and deal with potential printing problems, thereby preventing defective products from flowing into the next process.

[0072] In one embodiment of the present application, determining whether there is a printing defect based on the enhanced ink printing pattern structure feature map includes: inputting the enhanced ink printing pattern structure feature map into a classifier-based defect detector to obtain a detection result, and the detection result is used to indicate whether there is a printing defect.

[0073] In a preferred example, the step of passing the enhanced ink printing pattern structure feature map through a classifier-based defect detector to obtain a detection result includes:

[0074] Calculating a characteristic mean of the enhanced ink printing pattern structure characteristic map, and dividing the characteristic mean by the difference between the maximum characteristic value and the minimum characteristic value of the enhanced ink printing pattern structure characteristic map to obtain an enhanced ink printing pattern structure distribution representation value;

[0075] Subtracting the enhanced ink printing pattern structure distribution characterization value from one and dividing the result by the enhanced ink printing pattern structure distribution characterization value to obtain an enhanced ink printing pattern structure distribution modulation value;

[0076] activating the enhanced ink printing pattern structure characteristic map through a probabilistic function to obtain a probabilistic enhanced ink printing pattern structure characteristic map;

[0077] performing point-wise subtraction between the probabilistic enhanced ink printing pattern structure characteristic map and the enhanced ink printing pattern structure distribution modulation value, taking the absolute value and calculating the negative of the logarithmic value with base 2 to obtain a probabilistic enhanced ink printing pattern structure distribution modulation information characteristic map;

[0078] After dividing the enhanced ink printing pattern structure distribution characterization value by one minus the difference between each eigenvalue of the probabilistic enhanced ink printing pattern structure feature map, summing all eigenvalues ​​of the probabilistic enhanced ink printing pattern structure feature map and dividing the sum by the scale of the enhanced ink printing pattern structure feature map to obtain a probabilistic enhanced ink printing pattern structure distribution modulation bias value;

[0079] Obtaining an optimized enhanced ink printing pattern structure feature map by multiplying the probabilistic enhanced ink printing pattern structure distribution modulation information feature map and the probabilistic enhanced ink printing pattern structure distribution modulation bias value by a weight serving as a hyperparameter; and

[0080] The optimized enhanced ink printing pattern structural feature map is passed through the classifier-based defect detector to obtain the detection result.

[0081] The optimized enhanced ink printing pattern structure characteristic diagram is represented as follows:

[0082]

[0083] And among them:

[0084]

[0085] in, represents the characteristic mean of the structural characteristic graph of the enhanced ink printing pattern, f max and f min represents the maximum eigenvalue and the minimum eigenvalue of the enhanced ink printing pattern structure characteristic map, respectively; p represents the enhanced ink printing pattern structure distribution representation value; F represents the probabilistic enhanced ink printing pattern structure characteristic map obtained after the enhanced ink printing pattern structure characteristic map is activated by the probabilistic function; f i represents the i-th eigenvalue of the probabilistic enhanced ink printing pattern structure feature map, log represents a logarithmic function with base 2, ε is a weight as a hyperparameter, S is the scale of the enhanced ink printing pattern structure feature map, that is, the width of the feature matrix of the enhanced ink printing pattern structure feature map multiplied by the height and then multiplied by the number of channels of the enhanced ink printing pattern structure feature map, F' represents the optimized enhanced ink printing pattern structure feature map, represents positional subtraction, Represents positional addition.

[0086] That is, considering the image semantic features of the ink printing pattern edge detection image expressed by the ink printing pattern structure feature map, after the cross-channel cross-feature space structure self-attention enhancement is performed, the enhanced ink printing pattern structure feature map obtained will also cause insufficient feature saliency coverage due to the staggered distribution of attention dimensions, thereby leading to outlier class inference mapping deviation, and further affecting the accuracy of the detection results obtained by the classifier-based defect detector of the enhanced ink printing pattern structure feature map.

[0087] Based on this, the probability information distribution planning of the enhanced ink printing pattern structure feature map based on the eigenvalue is carried out through the Bernoulli probability modulation distribution of the enhanced ink printing pattern structure feature map relative to the eigenvalue distribution, and the probability reverse mapping of the probability characteristics of the enhanced ink printing pattern structure feature map as a whole is used as the extended coverage of the set mapping space of the enhanced ink printing pattern structure feature map to independently understand the interaction path between the intuitive probability information distribution and the abstract probability space mapping of the enhanced ink printing pattern structure feature map, so as to improve the accuracy of the detection results of the optimized enhanced ink printing pattern structure feature map obtained by the classifier-based defect detector by avoiding the counterfactual reasoning mapping of the outlier feature distribution of the enhanced ink printing pattern structure feature map to the class probability.

[0088] In summary, the above solution uses a camera to capture images of the ink-printed pattern on PCBs. Deep learning-based computer vision technology then analyzes these images, extracting edge information and exploring the deep structural features of the printed pattern. This allows for intelligent identification of defects. This approach enables rapid and accurate detection of printing defects, improving production efficiency and product quality for carbon-ink-printed PCBs.

[0089] Figure 3 FIG. 1 is a block diagram of a carbon oil PCB printing system according to an exemplary embodiment. Figure 3 As shown, the system 200 includes:

[0090] The carbon ink stirring module 201 is used to fully stir the carbon ink to achieve the desired viscosity;

[0091] The carbon ink pattern making module 202 is used to cure the solder resist on the PCB substrate and make the carbon ink pattern to be printed, and then install it on the screen printing machine;

[0092] Screen making and installation module 203, for making a screen and installing it on the screen printing machine, sealing the screen frame and the non-graphic area on the screen with glue, wherein the screen tension is 20-30N / cm;

[0093] A screen spacing and scraper stroke adjustment module 204 is used to adjust the screen spacing and scraper stroke to ensure that the scraper stroke can cover the graphic area on the screen during screen printing, wherein the scraper scrapes at an angle of 45 to 60 degrees;

[0094] The relative position adjustment module 205 of the screen is used to adjust the relative position of the screen so that the pattern area on the screen is aligned with the carbon ink pattern to be printed on the PCB board;

[0095] A carbon ink printed PCB board manufacturing module 206 is used to pour the prepared carbon ink on the non-graphic area of ​​the screen and use a scraper to print the carbon ink on the PCB board to obtain a carbon ink printed PCB board;

[0096] A carbon oil PCB board curing module 207 is used to bake the carbon oil printed PCB board in an oven to obtain a cured carbon oil PCB board;

[0097] The printing defect recognition module 208 is used to detect the printing effect of the cured carbon oil PCB board and identify whether there are printing defects. The printing defect recognition module 208 includes:

[0098] The ink printing pattern effect image acquisition unit 2081 is used to acquire the ink printing pattern effect image acquired by the camera;

[0099] The pattern structure feature extraction unit 2082 is used to extract the pattern structure features of the ink printing pattern effect image to obtain an ink printing pattern structure feature map;

[0100] A feature autocorrelation enhancement unit 2083 is configured to perform feature autocorrelation enhancement on the ink printing pattern structure feature map to obtain an enhanced ink printing pattern structure feature map;

[0101] The printing defect determination unit 2084 is configured to determine whether a printing defect exists based on the enhanced ink printing pattern structure feature map.

[0102] Reference below Figure 4 , which shows a schematic structural diagram of an electronic device 600 suitable for implementing an embodiment of the present application. The terminal device in the embodiment of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 4 The electronic device shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0103] like Figure 4As shown, the electronic device 600 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 into a random access memory (RAM) 603. Various programs and data required for the operation of the electronic device 600 are also stored in the RAM 603. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0104] Typically, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 4 The electronic device 600 is shown with various devices, but it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed instead.

[0105] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 609, or installed from the storage device 608, or installed from the ROM 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the method of the embodiment of the present application are performed.

[0106] It should be noted that the computer-readable medium mentioned above in this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this application, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. This propagated data signal can take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0107] In some embodiments, the client and server can communicate using any currently known or future developed network protocol, such as HTTP (HyperText Transfer Protocol), and can be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0108] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0109] Computer program code for performing the operations of the present application can be written in one or more programming languages, or a combination thereof, including, but not limited to, object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0110] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0111] The modules described in the embodiments of this application may be implemented in software or hardware. In some cases, the name of a module does not necessarily limit the module itself. For example, a test parameter acquisition module may also be described as a "module for acquiring device test parameters corresponding to a target device."

[0112] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0113] In the context of the present application, a machine-readable medium can be a tangible medium that can contain or store a program for use by an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0114] Figure 5 This is an application scenario diagram of a carbon oil PCB printing method according to an exemplary embodiment. Figure 5 As shown, in this application scenario, first, an ink printing pattern effect image captured by a camera is obtained (for example, Figure 5 Then, the obtained ink printing pattern effect image is input to a server (for example, Figure 5 In the S) shown in , the server is capable of processing the ink printing pattern effect image based on the printing algorithm of the carbon oil PCB board to determine whether there are printing defects.

[0115] The above description is merely a preferred embodiment of the present application and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of disclosure in this application is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but also encompasses other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the above-mentioned disclosed concepts. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions disclosed in this application.

[0116] In addition, although adopting specific order to describe each operation, this should not be interpreted as requiring these operations to be executed in the specific order shown or in sequential order.Under certain environment, multitasking and parallel processing may be advantageous.Similarly, although comprising some specific implementation details in the above discussion, these should not be interpreted as limiting the scope of the application.Some features described in the context of separate embodiment can also be implemented in a single embodiment in combination.On the contrary, the various features described in the context of a single embodiment also can be implemented in multiple embodiments individually or in the mode of any suitable subcombination.

[0117] Although the subject matter has been described using language specific to structural features and / or method logic, it should be understood that the subject matter as defined is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely exemplary implementations. Regarding the apparatus in the above-described embodiments, the specific manner in which each module performs operations has been described in detail in the embodiments related to the method and will not be further elaborated here.

Claims

1. A method for printing a carbon oil PCB board, comprising: Stir the carbon ink thoroughly to achieve the desired viscosity; The solder resist is cured on the PCB substrate, and a carbon ink pattern to be printed is prepared, which is then installed on a screen printer; a screen is prepared and installed on the screen printer, and the screen frame and the non-pattern area on the screen are sealed with glue, wherein the screen tension is 20 to 30 N / cm; the screen spacing and the scraper stroke are adjusted to ensure that the scraper stroke can cover the pattern area on the screen during screen printing, wherein the angle of the scraper when scraping is 45 to 60 degrees; the relative position of the screen is adjusted to align the pattern area on the screen with the carbon ink pattern to be printed on the PCB; the prepared carbon ink is poured on the non-pattern area of ​​the screen, and the carbon ink is scraped onto the PCB with a scraper to obtain a carbon oil printed PCB; the carbon oil printed PCB is placed in an oven for baking to obtain a cured carbon oil PCB; the cured carbon oil PCB is subjected to a printing effect inspection to identify whether there are printing defects, characterized in that the printing effect inspection to identify whether there are printing defects on the cured carbon oil PCB comprises: Acquire an ink printing pattern effect image captured by a camera; Extracting pattern structural features of the ink printing pattern effect image to obtain an ink printing pattern structural feature map, comprising: performing image denoising and image grayscale processing on the ink printing pattern effect image to obtain an ink printing pattern grayscale image; performing edge detection on the ink printing pattern grayscale image using a Gabor filter to obtain an ink printing pattern edge detection image; and inputting the ink printing pattern edge detection image into a pattern structural feature extractor based on a dilated convolutional neural network model to obtain the ink printing pattern structural feature map; Performing feature autocorrelation enhancement on the ink printing pattern structure feature map to obtain an enhanced ink printing pattern structure feature map, comprising: inputting the ink printing pattern structure feature map into a feature space structure preserving self-attention enhancement module based on cross-channel intersection to obtain the enhanced ink printing pattern structure feature map; Based on the structural characteristic map of the enhanced ink printing pattern, it is determined whether there is a printing defect.

2. The carbon oil PCB printing method according to claim 1, characterized in that: Inputting the ink printing pattern structure feature map into a feature space structure preserving self-attention enhancement module based on cross-channel intersection to obtain the enhanced ink printing pattern structure feature map, comprising: performing layer normalization on the ink printing pattern structure characteristic map to obtain a normalized ink printing pattern structure characteristic map; Performing point convolution processing on the normalized ink printing pattern structure feature map to obtain an ink printing pattern structure channel context association representation feature map; performing convolution encoding on the ink printing pattern structure channel context association representation feature map to obtain an ink printing pattern structure space context association representation feature map; The channel context association representation feature map of the ink printing pattern structure and the spatial context association representation feature map of the ink printing pattern structure are fused with channel-space global interactive attention to obtain the enhanced ink printing pattern structure feature map.

3. The carbon oil PCB printing method according to claim 2, characterized in that: Performing channel-space global interactive attention fusion on the ink printing pattern structure channel context association representation feature map and the ink printing pattern structure space context association representation feature map to obtain the enhanced ink printing pattern structure feature map, including: Copying the ink printing pattern structure space context association representation feature map to obtain a backup ink printing pattern structure space context association representation feature map; reshaping the ink printing pattern structure channel context association representation feature map, the ink printing pattern structure space context association representation feature map, and the backup ink printing pattern structure space context association representation feature map to obtain an ink printing pattern structure channel context association representation feature matrix, an ink printing pattern structure space context association representation feature matrix, and a backup ink printing pattern structure space context association representation feature matrix; Calculating a cross-channel cross covariance matrix between the ink printing pattern structure channel context association representation feature matrix and the ink printing pattern structure space context association representation feature matrix; Activating the cross-channel cross-covariance matrix using a Softmax function to obtain a global interactive attention matrix of the ink printing pattern structure feature; Calculating the product of the backup ink printing pattern structure space context association representation feature matrix and the ink printing pattern structure feature global interaction attention matrix to obtain an attention-enhanced ink printing pattern structure feature representation matrix; The attention-enhancing ink printing pattern structure feature representation matrix is ​​reshaped to obtain the attention-enhancing ink printing pattern structure feature map.

4. The carbon oil PCB printing method according to claim 3, characterized in that: Determining whether there is a printing defect based on the enhanced ink printing pattern structure characteristic map includes: The enhanced ink printing pattern structural feature map is input into a classifier-based defect detector to obtain a detection result, which is used to indicate whether there is a printing defect.

Images