A quality monitoring method, system, equipment and medium for direct writing molding circuit

Abstract

The present invention relates to the field of 3D printing technology, and discloses a quality monitoring method, system, equipment and medium for direct writing molding circuits. The method comprises: determining a captured image of a discharge area according to a needle position; performing binarization processing and connected domain analysis on the captured image and a preset template image, respectively, to determine the discharge area of ​​the captured image and the discharge area of ​​the preset template image; performing a difference image subtraction between the captured binary image and the template binary image, and performing connected domain analysis on the difference image to obtain a difference analysis result; calculating the discharge area ratio of the captured image and the preset template image, and monitoring the quality of the direct writing molding circuit according to the discharge area ratio difference analysis result. The present invention analyzes the image of the discharge area, makes the judgment of material breakage more accurate, and can also perform material breakage detection on materials in various states. By calculating the discharge area, an early warning can be given before the material is completely exhausted, thereby ensuring the effect of direct writing molding.

Description

Technical Field

[0001] The present invention relates to the field of 3D printing technology, and in particular to a quality monitoring method, system, equipment and medium for direct writing molding circuits. Background Art

[0002] Currently, the most common quality monitoring schemes for 3D printing technology circuits rely on mechanical structures for detection. For example, they use the relative relationship between the internal filament feed speed sensor and the discharge speed sensor to determine if a material breakage has occurred. Optocouplers use light as a medium to transmit electrical signals, with the diameter of the printing filament blocking the light source. When the filament is exhausted or a break occurs, the light transmission is unobstructed, and the optocoupler receives the light, generating a current and outputting an output, indicating that the filament is out of material. The core of existing technologies relies on the design of specialized detection or sensing devices. Mainstream 3D printing technology is achieved by melting plastic filament. The filament is solid before melting, and most detection devices only detect the filament in its pre-melting state.

[0003] The quality monitoring technology of commonly used lines cannot adapt to the detection of other liquid materials such as metals and resins, and feedback can only be provided when material breakage is obvious, making it impossible to provide accurate early warning. Summary of the Invention

[0004] In view of this, the present invention provides a method, system, equipment and medium for monitoring the quality of direct writing molding circuits to solve the problems of being unable to provide accurate early warning and unable to detect liquid materials.

[0005] In a first aspect, the present invention provides a method for monitoring the quality of a direct-write circuit, the method comprising:

[0006] Obtain the needle position of the detection image, and determine the collected image of the discharge area based on the needle position;

[0007] Performing binarization processing and connected domain analysis on the collected image to obtain a collected binary image, and determining the discharge area of ​​the collected image based on the collected binary image;

[0008] Performing binarization processing and connected domain analysis on the preset template image to obtain a template binary image, and determining the discharge area of ​​the preset template image according to the template binary image;

[0009] Subtracting the acquired binary image from the template binary image to obtain a difference image, and performing connected domain analysis on the difference image to obtain a difference analysis result;

[0010] The ratio of the discharge area of ​​the captured image to the discharge area of ​​the preset template image is calculated, and the quality of the direct writing circuit is monitored based on the relationship between the discharge area ratio and the preset ratio range and the difference analysis results.

[0011] The quality monitoring method of the direct writing molding circuit provided by the present invention can more accurately judge the material breakage by analyzing the image of the discharge area. At the same time, it can detect the material breakage in various states. By calculating the discharge area, it can provide an early warning before the material is completely exhausted, thereby ensuring the effect of direct writing molding.

[0012] In an optional embodiment, obtaining the needle position of the detection image and determining the collected image of the discharge area according to the needle position includes:

[0013] Acquire a test image, and determine the needle position in the test image using a needle position model;

[0014] Determine the discharge area based on the needle position;

[0015] The detection image is cropped according to the range of the discharge area to obtain the collected image of the discharge area.

[0016] The quality monitoring method of the direct writing molding circuit provided by the present invention uses the needle position to determine the range of the discharge area, and crops the detection image according to the range of the discharge area to obtain the collected image of the discharge area, ensuring that the collected image of the discharge area is identical to the preset template image except for the discharge area, thereby improving the accuracy of calculating the discharge area using the difference image.

[0017] In an optional embodiment, determining the needle position in the detection image using the needle position model includes:

[0018] Acquire multiple sample images, each of which includes a needle position;

[0019] Use deep learning to extract needle position features in sample images;

[0020] The needle position model is obtained by training a preset deep learning model using the needle position features in multiple sample images;

[0021] A detection image is acquired, and the detection image is input into the needle position model to obtain the needle position of the detection image.

[0022] The quality monitoring method for direct-write molding circuits provided by the present invention utilizes deep learning to obtain a needle position model, utilizes the needle position model to determine the needle position of a detection image, quickly and accurately finds the needle position in the detection image, and improves the efficiency of needle position determination.

[0023] In an optional embodiment, the process of obtaining the preset template image includes:

[0024] Acquire multiple template images in a needle-discharging state;

[0025] Calculate the average value of pixels at the same position in each template image, compare the pixel value at each position in each template image with the corresponding pixel average value, and obtain the position pixel difference;

[0026] Determining multiple valid template images based on the position pixel difference of each position in each template image and a preset pixel difference threshold;

[0027] The effective pixel average value at the same position in each effective template image is calculated, and the effective pixel average values ​​at all positions are fused to obtain the preset template image.

[0028] The quality monitoring method of the direct writing molding circuit provided by the present invention processes and analyzes multiple stable discharge images to obtain a preset template image as a standard for stable discharge, which is beneficial for comparing the actual discharge situation with the standard state of stable discharge in the detection of broken material, and then determining whether the actual discharge has broken material, thereby improving the accuracy of broken material detection.

[0029] In an optional embodiment, determining multiple valid template images based on the position pixel difference of each position in each template image and a preset pixel difference threshold includes:

[0030] Comparing the position pixel difference of each position in each template image with the preset pixel difference threshold, and taking the position where the position pixel difference is less than the preset pixel difference threshold as a valid position;

[0031] Calculate the effective ratio of the effective position in each template image to the total position in each template image;

[0032] The effective ratio is compared with a preset effective threshold, and the template image with an effective ratio greater than the preset effective threshold is taken as a valid template image.

[0033] The quality monitoring method of the direct writing molding circuit provided by the present invention determines the effective position through the size relationship between the position pixel difference and the preset pixel difference threshold, and determines the effective template image according to the ratio of the effective position to the total position. The obtained effective template image can more accurately reflect the image characteristics of the discharge area during stable discharge, thereby improving the practicality of the effective template image.

[0034] In an optional embodiment, performing binarization processing and connected domain analysis on the collected image to obtain a collected binary image, and determining the discharge area of ​​the collected image according to the collected binary image includes:

[0035] Obtain the pixel value of each position of the collected image, and perform binarization processing on the pixel value of each position of the difference image to obtain the discharge position of the collected image;

[0036] Performing a connected domain analysis on the discharge position of the collected image to determine the discharge connected domain of the collected image;

[0037] The area of ​​the discharge connected domain is calculated as the discharge area of ​​the acquired image.

[0038] The quality monitoring method of the direct writing molding circuit provided by the present invention can more accurately determine the discharge area of ​​the collected image through binarization processing and connected domain analysis, thereby improving the accuracy of the broken material detection result.

[0039] In an optional embodiment, monitoring the quality of the direct writing circuit based on the relationship between the discharge area ratio and the preset ratio range and the difference analysis result includes:

[0040] If the discharge area ratio is greater than the upper limit of the preset ratio range, or less than the lower limit of the preset ratio range, or if there is a difference in the discharge position of the difference image, the quality of the direct writing molding circuit is unqualified;

[0041] If the discharge area ratio is within the preset ratio range and there is no difference in the discharge position of the difference image, the quality of the direct writing molding circuit is qualified.

[0042] The quality monitoring method of the direct writing molding circuit provided by the present invention directly determines whether the material is broken by calculating the relationship between the discharge area ratio of the collected image and the preset ratio range. It can be applied to liquid materials, has high versatility, and does not require indirect detection of material breaks through the feeding situation, thereby improving the accuracy of material break detection during actual printing.

[0043] In a second aspect, the present invention provides a quality monitoring system for a direct writing molding circuit, the system comprising:

[0044] An image acquisition module is used to obtain the needle position of the detection image and determine the acquisition image of the discharge area according to the needle position;

[0045] The actual discharge area determination module is used to perform binarization processing and connected domain analysis on the collected image to obtain a collected binary image, and determine the discharge area of ​​the collected image based on the collected binary image;

[0046] A standard discharge area determination module is used to perform binarization processing and connected domain analysis on a preset template image to obtain a template binary image, and determine the discharge area of ​​the preset template image based on the template binary image;

[0047] The difference analysis module is used to perform a difference analysis on the acquired binary image and the template binary image to obtain a difference image, and perform a connected domain analysis on the difference image to obtain a difference analysis result;

[0048] The quality monitoring module is used to calculate the discharge area ratio of the captured image to the discharge area of ​​the preset template image, and monitor the quality of the direct writing molding circuit based on the size relationship between the discharge area ratio and the preset ratio range and the difference analysis results.

[0049] In a third aspect, the present invention provides a computer device comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0050] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the method of the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0052] Figure 1 1 is a flow chart of a method for monitoring the quality of a direct write molding circuit according to an embodiment of the present invention;

[0053] Figure 2 is a flow chart of another method for monitoring quality of a direct write molding circuit according to an embodiment of the present invention;

[0054] Figure 3 is a structural block diagram of a quality monitoring system for a direct write molding circuit according to an embodiment of the present invention;

[0055] Figure 4 Schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0056] To make the purpose, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of the present invention.

[0057] An embodiment of the present invention provides a quality monitoring method for a direct writing molding circuit, which analyzes images of a discharge area to improve the accuracy of material breakage detection and adapt to liquid-like materials.

[0058] According to an embodiment of the present invention, an embodiment of a quality monitoring method for a direct-write molding circuit is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0059] In this embodiment, a method for monitoring the quality of a direct write molding circuit is provided, which can be used in the above-mentioned computer system. Figure 1 FIG. 1 is a flow chart of a method for monitoring the quality of a direct-write molding circuit according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0060] Step S101, obtaining the needle position of the detection image, and determining the collected image of the discharge area according to the needle position.

[0061] Specifically, the needle refers to the printing needle of the printing device, which is installed at the discharge end of the printing nozzle and is used to print tubular filaments. The relative position of the needle and the discharge area is fixed, and the shape of the needle usually does not change. It is relatively easy to detect its position, so the discharge area can be determined by the needle position. For example, a circular area with the needle position as the center and a radius of 10 mm is used as the discharge area. This is only an example, but not limited to this. The collected image of the discharge area is determined according to the size of the discharge area, and the collected image of the discharge area must include the entire discharge area.

[0062] Step S102 , performing binarization processing and connected domain analysis on the collected image to obtain a collected binary image, and determining the discharge area of ​​the collected image based on the collected binary image.

[0063] Specifically, the preset template image is a standard image of stable material discharge obtained when the needle is in a normal, stable material discharge state. During the actual printing process, a captured image is acquired in real time and compared with the preset template image. It should be noted that when acquiring the captured image and the preset template image, the relative position of the visual camera and the material discharge area is exactly the same, that is, the captured image and the preset template image have the same screen.

[0064] The pixel values ​​at each position in the acquired image are binarized to obtain the acquired binary image corresponding to the acquired image. The acquired binary image is subjected to connected domain analysis to obtain connected components at positions with similar pixel values. The discharge area is located according to the connected components, and the area of ​​the discharge area is calculated as the discharge area of ​​the acquired image.

[0065] Step S103 , performing binarization processing and connected domain analysis on the preset template image to obtain a template binary image, and determining the discharge area of ​​the preset template image according to the template binary image.

[0066] Specifically, the discharge area of ​​the preset template image is determined by binarization processing and connected domain analysis. The specific calculation process is the same as the process of determining the discharge area of ​​the captured image in step S102, and will not be repeated here.

[0067] Step S104 : performing a difference analysis on the acquired binary image and the template binary image to obtain a difference image, and performing a connected component analysis on the difference image to obtain a difference analysis result.

[0068] Specifically, the pixel values ​​at the same position of the acquired binary image and the template binary image are subtracted to obtain the pixel values ​​at each position of the difference image, as shown in the following formula:

[0069] D(x,y)=|f(x,y)-F(x,y)|

[0070] Where x represents the width of the acquired binary image or the template binary image, y represents the length of the acquired binary image or the template binary image, D(x,y) represents the pixel value at position (x,y) in the difference image, f(x,y) represents the pixel value at position (x,y) in the acquired binary image, and F(x,y) represents the pixel value at position (x,y) in the template binary image.

[0071] The connected domain analysis is performed on the difference image to determine the difference connected domain composed of the points with differences and the same connected domain composed of the points without differences in the difference image, and whether there is a difference in the discharge position in the difference image is determined based on the difference connected domain and the same connected domain.

[0072] Step S105 , calculating the ratio of the discharge area of ​​the captured image to the discharge area of ​​the preset template image, and monitoring the quality of the direct writing circuit according to the relationship between the discharge area ratio and the preset ratio range and the difference analysis result.

[0073] Specifically, the output area ratio of the captured image to the output area of ​​the preset template image is calculated, and a preset ratio range is set according to the requirements of the actual printed product for output. For example, the preset ratio range is 90%. When the output area ratio is smaller than the preset ratio range and there is a difference in the output position of the difference image, it means that the output area is too small and there is a defect in the output position in the captured image, indicating that material breakage occurs. This is only an example, but not limited to this.

[0074] The quality monitoring method for the direct writing molding circuit provided in this embodiment can more accurately judge the material breakage by analyzing the image of the discharge area. At the same time, it can detect the material breakage in various states. By calculating the discharge area, it can provide an early warning before the material is completely exhausted, thereby ensuring the effect of direct writing molding.

[0075] In this embodiment, a method for monitoring the quality of a direct write molding circuit is provided, which can be used in the above-mentioned computer system. Figure 2 FIG. 1 is a flow chart of a method for monitoring the quality of a direct-write molding circuit according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:

[0076] Step S201 , obtaining the needle position of the detection image, and determining the collected image of the discharge area according to the needle position.

[0077] Specifically, the above step S201 includes:

[0078] Step S2011: Acquire a detection image and determine the needle position in the detection image using a needle position model.

[0079] In some optional implementations, the above step S2011 includes:

[0080] Step a1: Acquire multiple sample images, each of which contains the needle tip position.

[0081] Specifically, sample images containing the needle position are collected from multiple angles or in different environments, and the needle position is manually marked, for example, by bolding the needle position. This is only an example and is not limited to this.

[0082] Step a2: Use deep learning to extract needle position features in the sample image.

[0083] Specifically, the artificial markers in each sample image are identified to determine the needle position, and the needle position features are extracted through a convolutional neural network.

[0084] Step a3: Use the needle position features in multiple sample images to train a preset deep learning model to obtain a needle position model.

[0085] Specifically, the needle position features in multiple sample images are input into a preset deep learning model for training to obtain a needle position model. The specific training process can be achieved through relevant model training technology and is not limited here.

[0086] Step a4: Acquire a detection image, input the detection image into the needle position model, and obtain the needle position of the detection image.

[0087] Specifically, during actual printing, a detection image is acquired in real time, and the detection image is directly input into the needle position model. The needle position model is used to analyze the features of each position in the detection image to determine the needle position in the detection image.

[0088] The quality monitoring method for direct writing molding circuits provided in this embodiment uses deep learning to obtain a needle position model, uses the needle position model to determine the needle position of the detection image, quickly and accurately finds the needle position in the detection image, and improves the efficiency of determining the needle position.

[0089] Step S2012, determining the discharge area range according to the needle position.

[0090] Specifically, since the relative position of the needle position and the discharge area is determined, the discharge area can be determined based on the needle position. For example, a circular area with the needle position as the center and a radius of 10 mm is used as the discharge area, and the circumscribed square corresponding to the discharge area is used as the discharge area range. This is only an example, but not limited to this.

[0091] Step S2013 , cropping the detection image according to the range of the discharge area to obtain a captured image of the discharge area.

[0092] Specifically, the detected image is cropped based on the discharge area, removing image areas unrelated to the discharge. This reduces the subsequent processing of invalid information and improves processing efficiency. After cropping, the image within the discharge area is retained as the captured image of the discharge area. It should be noted that the shape and size of the discharge area are not restricted and can be adjusted according to actual printing conditions.

[0093] The quality monitoring method of the direct writing molding circuit provided in this embodiment uses the needle position to determine the range of the discharge area, and crops the detection image according to the range of the discharge area to obtain a captured image of the discharge area, ensuring that the captured image of the discharge area is identical to the preset template image except for the discharge area, thereby improving the accuracy of calculating the discharge area using the difference image.

[0094] Step S202 , performing binarization processing and connected domain analysis on the collected image to obtain a collected binary image, and determining the discharge area of ​​the collected image based on the collected binary image.

[0095] Specifically, the above step S202 includes:

[0096] Step S2021 , obtaining pixel values ​​at each position of the collected image, and binarizing the pixel values ​​at each position of the collected image to obtain the discharge position of the collected image.

[0097] Specifically, the pixel values ​​at each position of the collected image are obtained, and a pixel constant is set according to the difference between the pixel values ​​at the discharge position and the remaining positions. The pixel values ​​at each position of the collected image are binarized according to the relationship between the pixel values ​​at each position of the collected image and the pixel constant. The formula is as follows:

[0098]

[0099] Where H(x,y) represents the pixel value at position (x,y), R(x,y) represents the pixel value at each position in the acquired binary image, T represents a pixel constant, and 0≤T≤255.

[0100] According to the material and the surrounding environment, the points with pixel values ​​of 0 in the collected binary image can be set to represent the discharge points. This is only an example, but not limited to this. All points with pixel values ​​of 0 constitute the discharge position.

[0101] Step S2022: Perform a connected domain analysis on the discharge position of the captured image to determine the discharge connected domain of the captured image.

[0102] Specifically, all discharge locations are subjected to connected domain analysis to obtain the discharge connected domains of all discharge locations.

[0103] Step S2023: Calculate the area of ​​the discharge connected domain as the discharge area of ​​the captured image.

[0104] Specifically, the area of ​​the discharge connected domain can be automatically calculated using a software measurement method, and the calculation result can be used as the discharge area of ​​the captured image. This is only an example, but not limited to this.

[0105] The quality monitoring method for direct writing molding circuits provided in this embodiment can more accurately determine the discharge area of ​​the captured image through binarization processing and connected domain analysis, thereby improving the accuracy of broken material detection results.

[0106] Step S203 , performing binarization processing and connected domain analysis on the preset template image to obtain a template binary image, and determining the discharge area of ​​the preset template image according to the template binary image.

[0107] Specifically, the calculation method of the discharge area of ​​the preset template image is the same as the calculation process in step S202, which will not be repeated here. It should be noted that the image size of the preset template image and the acquired image is exactly the same, that is, the difference between the preset template image and the acquired image is only the difference in the discharge area, and the other positions should be kept as the same as possible.

[0108] In some optional implementations, the process of obtaining the preset template image includes:

[0109] Step b1, obtaining multiple template images in a needle-discharging state.

[0110] Specifically, the preset template image is the comparison standard for the collected images during the actual detection process, so it is necessary to obtain multiple template images in the stable discharge state of the needle. It should be noted that the acquisition process of each template image is the same as the acquisition process of the collected image. It is also necessary to determine the discharge area according to the needle position, and then determine the template image according to the discharge area. The specific process will not be repeated here.

[0111] Step b2: Calculate the average value of pixels at the same position in each template image, compare the pixel value at each position in each template image with the corresponding pixel average value, and obtain the position pixel difference.

[0112] Specifically, the formula for calculating the average value of pixels at the same position in each template image is as follows:

[0113]

[0114] Among them, g(x,y) represents the average value of pixels at the same position (x,y) in multiple template images, n represents the total number of template images, and h i (x,y) represents the pixel value at position (x,y) in the i-th template image, where 0≤i≤n, 0≤x≤image width, and 0≤y≤image length.

[0115] Calculate the difference between the pixel value at each position in each template image and the corresponding pixel average value, and obtain the calculation formula for the position pixel difference:

[0116] |h i (x,y)-g(x,y) where 0≤i <n。

[0117] Step b3: determining a plurality of valid template images according to the position pixel difference of each position in each template image and a preset pixel difference threshold.

[0118] Specifically, according to the actual printing material, a preset pixel difference threshold is set in advance, and the position pixel difference value of each position in each template image is compared with the preset pixel difference threshold. The formula is as follows:

[0119] |h i (x,y)-g(x,y)|≥K, where 0≤i <n

[0120] Wherein, K represents a preset pixel difference threshold.

[0121] If the number of position pixel differences at each position in a template image that is greater than a preset pixel difference threshold is within a preset difference number range, then the template image is a valid template image. Conversely, if the number of position pixel differences at each position in a template image that is greater than a preset pixel difference threshold exceeds a preset difference number range, then the template image is an invalid template image. After eliminating invalid template images, multiple valid template images remain. This is only an example, but is not limited to this.

[0122] Step b4, calculating the average value of valid pixels at the same position in each valid template image, and fusing the average values ​​of valid pixels at all positions to obtain a preset template image.

[0123] Specifically, the average value of valid pixels at the same position in each valid template image is calculated using the following formula:

[0124]

[0125] Where H(x,y) represents the average value of the effective pixels at the same position (x,y) in each effective template image, m represents the number of effective template images, and 0<m≤n, h i (x,y) represents the pixel value at position (x,y) in the i-th valid template image.

[0126] The effective pixel average values ​​H(x,y) of all positions are fused to obtain the preset template image.

[0127] The quality monitoring method of the direct writing molding circuit provided in this embodiment processes and analyzes multiple stable discharge images to obtain a preset template image as a standard for stable discharge. This is beneficial for comparing the actual discharge situation with the standard state of stable discharge in the detection of broken material, and then determining whether the actual discharge has broken material, thereby improving the accuracy of broken material detection.

[0128] In some optional implementations, the above step b3 includes:

[0129] Step b31 : comparing the position pixel difference of each position in each template image with a preset pixel difference threshold, and taking the position where the position pixel difference is smaller than the preset pixel difference threshold as a valid position.

[0130] Step b32: Calculate the effective ratio of the effective position in each template image to the total position in each template image.

[0131] Step b33: compare the effective ratio with a preset effective threshold, and take the template image with an effective ratio greater than the preset effective threshold as a valid template image.

[0132] Specifically, to ensure accurate determination of the effective template image, it can be determined by calculating the effective ratio of the effective position to the total position in each template image, and the template image whose effective ratio of the effective position in the template image is greater than the preset effective threshold is taken as the effective template image, thereby improving the effectiveness of the preset template image.

[0133] The quality monitoring method for the direct writing molding circuit provided in this embodiment determines the effective position through the size relationship between the position pixel difference and the preset pixel difference threshold, and determines the effective template image based on the ratio of the effective position to the total position. The obtained effective template image can more accurately reflect the image characteristics of the discharge area during stable discharge, thereby improving the practicality of the effective template image.

[0134] Step S204: Subtract the acquired binary image from the template binary image to obtain a difference image, and perform connected domain analysis on the difference image to obtain a difference analysis result. Figure 1 Step S104 of the illustrated embodiment will not be described in detail here.

[0135] Step S205 , calculating the ratio of the discharge area of ​​the captured image to the discharge area of ​​the preset template image, and monitoring the quality of the direct writing circuit according to the relationship between the discharge area ratio and the preset ratio range and the difference analysis result.

[0136] In some optional embodiments, monitoring the quality of the direct writing circuit based on the relationship between the discharge area ratio and the preset ratio range includes:

[0137] In step S2051 , if the discharge area ratio is greater than the upper limit of the preset ratio range, or less than the lower limit of the preset ratio range, or if there is a difference in the discharge positions of the difference images, the quality of the direct writing circuit is unqualified.

[0138] Specifically, whether the quality of the direct writing molding circuit is qualified cannot be determined only based on the fact that the discharge area ratio is greater than the upper limit of the preset ratio range, or is less than the lower limit of the preset ratio range. For example, the preset ratio range is 85% to 110%, the length and width of the discharge area in the actual detection are 1 mm and 2 mm respectively, and the length and width of the discharge area in the preset template image are 2 mm and 2 mm respectively. At this time, the detected discharge area is smaller than the area of ​​the preset template image, and the discharge area ratio is 50%, which is lower than the lower limit of the preset ratio range. However, it may be that the discharge speed is slowed down, resulting in a shorter length of the material within the detection range; if the length and width of the discharge area in the actual detection are 2 mm and 2 mm respectively, and the length and width of the discharge area in the preset template image are 1 mm and 2 mm respectively, the detected discharge area is larger than the discharge area of ​​the preset template image, and the discharge area ratio is 200%, which is higher than the upper limit of the preset ratio range, but it may be that the needle position is increased, the discharge speed is accelerated, resulting in a longer length of the material within the detection range; further determine whether there is a difference in the discharge position of the difference image. If there is a difference, it indicates that the discharge is abnormal. Any of the above three situations can be used to determine that a print quality problem has occurred in the direct write circuit. If a print quality problem occurs, printing is stopped immediately.

[0139] Step S2052: If the discharge area ratio is within the preset ratio range and there is no difference in the discharge positions of the difference images, the quality of the direct writing circuit is qualified.

[0140] Specifically, if the discharge area ratio is within the preset range, the quality of the direct-write circuit cannot be directly determined to be acceptable. For example, in actual testing, the length and width of the discharge area are 1mm and 4mm, respectively, while the length and width of the discharge area in the preset template image are 2mm and 2mm, respectively. In this case, the detected discharge area is exactly the same as the discharge area in the preset template image, but the discharge may be thinner, and the discharge still has defects. Therefore, it is necessary to further determine whether there is a difference in the discharge position based on the difference image. If the discharge area ratio is within the preset range and there is no difference, the quality of the direct-write circuit is acceptable. If the quality is acceptable, printing continues.

[0141] The quality monitoring method of the direct writing molding circuit provided in this embodiment directly determines whether the material is broken by calculating the relationship between the output area ratio of the collected image and the preset ratio range. It can be applied to liquid materials, has high versatility, and does not require indirect detection of material breaks through feeding conditions, thereby improving the accuracy of material break detection in actual printing.

[0142] In a specific embodiment, stacked lines are printed continuously, with a printing speed of 8mm / s, a printing line width of 150μm, a line length of 1mm, a stacking height of 500μm, a camera detection module field of view of 2.8mm*2.3mm, a detection time interval of 1.2s, and a negative correlation between the detection interval and the printing speed. The printing needle prints liquid silver paste lines with a line width of 150μm and a line length of 1mm at a speed of 8mm / s, and multi-layer stacking printing of liquid metal is achieved by lifting the printing needle. During the printing process, 9 images in the normal discharge state are taken and fused to produce a standard template image (preset template image). During the actual printing process, the image is obtained in real time and the broken material is detected by the quality monitoring method of the direct writing molding circuit in the above embodiment.

[0143] This embodiment also provides a quality monitoring system for a direct-write molding circuit. This system is used to implement the above-mentioned embodiments and preferred embodiments, and details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the systems described in the following embodiments are preferably implemented in software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.

[0144] This embodiment provides a quality monitoring system for direct writing molding circuits, such as Figure 3 As shown, including:

[0145] Image acquisition module 301, used to obtain the needle position of the detection image and determine the collected image of the discharge area according to the needle position;

[0146] The actual discharge area determination module 302 is used to perform binarization processing and connected domain analysis on the collected image to obtain a collected binary image, and determine the discharge area of ​​the collected image based on the collected binary image;

[0147] The standard discharge area determination module 303 is used to perform binarization processing and connected domain analysis on the preset template image to obtain a template binary image, and determine the discharge area of ​​the preset template image based on the template binary image;

[0148] The difference analysis module 304 is used to perform a difference analysis on the acquired binary image and the template binary image to obtain a difference image, and perform a connected component analysis on the difference image to obtain a difference analysis result;

[0149] The quality monitoring module 305 is used to calculate the ratio of the discharge area of ​​the captured image to the discharge area of ​​the preset template image, and monitor the quality of the direct writing circuit based on the relationship between the discharge area ratio and the preset ratio range and the difference analysis results.

[0150] In some optional implementations, the image acquisition module 301 includes:

[0151] The needle position detection unit is used to obtain a detection image and determine the needle position in the detection image using a needle position model.

[0152] The discharge area range determination unit is used to determine the discharge area range according to the needle position.

[0153] The image acquisition unit is used to crop the detection image according to the range of the discharge area to obtain the acquired image of the discharge area.

[0154] In some optional embodiments, the needle position detection unit includes:

[0155] The sample acquisition subunit is used to acquire multiple sample images, each of which contains the needle position.

[0156] The feature extraction subunit is used to extract the needle position features in the sample image using deep learning.

[0157] The model training subunit is used to train a preset deep learning model using the needle position features in multiple sample images to obtain a needle position model.

[0158] The position determination subunit is used to obtain a detection image, input the detection image into the needle position model, and obtain the needle position of the detection image.

[0159] In some optional implementations, the actual discharge area determination module 302 includes:

[0160] The binarization processing unit is used to obtain the pixel value of each position of the collected image, and perform binarization processing on the pixel value of each position of the collected image to obtain the discharge position of the collected image.

[0161] The connected domain analysis unit is used to perform connected domain analysis on the discharge position of the collected image to determine the discharge connected domain of the collected image.

[0162] The discharge area calculation unit is used to calculate the area of ​​the discharge connected domain as the discharge area of ​​the collected image.

[0163] In some optional implementations, the quality monitoring module 305 includes:

[0164] The unbroken material determining unit is used to determine that the quality of the direct writing molding circuit is unqualified if the discharge area ratio is greater than the upper limit of the preset ratio range, or is less than the lower limit of the preset ratio range, or there is a difference in the discharge position of the difference image.

[0165] The material breaking determination unit is used to determine that the quality of the direct writing molding circuit is qualified if the material discharge area ratio is within a preset ratio range and there is no difference in the material discharge positions of the difference images.

[0166] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0167] The quality monitoring system of the direct write molding circuit in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0168] The embodiment of the present invention also provides a computer device having the above Figure 3 The quality monitoring system of the direct write molding line is shown.

[0169] See also Figure 4 , Figure 4 is a structural diagram of a computer device provided by an optional embodiment of the present invention, such as Figure 4As shown, the computer device includes: one or more processors 10, memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components utilize different buses to communicate with each other and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in the memory or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Equally, multiple computer devices can be connected, and each device provides part of the necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 4 A processor 10 is taken as an example.

[0170] The processor 10 may be a central processing unit, a network processor, or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic, or any combination thereof.

[0171] The memory 20 stores instructions that can be executed by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0172] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created based on the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0173] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0174] The computer device further includes a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0175] The embodiment of the present invention also provides a computer-readable storage medium. The above-mentioned method according to the embodiment of the present invention can be implemented in hardware, firmware, or implemented as a computer code that can be recorded in a storage medium, or implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor or hardware, the method shown in the above embodiment is implemented.

[0176] Although the embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention. Such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for monitoring the quality of a direct-write circuit, characterized in that: The method comprises: Obtain the needle position of the detection image, and determine the collected image of the discharge area based on the needle position; Performing binarization processing and connected domain analysis on the collected image to obtain a collected binary image, and determining a discharge area of ​​the collected image according to the collected binary image; Performing binarization processing and connected domain analysis on the preset template image to obtain a template binary image, and determining the discharge area of ​​the preset template image according to the template binary image; Subtracting the acquired binary image from the template binary image to obtain a difference image, and performing connected domain analysis on the difference image to obtain a difference analysis result; Calculating the ratio of the discharge area of ​​the captured image to the discharge area of ​​the preset template image, and monitoring the quality of the direct writing circuit according to the relationship between the discharge area ratio and the preset ratio range and the difference analysis result; The step of performing binarization and connected domain analysis on the acquired image to obtain an acquired binary image, and determining the discharge area of ​​the acquired image based on the acquired binary image, comprises: obtaining pixel values ​​at each position of the acquired image, and binarizing the pixel values ​​at each position of the difference image to obtain the discharge position of the acquired image; performing connected domain analysis on the discharge position of the acquired image to determine the discharge connected domain of the acquired image; and calculating the area of ​​the discharge connected domain as the discharge area of ​​the acquired image; The quality of the direct-write molding circuit is monitored based on the size relationship between the discharge area ratio and the preset ratio range and the difference analysis result, including: if the discharge area ratio is greater than the upper limit of the preset ratio range, or is less than the lower limit of the preset ratio range, or there is a difference in the discharge position of the difference image, then the quality of the direct-write molding circuit is unqualified; if the discharge area ratio is within the preset ratio range and there is no difference in the discharge position of the difference image, then the quality of the direct-write molding circuit is qualified.

2. The method according to claim 1, characterized in that The method of obtaining the needle position of the detection image and determining the collected image of the discharge area according to the needle position includes: Acquire a detection image, and determine the needle position in the detection image using a needle position model; Determine the discharge area based on the needle position; The detection image is cropped according to the range of the discharge area to obtain a captured image of the discharge area.

3. The method according to claim 2, characterized in that The method of determining the needle position in the detection image using the needle position model includes: Acquire a plurality of sample images, each of the sample images including a needle tip position; Extracting needle position features in the sample image using deep learning; The needle position model is obtained by training a preset deep learning model using the needle position features in multiple sample images; A detection image is acquired, and the detection image is input into the needle position model to obtain the needle position of the detection image.

4. The method according to claim 1, wherein The process of obtaining the preset template image includes: Acquire multiple template images in a needle-discharging state; Calculate the average value of pixels at the same position in each template image, compare the pixel value at each position in each template image with the corresponding pixel average value, and obtain the position pixel difference; Determining multiple valid template images based on the position pixel difference of each position in each template image and a preset pixel difference threshold; The effective pixel average value at the same position in each effective template image is calculated, and the effective pixel average values ​​at all positions are fused to obtain the preset template image.

5. The method according to claim 4, characterized in that The determining of multiple valid template images according to the position pixel difference of each position in each template image and a preset pixel difference threshold comprises: Comparing the position pixel difference of each position in each template image with the preset pixel difference threshold, and taking the position where the position pixel difference is less than the preset pixel difference threshold as a valid position; Calculate the effective ratio of the effective position in each template image to the total position in each template image; The effective ratio is compared with a preset effective threshold, and the template image with an effective ratio greater than the preset effective threshold is taken as a valid template image.

6. A quality monitoring system for direct writing molding circuits, characterized in that: The system is used to perform the quality monitoring method of the direct writing molding circuit according to any one of claims 1 to 5, and the system includes: An image acquisition module is used to obtain the needle position of the detection image and determine the acquisition image of the discharge area according to the needle position; an actual discharge area determination module, configured to perform binarization processing and connected domain analysis on the collected image to obtain a collected binary image, and determine the discharge area of ​​the collected image based on the collected binary image; A standard discharge area determination module is used to perform binarization processing and connected domain analysis on a preset template image to obtain a template binary image, and determine the discharge area of ​​the preset template image based on the template binary image; A difference analysis module is used to perform a difference analysis on the acquired binary image and the template binary image to obtain a difference image, and perform a connected domain analysis on the difference image to obtain a difference analysis result; The quality monitoring module is used to calculate the discharge area ratio of the collected image to the discharge area of ​​the preset template image, and monitor the quality of the direct writing molding circuit based on the size relationship between the discharge area ratio and the preset ratio range and the difference analysis result.

7. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method according to any one of claims 1 to 5 by executing the computer instructions.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method according to any one of claims 1 to 5.

Images