Ink jet nozzle detection method and system and 3D printer

Abstract

The invention provides an ink jet nozzle detection method and system and a 3D printer, and the method comprises the steps: firstly, collecting a first detection image of a to-be-detected ink jet nozzle, the first detection image being used for representing a detection printing model of the to-be-detected ink jet nozzle according to a standard jet hole detection diagram; wherein the standard spray hole detection diagram corresponds to a standard detection template, and the standard detection template comprises a detection frame and identification information. Secondly, performing image preprocessing and binarization processing on the first detection image to obtain a second detection image; next, the standard detection template is mapped to the second detection image, and the number of target pixel points of a detection frame in the second detection image after mapping is determined; finally, under the condition that the number of the target pixel points is smaller than a preset pixel point number threshold value, it is determined that the spraying holes corresponding to the detection frames corresponding to the number of the target pixel points are abnormal, and identification information of the detection frames is output. Therefore, the detection efficiency and accuracy of the ink jet nozzle can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of 3D printing, and in particular to an inkjet nozzle detection method, system and 3D printer. Background Art

[0002] Inkjet 3D printing (3D printing) technology is widely used in the fields of industrial printing and 3D printing. Its core principle is to accurately spray liquid ink droplets or binders onto the printing medium or powder plane through an inkjet nozzle to form the desired pattern or structure. In industrial inkjet printing equipment, the inkjet nozzle is a key component, and the working state of the nozzle (or nozzle) of the inkjet nozzle directly determines the printing quality and accuracy. For example, with the long-term operation of inkjet 3D printing equipment, the nozzle of the inkjet nozzle is easily affected by ink residue and dust accumulation, resulting in abnormal conditions such as nozzle blockage, uneven spraying or droplet deviation. These abnormalities are usually manifested as broken lines, defects or quality degradation in printed images or 3D printed products, which seriously affect the final product effect.

[0003] Therefore, in order to ensure the printing quality of inkjet 3D printing, it is necessary to detect the inkjet nozzle in a timely manner. The traditional detection method usually controls the inkjet nozzle to print a test pattern on a paper base or other substrate. Then, based on the test pattern, it depends on manual visual inspection and experience to determine whether there is any abnormality in the nozzle of the inkjet nozzle.

[0004] However, this manual inspection method is not only time-consuming and susceptible to human errors, but also prone to misjudgment or missed judgments, making it difficult to ensure the objectivity and consistency of the inspection results, thereby reducing the efficiency and accuracy of inkjet head inspection. Summary of the invention

[0005] The technical problem to be solved by the present invention is that the inkjet nozzle cannot be detected efficiently and accurately.

[0006] In order to solve the above technical problems, the present invention provides an inkjet nozzle detection method, system and 3D printer, which specifically adopt the following technical solutions:

[0007] In the first aspect, the present invention provides an inkjet nozzle detection method, comprising: first, collecting a first detection image of an inkjet nozzle to be tested, the first detection image is used to characterize the detection printing model of the inkjet nozzle to be tested according to the standard nozzle detection map. Among them, the standard nozzle detection map corresponds to a standard detection template, and the standard detection template includes: a detection frame corresponding to multiple nozzles of the inkjet nozzle to be tested, and identification information of the detection frame. Then, the first detection image is subjected to image preprocessing and binarization processing to obtain a second detection image. Next, the standard detection template is mapped to the second detection image to obtain the mapped second detection image. Determine the number of target pixels corresponding to the detection frame in the mapped second detection image, the target pixel number is the number of target pixels in the second detection image in the detection frame, and the target pixel is used to characterize the detection printing model. Finally, when the number of target pixels is less than the preset pixel number threshold, determine that the nozzle corresponding to the detection frame corresponding to the target pixel number has an abnormality, and output the identification information of the detection frame corresponding to the target pixel number, so as to determine the nozzle with the abnormality.

[0008] In the method, first, a test image of a test print model for characterizing the inkjet nozzle to be tested according to a standard nozzle test map is collected. Then, the test image is preprocessed and binarized to further highlight the line features of the test print model. Finally, effective pixel point detection is performed based on the binarized test image and the standard test template corresponding to the standard nozzle test map to determine whether the nozzle of the inkjet nozzle has an abnormality. In addition, the nozzle with an abnormality can also be determined based on the identification information of the output detection frame. In this way, the efficiency and accuracy of inkjet nozzle detection can be effectively improved.

[0009] In combination with the first aspect, in an optional implementation, the method further includes: first, when the number of target pixels is greater than or equal to a preset pixel number threshold, determine the centroid position corresponding to the detection frame in the mapped second detection image, the centroid position being the position of the centroid of the target pixel in the second detection image within the detection frame. Then, based on the centroid position corresponding to the detection frame and the preset reference centroid position, determine the horizontal coordinate offset and the vertical coordinate offset corresponding to the detection frame. Finally, when the horizontal coordinate offset is greater than the first offset threshold, or the vertical coordinate offset is greater than the second offset threshold, determine that the nozzle corresponding to the detection frame corresponding to the horizontal coordinate offset and the vertical coordinate offset has an abnormality, and output the identification information of the detection frame corresponding to the horizontal coordinate offset and the vertical coordinate offset.

[0010] In this implementation, after the effective pixel point detection of the nozzle in the inkjet head is passed, the centroid position corresponding to the detection frame in the mapped second detection image can also be determined to perform centroid detection, so as to further determine whether the nozzle of the inkjet head has abnormal conditions such as unstable or intermittent jetting. In this way, the accuracy of inkjet head detection can be further improved.

[0011] In combination with the first aspect, in an optional implementation, the method further includes: first, when the horizontal coordinate offset is less than or equal to the first offset threshold, and the vertical coordinate offset is less than or equal to the second offset threshold, or when the horizontal coordinate offset is greater than the first offset threshold and the vertical coordinate offset is greater than the second offset threshold, determining the number of connected lines corresponding to the detection frame in the mapped second detection image. Then, when the number of connected lines is greater than a preset line number threshold, determining that the nozzle corresponding to the detection frame corresponding to the number of connected lines has an abnormality, and outputting identification information of the detection frame corresponding to the number of connected lines.

[0012] In this implementation, after the centroid detection of the nozzle hole in the inkjet head is passed, the number of connected lines corresponding to the detection frame in the mapped second detection image can also be determined to perform line continuity detection, so as to further determine whether the nozzle hole of the inkjet head has abnormal conditions such as intermittent spraying. In this way, the accuracy of inkjet head detection can be further improved.

[0013] In combination with the first aspect, in an optional implementation, the method further includes: first, when the number of connected lines is less than or equal to a preset line number threshold, determining the angle difference corresponding to the detection frame in the mapped second detection image, where the angle difference is the angle between the fitted straight line of the target pixel point in the second detection image within the detection frame and the preset direction. Then, when the angle difference is greater than the preset angle threshold, determining that the nozzle corresponding to the detection frame corresponding to the angle difference has an abnormality, and outputting identification information of the detection frame corresponding to the angle difference. When the angle difference is less than or equal to the preset angle threshold, determining that the nozzle corresponding to the detection frame corresponding to the angle difference is in a normal working state.

[0014] In this implementation, after the line continuity detection of the nozzle holes in the inkjet head is passed, the angle difference corresponding to the detection frame in the mapped second detection image can also be determined to perform angle detection, so as to further determine whether the nozzle holes in the inkjet head have abnormal spray angles or other abnormal conditions. In this way, the accuracy of inkjet head detection can be further improved.

[0015] In combination with the first aspect, in an optional implementation, performing image preprocessing on the first detection image includes: first, performing noise reduction processing on the first detection image to obtain a noise-reduced detection image. Then, performing image enhancement processing on the noise-reduced detection image to obtain an image-enhanced detection image. Secondly, performing region of interest ROI extraction on the image-enhanced detection image to obtain a region-extracted detection image. Finally, performing geometric correction on the region-extracted detection image to obtain a corrected detection image.

[0016] In this implementation, by performing image preprocessing on the first detection image, noise in the first detection image can be removed, and line features of the detection printing model can be enhanced, so as to improve the accuracy of subsequent inkjet head detection based on the detection image.

[0017] In combination with the first aspect, in an optional implementation, the noise reduction process uses a median filtering method, the image enhancement process uses a high-pass filtering method, and the geometric correction uses a perspective transformation method.

[0018] In combination with the first aspect, in an optional implementation, the above-mentioned standard nozzle detection image includes: multiple detection lines, gap areas, and auxiliary correction marks. Among them, the multiple detection lines correspond one-to-one to the multiple nozzles of the inkjet nozzle to be tested, and the detection lines are used to indicate the patterns of the nozzles corresponding to the detection lines; the gap areas are used to separate the multiple detection lines; and the auxiliary correction marks are used to perform geometric correction on the first detection image.

[0019] In combination with the first aspect, in an optional implementation, the auxiliary correction mark is: two parallel straight lines located above and below the standard nozzle detection map, or two parallel straight lines located above and below the standard nozzle detection map, respectively. Figure 4 The four crosshairs at the corners, or respectively at the standard nozzle detection Figure 4 Four calibration points for each corner.

[0020] In the second aspect, the present invention provides an inkjet nozzle detection system, including: an acquisition module, a preprocessing module and a detection module. The acquisition module is used to acquire a first detection image of the inkjet nozzle to be tested, and the first detection image is used to characterize the detection printing model of the inkjet nozzle to be tested according to the standard nozzle detection diagram; wherein the standard nozzle detection diagram corresponds to a standard detection template, and the standard detection template includes: a detection frame corresponding to multiple nozzles of the inkjet nozzle to be tested, and identification information of the detection frame. The preprocessing module is used to perform image preprocessing and binarization on the first detection image to obtain a second detection image. The detection module is used to map the standard detection template to the second detection image to obtain a mapped second detection image. And determine the number of target pixels corresponding to the detection frame in the mapped second detection image, the target pixel number is the number of target pixels in the second detection image in the detection frame, and the target pixel is used to characterize the detection printing model. The detection module is also used to determine that the nozzle corresponding to the detection frame corresponding to the target number of pixels has an abnormal situation when the number of target pixels is less than a preset pixel number threshold, and output the identification information of the detection frame corresponding to the target number of pixels to determine the nozzle with the abnormal situation.

[0021] In a third aspect, the present invention provides a 3D printer, comprising: a printing system and an inkjet nozzle detection system. The printing system is used to print a target model through the inkjet nozzle to be tested. The inkjet nozzle detection system is used to execute the method provided in the first aspect and any optional implementation method.

[0022] In a fourth aspect, the present invention provides an electronic device comprising: a memory and one or more processors; the memory is coupled to the processor; wherein the memory stores computer program code, the computer program code comprises computer instructions, and when the computer instructions are executed by the processor, the electronic device executes the method provided in the second aspect above.

[0023] In a fifth aspect, the present invention provides a computer-readable storage medium, comprising computer instructions, which, when executed on an electronic device, enable the electronic device to execute the method provided in the second aspect.

[0024] It can be understood that the beneficial effects that can be achieved by the inkjet nozzle detection system provided by the second aspect, the 3D printer of the third aspect, the electronic device of the fourth aspect, and the computer-readable storage medium of the fifth aspect can be referred to the beneficial effects in the first aspect and any possible design method thereof, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 A flow chart of an inkjet nozzle detection method provided in an embodiment of the present application;

[0026] Figure 2 Schematic diagram of the standard nozzle detection diagram provided in the embodiment of the present application Figure 1 ;

[0027] Figure 3 A schematic diagram of the arrangement of the detection lines provided in the embodiment of the present application;

[0028] Figure 4 Schematic diagram of the standard nozzle detection diagram provided in the embodiment of the present application Figure 2 ;

[0029] Figure 5 A schematic diagram of a standard detection template provided in an embodiment of the present application;

[0030] Figure 6 A schematic diagram of a second detection image after mapping provided in an embodiment of the present application;

[0031] Figure 7 A schematic diagram of the structure of an inkjet nozzle detection system provided in an embodiment of the present application;

[0032] Figure 8 A schematic diagram of the structure of a 3D printer provided in an embodiment of the present application. DETAILED DESCRIPTION

[0033] The following embodiments are described in detail, and examples thereof are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following embodiments do not represent all implementations consistent with the present application. They are only examples of systems and methods consistent with some aspects of the present application as detailed in the claims.

[0034] Inkjet 3D printing (3D printing) technology is widely used in the fields of industrial printing and 3D printing. Its core principle is to accurately spray liquid ink droplets or binders onto the printing medium or powder plane through an inkjet nozzle to form the desired pattern or structure. In industrial inkjet printing equipment, the inkjet nozzle is a key component, and the working state of the nozzle (or nozzle) of the inkjet nozzle directly determines the printing quality and accuracy. For example, with the long-term operation of inkjet 3D printing equipment, the nozzle of the inkjet nozzle is easily affected by ink residue and dust accumulation, resulting in abnormal conditions such as nozzle blockage, uneven spraying or droplet deviation. These abnormalities are usually manifested as broken lines, defects or quality degradation in printed images or 3D printed products, which seriously affect the final product effect.

[0035] Therefore, in order to ensure the printing quality of inkjet 3D printing, it is necessary to detect the inkjet nozzle in a timely manner. The traditional detection method usually controls the inkjet nozzle to print a test pattern on a paper base or other substrate. Then, based on the test pattern, it depends on manual visual inspection and experience to determine whether there is any abnormality in the nozzle of the inkjet nozzle.

[0036] However, this manual inspection method is not only time-consuming and susceptible to human errors, but also prone to misjudgment or missed judgments, making it difficult to ensure the objectivity and consistency of the inspection results, thereby reducing the efficiency and accuracy of inkjet head inspection.

[0037] In order to solve the above problems, the embodiments of the present application provide an inkjet nozzle detection method, system and 3D printer. The method first collects a detection image of a detection print model used to characterize the inkjet nozzle to be tested spraying according to a standard nozzle detection diagram. Then, based on the detection image and the standard detection template corresponding to the standard nozzle detection diagram, it can be determined whether the nozzle of the inkjet nozzle to be tested has an abnormality. In addition, the nozzle with an abnormality can also be determined based on the identification information of the output detection frame. In this way, efficient and accurate detection of inkjet nozzles can be achieved.

[0038] The solution provided by the embodiment of the present application is introduced below in conjunction with the accompanying drawings.

[0039] Specifically, Figure 1 The flowchart of the inkjet nozzle detection method provided in the embodiment of the present application is as follows: Figure 1 As shown, the inkjet nozzle detection method provided in the embodiment of the present application includes the following steps S101-S105:

[0040] S101, collecting a first detection image of an inkjet head to be tested.

[0041] In an embodiment of the present application, the first test image can be used to characterize the test print model of the inkjet head to be tested according to the standard nozzle test map. Specifically, first, the inkjet head to be tested can spray the test print model according to the standard nozzle test map. Then, the image of the test print model is collected as the first test image.

[0042] The standard nozzle detection diagram can be determined based on the number and arrangement of nozzles in the inkjet head to be tested, and the standard nozzle detection diagram can be used to indicate the pattern of nozzles in the inkjet head to be tested, so as to detect the spraying state of the nozzles.

[0043] In some embodiments, Figure 2 Schematic diagram of the standard nozzle detection diagram provided in the embodiment of the present application Figure 1 ,like Figure 2 As shown, the standard nozzle inspection diagram 200 includes: a plurality of inspection lines 201 , a gap area 202 , and an auxiliary correction mark 203 .

[0044] The plurality of detection lines correspond one-to-one to the plurality of nozzles of the inkjet head to be tested, and the detection lines can be used to indicate the pattern of the nozzles corresponding to the detection lines. Specifically, each nozzle in the inkjet head to be tested corresponds to an independent detection line in the standard nozzle detection diagram to ensure that the spraying state of each nozzle can be detected and identified separately.

[0045] The arrangement of multiple detection lines ensures that the detection lines are clearly distinguishable and can avoid mutual interference. Specifically, multiple detection lines can be arranged in a staggered manner to ensure full coverage of the detection area, and reserve appropriate gap areas. The gap areas can be used to separate multiple detection lines to avoid mutual interference between adjacent detection lines, so that the state of each nozzle can be accurately distinguished. In the case where multiple detection lines are difficult to distinguish, the multiple detection lines can be further subdivided and staggered to improve detection accuracy.

[0046] In one example, Figure 3 The schematic diagram of the arrangement of the detection lines provided in the embodiment of the present application is as follows: Figure 3 As shown in (a), the detection lines 301 can be arranged in a row and correspond to the nozzle holes 300 one by one.

[0047] In another example, multiple detection lines may be subdivided and arranged in an interlaced manner. Figure 3 As shown in (b), the detection lines can also be arranged in two rows, and the detection lines in the first row and the detection lines in the second row correspond to the nozzle holes in an alternating manner. Specifically, the detection line 301A corresponds to the nozzle hole 300A, the detection line 301B corresponds to the nozzle hole 300B, the detection line 301C corresponds to the nozzle hole 300C, the detection line 301D corresponds to the nozzle hole 300D, etc. In this way, it can be ensured that the detection images collected subsequently can clearly and accurately determine the spraying state of the nozzle hole.

[0048] In some embodiments, multiple detection lines can be set to different lengths to facilitate users to quickly distinguish and identify the detection lines. In addition, it is also convenient to quickly determine and adjust the standard detection template corresponding to the standard nozzle detection diagram so that the standard detection template meets the needs of the detection application.

[0049] For example, Figure 2 As shown, the length of the detection line 201A is greater than that of the detection line 201B, the detection line 201C, the detection line 201D and the detection line 201E. In this way, it is easy to quickly distinguish and locate the detection lines on the left side of the detection line 201A (for example, the detection line 201B and the detection line 201C) and the detection lines on the right side of the detection line 201A (for example, the detection line 201D and the detection line 201E).

[0050] Continue to see Figure 2The auxiliary correction mark 203 can be used to perform geometric correction on the first detection image to ensure the accuracy of the detection.

[0051] In some embodiments, Figure 2 As shown, the auxiliary calibration mark 203 may be: two parallel straight lines (straight line 203A and straight line 203B) located above and below the standard nozzle detection diagram, respectively. Or, Figure 4 Schematic diagram of the standard nozzle detection diagram provided in the embodiment of the present application Figure 2 ,like Figure 4 As shown in (a), the auxiliary calibration mark 203 can also be: located at the standard nozzle detection Figure 4 Four crosshairs at the corners (crosshair 203C, crosshair 203D, crosshair 203E and crosshair 203F). Or, Figure 4 As shown in (b), the auxiliary calibration mark 203 can also be: located at the standard nozzle detection Figure 4 Four calibration points of the corners (calibration point 203G, calibration point 203H, calibration point 203I and calibration point 203J).

[0052] In the embodiment of the present application, each standard nozzle detection image has a corresponding standard detection template, and the standard detection template can be used to quickly locate the pattern of each nozzle spray in the first detection image to further determine the spray state of the nozzle.

[0053] Figure 5 A schematic diagram of a standard detection template provided in an embodiment of the present application, such as Figure 5 As shown, the standard detection template 500 includes: a detection frame 501 corresponding one-to-one to multiple nozzles of the inkjet nozzle to be tested, and identification information 502 of the detection frame 501. The identification information can be, for example, a digital number, coordinate information, etc. Since there is a one-to-one mapping relationship between the detection frame and the nozzle, the identification information and the nozzle also have a one-to-one mapping relationship. That is, the nozzle in the inkjet nozzle to be tested can be effectively and accurately located through the identification information. In this way, the nozzle with abnormal conditions in the inkjet nozzle to be tested can be accurately located through the identification information.

[0054] S102: Perform image preprocessing and binarization processing on the first detection image to obtain a second detection image.

[0055] Next, the first detection image collected can be processed to remove noise, extract regions, perform geometric correction, and perform binarization to obtain a second detection image, that is, the second detection image is a binarized image. In this way, the spray state of the nozzle in the inkjet head to be tested can be more accurately determined based on the second detection image, thereby improving the detection accuracy.

[0056] In some embodiments, performing image preprocessing on the first detection image in S102 specifically includes the following steps S1021-S1024:

[0057] S1021. Perform noise reduction processing on the first detection image to obtain a noise-reduced detection image.

[0058] Specifically, the noise reduction process can adopt the median filtering method. For the noise existing in the first detection image, especially the noise caused by dust particles, the median filtering method can be used for noise reduction. The median filtering can effectively remove salt and pepper noise and some random noise by replacing the gray value of the pixel point with the median of the gray value in the pixel neighborhood, thereby improving the clarity of the first detection image.

[0059] S1022: Perform image enhancement processing on the denoised detection image to obtain an image enhanced detection image.

[0060] Specifically, the image enhancement process can adopt the high-pass filtering method. In order to highlight the characteristics of the nozzle injection, the high-pass filtering can be used to enhance the noise-reduced detection image. The high-pass filtering can extract the edge and detail information in the noise-reduced detection image, thereby enhancing the characteristics of the nozzle injection, which is convenient for subsequent feature extraction and analysis.

[0061] S1023, extracting the region of interest (ROI) from the enhanced detection image to obtain a detection image after region extraction.

[0062] Specifically, ROI extraction can be performed on the detection image after image enhancement according to the standard detection template to remove interference of irrelevant information in the detection image after image enhancement, thereby further improving the efficiency and accuracy of detection.

[0063] S1024, performing geometric correction on the detection image after region extraction to obtain a corrected detection image.

[0064] Specifically, the geometric correction can utilize the auxiliary correction mark in the standard nozzle detection image (for the convenience of description, referred to as identification pattern A below) and the pattern sprayed by the inkjet head to be tested in the first detection image after S1021-S1023 (i.e., the detection image after area extraction) according to the auxiliary correction mark (for the convenience of description, referred to as identification pattern B below), and use the perspective transformation method to perform geometric correction to obtain a corrected detection image.

[0065] Exemplarily, first, four corresponding points can be selected from the identification pattern A and the identification pattern B respectively. For example, when the auxiliary correction mark is four calibration points, the corresponding points can be four calibration points. Then, according to the coordinate information of the four corresponding points, the perspective transformation matrix H is calculated by the direct linear transformation (DLT) algorithm. Finally, the perspective transformation matrix H is applied to each pixel in the detection image after region extraction, so as to obtain the transformed image, that is, the corrected detection image.

[0066] In one example, the detection image after region extraction is geometrically corrected by the perspective transformation matrix H, and the expression of the corrected detection image is obtained as follows:

[0067]

[0068] Among them, (x ′ ,y ′ ) represents the pixel coordinates in the corrected detection image, (x, y) represents the pixel coordinates in the detection image after region extraction, (x, y, 1) represents the homogeneous coordinates corresponding to (x, y), ω ′ represents the scaling factor for homogeneous coordinates, Represents the perspective transformation matrix H.

[0069] Furthermore, the corrected detection image is binarized to obtain a second detection image.

[0070] In one implementation, the maximum inter-class variance (Otsu) method can be used to binarize the corrected detection image. Specifically, the Otsu method is a binarization method for automatic threshold selection. First, the grayscale histogram of the corrected detection image is calculated to obtain the number of pixels for each grayscale value. Secondly, for each possible threshold, the inter-class variance of the foreground and background is calculated. Then, the threshold that maximizes the inter-class variance is selected as the final segmentation threshold. Finally, the corrected detection image is divided into two parts, the foreground and the background, using the selected threshold to generate a binary image, that is, to obtain a second detection image.

[0071] S103: Map the standard detection template to the second detection image to obtain a mapped second detection image.

[0072] Specifically, the standard detection template corresponding to the standard nozzle detection image is mapped to the second detection image to obtain the mapped second detection image. That is, the printed lines sprayed by each nozzle in the second detection image according to the detection line are calibrated according to the detection frame in the standard detection template. The mapped second detection image may include the same detection frame corresponding to the standard detection template, as well as identification information of the detection frame. In this way, it is convenient to quickly and accurately detect whether the corresponding nozzle has an abnormality according to the printed lines in the detection frame.

[0073] S104: Determine the number of target pixels corresponding to the detection box in the mapped second detection image.

[0074] Next, the number of target pixels corresponding to any detection frame in the mapped second detection image can be determined to perform effective pixel detection. The number of target pixels is the number of target pixels in the second detection image within the detection frame, that is, the number of target pixels within the calibration area of ​​the detection frame in the second detection image. The target pixels are used to characterize the detection printing model, that is, to characterize the printed lines ejected by the nozzle.

[0075] For example, Figure 6 A schematic diagram of a second detected image after mapping provided in an embodiment of the present application, such as Figure 6 As shown, the white area 601 in the mapped second detection image represents the detection printing model, that is, the printed line ejected by each nozzle. The black area 602 in the second detection image represents the background. The detection frame 603 represents the detection frame corresponding to the printed line 601A, and the target pixel point is the white pixel point. That is, the number of target pixel points corresponding to the detection frame 603 is the total number of white pixel points in the detection frame 603.

[0076] S105: Determine whether the target pixel number is less than a preset pixel number threshold.

[0077] Furthermore, the target pixel number is compared with a preset pixel number threshold to determine whether the print line (i.e., effective pixel) ejected by the nozzle corresponding to the detection frame corresponding to the target pixel number meets the application requirements (i.e., the preset pixel number threshold). The preset pixel number threshold can be preset based on prior knowledge and actual application requirements, and this application does not make specific limitations on this.

[0078] S106. When the number of target pixels is less than a preset pixel number threshold, determine that the nozzle corresponding to the detection frame corresponding to the target pixel number has an abnormality, and output identification information of the detection frame corresponding to the target pixel number to determine the nozzle with the abnormality.

[0079] When the number of target pixels is less than the preset pixel number threshold, it can be determined that the effective pixel points ejected by the nozzle corresponding to the detection frame corresponding to the target pixel number do not meet the application requirements. In this case, it can be determined that the nozzle corresponding to the detection frame corresponding to the target pixel number has an abnormality, that is, the nozzle is invalid. At the same time, the identification information of the detection frame corresponding to the target pixel number can be output, because the detection frame corresponds to the nozzle one-to-one. Therefore, according to the identification information of the output detection frame, the nozzle with abnormal conditions can be quickly located, so that maintenance personnel can quickly deal with the abnormal nozzle.

[0080] In some embodiments, Figure 1 As shown, the method further comprises the following steps:

[0081] S107: When the number of target pixels is greater than or equal to a preset pixel number threshold, determine a centroid position corresponding to the detection frame in the mapped second detection image.

[0082] Furthermore, when the number of target pixels is greater than or equal to the preset pixel number threshold, it can be determined that the effective pixel points ejected by the nozzle corresponding to the detection frame corresponding to the target pixel number meet the application requirements. Next, the centroid position corresponding to the detection frame in the mapped second detection image can be determined for centroid detection. The centroid position is the position of the centroid of the target pixel in the second detection image within the detection frame.

[0083] The centroid detection helps to accurately identify the spray deviation of the nozzle, especially when the nozzle is blocked or otherwise abnormal, the centroid position will change significantly. Specifically, the calculation expression of the centroid position can be:

[0084]

[0085] Among them, (X C , Y C ) represents the center of mass position, N pixels Represents the total number of target pixels, (x i ,y i ) represents the position coordinates of the i-th target pixel.

[0086] S108. Determine the horizontal coordinate offset and the vertical coordinate offset corresponding to the detection frame according to the centroid position corresponding to the detection frame and the preset reference centroid position.

[0087] Specifically, the calculation expressions for the horizontal and vertical coordinate offsets can be:

[0088] Offset X =X C -X 0 ;

[0089] Offset Y =Y C -Y 0 ;

[0090] Among them, Offset X Indicates the horizontal axis offset, Offset Y Indicates the vertical coordinate offset, (X 0 , Y 0 ) represents the preset reference centroid position. The preset reference centroid position can be determined based on the detection line in the standard nozzle detection diagram and the detection frame in the standard detection template.

[0091] S109: Determine whether the horizontal axis offset is less than or equal to a first offset threshold, and whether the vertical axis offset is less than or equal to a second offset threshold.

[0092] Further, the horizontal coordinate offset is compared with a first offset threshold, and the vertical coordinate offset is compared with a second offset threshold to determine whether the print line ejected by the nozzle corresponding to the detection frame corresponding to the coordinate offset meets the application requirements of the offset.

[0093] Among them, the first offset threshold and the second offset threshold can be preset according to prior knowledge and actual application requirements, and this application does not make specific limitations on this.

[0094] S110. When the horizontal axis offset is greater than the first offset threshold, or the vertical axis offset is greater than the second offset threshold, or the horizontal axis offset is greater than the first offset threshold and the vertical axis offset is greater than the second offset threshold, determine that an abnormality exists in the nozzle corresponding to the detection frame corresponding to the horizontal axis offset and the vertical axis offset, and output identification information of the detection frame corresponding to the horizontal axis offset and the vertical axis offset.

[0095] Specifically, when at least one of the horizontal coordinate offset and the vertical coordinate offset is greater than the corresponding offset threshold, it can be determined that the print line ejected by the nozzle corresponding to the detection frame corresponding to the coordinate offset does not meet the application requirements of the offset. In this case, it can be determined that the nozzle corresponding to the detection frame corresponding to the coordinate offset has an abnormality, that is, the nozzle has unstable or intermittent ejection. At the same time, the identification information of the detection frame corresponding to the horizontal coordinate offset and the vertical coordinate offset can be output, so as to quickly locate the nozzle with the abnormality according to the output identification information of the detection frame, so that the maintenance personnel can quickly deal with the abnormal nozzle.

[0096] In some embodiments, Figure 1 As shown, the method further comprises the following steps:

[0097] S111. When the horizontal axis offset is less than or equal to the first offset threshold, and the vertical axis offset is less than or equal to the second offset threshold, determine the number of connected lines corresponding to the detection box in the mapped second detection image.

[0098] Specifically, when both the horizontal coordinate offset and the vertical coordinate offset are less than or equal to the corresponding offset threshold, it can be determined that the print line ejected by the nozzle corresponding to the detection frame corresponding to the coordinate offset meets the application requirements of the offset. Next, the number of connected lines corresponding to the detection frame in the mapped second detection image can be determined for line continuity detection. The number of connected lines is the number of connected lines in the second detection image within the detection frame.

[0099] Line continuity detection is to check whether the lines of the printed lines ejected by the nozzles are continuous, and to determine whether there are breaks or multiple lines. Specifically, firstly, the second detection image can be processed by morphological dilation and erosion operation methods to fill small breaks. Secondly, the number of connected lines L can be counted by using connected component analysis (CCA) or contour extraction methods. i Finally, according to the preset minimum line length threshold L min Filter out the noise or small-area pseudo lines and get the number of connected lines L line .

[0100] S112: Determine whether the number of connected lines is greater than a preset line number threshold.

[0101] Furthermore, the number of connected lines L line and the preset line number threshold T L The comparison is performed to determine whether the printed lines ejected by the nozzles corresponding to the detection frame corresponding to the number of connected lines meet the application requirements of the number of connected lines. The preset line number threshold can be preset according to prior knowledge and actual application requirements, and this application does not make specific restrictions on this. For example, the preset line number threshold can be 2.

[0102] S113. When the number of connected lines is greater than a preset line number threshold, determine that the nozzle corresponding to the detection frame corresponding to the number of connected lines has an abnormality, and output identification information of the detection frame corresponding to the number of connected lines.

[0103] Specifically, when the number of connected lines L line Greater than the preset line number threshold T LIn the case of the number of connected lines, it can be determined that the print line ejected by the nozzle corresponding to the detection frame corresponding to the number of connected lines does not meet the application requirement of the number of connected lines. In this case, it can be determined that the nozzle corresponding to the detection frame corresponding to the number of connected lines has an abnormality, that is, the nozzle has intermittent ejection. At the same time, the identification information of the detection frame corresponding to the number of connected lines can be output, so that the nozzle with the abnormality can be quickly located according to the output identification information of the detection frame, so that the maintenance personnel can quickly deal with the nozzle with the abnormality.

[0104] In some embodiments, Figure 1 As shown, the method further comprises the following steps:

[0105] S114. When the number of connected lines is less than or equal to a preset line number threshold, determine an angle difference corresponding to the detection frame in the mapped second detection image.

[0106] Specifically, when the number of connected lines is less than or equal to the preset line number threshold, it can be determined that the print line ejected by the nozzle corresponding to the detection frame corresponding to the number of connected lines meets the application requirement of the number of connected lines. Next, the angle difference corresponding to the detection frame in the mapped second detection image can be determined for angle detection. The angle difference is the angle between the fitted straight line of the target pixel point in the second detection image in the detection frame and the preset direction.

[0107] For example, taking the preset direction as the vertical direction (90°) as an example, first, the target pixel points in the second detection image in the detection frame can be fitted as a straight line. Then, the difference between the straight line and 90° is calculated to obtain the angle difference.

[0108] S115: Determine whether the angle difference is greater than a preset angle threshold.

[0109] Further, the angle difference is compared with a preset angle threshold to determine whether the print line ejected by the nozzle corresponding to the detection frame corresponding to the angle difference meets the angle application requirements. The preset angle threshold can be preset based on prior knowledge and actual application requirements, and this application does not make specific restrictions on this. For example, the preset angle threshold can be 5°.

[0110] S116. When the angle difference is greater than a preset angle threshold, determine that an abnormality exists in the nozzle corresponding to the detection frame corresponding to the angle difference, and output identification information of the detection frame corresponding to the angle difference.

[0111] Specifically, when the angle difference is greater than the preset angle threshold, it can be determined that the printed line ejected by the nozzle corresponding to the detection frame corresponding to the angle difference does not meet the angle application requirements. In this case, it can be determined that the nozzle corresponding to the detection frame corresponding to the number of connected lines has an abnormality, that is, the nozzle has an abnormal injection angle. At the same time, the identification information of the detection frame corresponding to the angle difference can be output, so that the nozzle with the abnormality can be quickly located according to the identification information of the output detection frame, so that the maintenance personnel can quickly deal with the abnormal nozzle.

[0112] S117: When the angle difference is less than or equal to a preset angle threshold, determine that the nozzle corresponding to the detection frame corresponding to the angle difference is in a normal working state.

[0113] Specifically, when the angle difference is less than or equal to the preset angle threshold, it can be determined that the print line ejected by the nozzle corresponding to the detection frame corresponding to the angle difference meets the angle application requirements. In this case, it can be determined that the nozzle corresponding to the detection frame corresponding to the number of connected lines has no abnormality and is in a normal working state.

[0114] The above-mentioned embodiment of the present application is used to provide an inkjet nozzle detection method, which first collects a detection image of a detection print model used to characterize the inkjet nozzle to be tested according to a standard nozzle detection map. Then, the detection image is subjected to image preprocessing and binarization to further highlight the line features of the detection print model. Finally, effective pixel point detection is performed based on the binarized detection image and the standard detection template corresponding to the standard nozzle detection map. Furthermore, centroid detection, line continuity detection and angle detection can also be performed to determine whether the nozzle of the inkjet nozzle has an abnormality. Moreover, the nozzle with an abnormality can also be determined based on the identification information of the output detection frame. In this way, the efficiency and accuracy of inkjet nozzle detection can be effectively improved.

[0115] Specifically, the inkjet nozzle detection method provided in the above embodiment of the present application also has the following beneficial effects:

[0116] 1. Significantly improve detection efficiency and shorten production cycle:

[0117] 1.1 Automated testing process: This method realizes the automation of the inkjet nozzle testing process without manual intervention, which greatly shortens the time required for testing.

[0118] 1.2 Fast detection method: The detection method uses a standard threshold to determine the nozzle status. It has a fast calculation speed and can quickly identify abnormal nozzles.

[0119] 2. Greatly improve detection accuracy and ensure printing quality:

[0120] 2.1 Refined standard nozzle detection diagram: The standard nozzle detection diagram provided in this application ensures that the state of each nozzle can be accurately distinguished, avoids interference between adjacent detection lines, and improves the accuracy of detection.

[0121] 2.2 Adaptive fine-tuning capability: Some nozzles have longer lines to facilitate fine-tuning of the standard detection template, which can improve detection accuracy and reliability.

[0122] 3. Comprehensive evaluation of the nozzle status to guide maintenance decisions:

[0123] 3.1 Independent detection of nozzles: This method can independently detect the working status of each nozzle, obtain accurate data of each nozzle, avoid the situation where some normal nozzles are regarded as abnormal nozzles, and improve the accuracy of detection.

[0124] 3.2 Quantitative evaluation of nozzle performance: This method can not only determine whether the nozzle is working properly, but also quantitatively evaluate the overall performance of the nozzle by calculating the overall state of the nozzle and the preset state threshold.

[0125] 4. Enhance the versatility and scalability of detection:

[0126] 4.1 Universal standard nozzle detection diagram: The standard nozzle detection diagram designed in this method has good versatility and can be applied to a variety of inkjet nozzle models and printing materials. There is no need to redesign for specific inkjet nozzles or materials, which reduces development costs.

[0127] 4.2 Scalable detection process: The detection process in this method can be adjusted and expanded according to actual needs. For example, the preprocessing parameters and thresholds can be adjusted according to the characteristics of different printing materials to meet the needs of different scenarios.

[0128] 5. Reduce maintenance costs and extend the service life of the nozzle:

[0129] 5.1 Accurate abnormality positioning: This method can accurately locate the position of abnormal nozzles, thereby facilitating maintenance personnel to carry out targeted maintenance, shortening maintenance time and reducing maintenance costs.

[0130] 5.2 Timely maintenance: By timely discovering abnormalities in the nozzle, maintenance or replacement can be carried out in advance to avoid further expansion of the problem, thereby extending the service life of the nozzle.

[0131] 5.3 Reduce printing failures: This detection method can effectively reduce printing failures caused by nozzle problems during the inkjet printing process, avoid waste of materials and time, and thus reduce production costs.

[0132] 6. Easy to integrate and realize automatic online detection:

[0133] 6.1 Real-time monitoring: During the printing process, the status of the inkjet nozzle can be monitored in real time, problems can be discovered and handled in time, and the stability and reliability of printing quality can be ensured.

[0134] 6.2 Closed-loop control: The test results can be fed back to the printing control system of the inkjet head to achieve closed-loop control of the printing process, thereby further improving the printing quality.

[0135] 7. Support different types of nozzle detection: There is no special requirement for the inkjet nozzle structure, and it is suitable for inkjet nozzles of various structures.

[0136] The present application also provides an inkjet head detection system. Figure 7 The schematic diagram of the structure of the inkjet nozzle detection system provided in the embodiment of the present application is as follows: Figure 7 As shown, the inkjet nozzle detection system 700 includes: a collection module 701, a pre-processing module 702 and a detection module 703.

[0137] The acquisition module 701 can be used to acquire a first detection image of the inkjet head to be tested, and the first detection image is used to characterize the detection printing model of the inkjet head to be tested sprayed according to the standard nozzle detection diagram. The standard nozzle detection diagram corresponds to a standard detection template, and the standard detection template includes: a detection frame corresponding to multiple nozzles of the inkjet head to be tested, and identification information of the detection frame.

[0138] The preprocessing module 702 may be used to perform image preprocessing and binarization processing on the first detection image to obtain a second detection image.

[0139] The detection module 703 can be used to map the standard detection template to the second detection image to obtain the mapped second detection image, and determine the number of target pixels corresponding to the detection frame in the mapped second detection image, where the number of target pixels is the number of target pixels in the second detection image within the detection frame, and the target pixels are used to characterize the detection printing model.

[0140] The detection module 703 can also be used to determine that the nozzle corresponding to the detection frame corresponding to the target number of pixels has an abnormality when the number of target pixels is less than a preset pixel number threshold, and output identification information of the detection frame corresponding to the target number of pixels to determine the nozzle with the abnormality.

[0141] In some embodiments, the detection module 703 may also be used to execute steps S107 - S117 in the above embodiments.

[0142] The inkjet nozzle detection system provided by the embodiment of the present application is adopted. The system can collect a detection image of the detection print model used to characterize the inkjet nozzle to be tested according to the standard nozzle detection map through the acquisition module. Then, the detection image can be preprocessed and binarized through the preprocessing module to further highlight the line features of the detection print model. Finally, the detection module performs effective pixel point detection based on the binarized detection image and the standard detection template corresponding to the standard nozzle detection map. Furthermore, centroid detection, line continuity detection and angle detection can also be performed to determine whether the nozzle of the inkjet nozzle has an abnormal situation. In addition, the detection module can also output the identification information of the detection frame to facilitate the determination of the nozzle with abnormal conditions. In this way, the efficiency and accuracy of inkjet nozzle detection can be effectively improved.

[0143] The embodiment of the present invention further provides a 3D printer, specifically, Figure 8 A schematic diagram of the structure of a 3D printer provided in an embodiment of the present application is shown in FIG. Figure 8 As shown, the 3D printer 800 includes: a printing system 801 and an inkjet head detection system 802 .

[0144] The printing system 801 can be used to print the target model through the inkjet head to be tested. The inkjet head detection system 802 can be used to execute the various methods or steps executed in the above-mentioned inkjet head detection image acquisition method embodiment.

[0145] An embodiment of the present invention further provides an electronic device, which may include: a display screen, a memory, and one or more processors. The display screen, the memory, and the processor are coupled. The memory is used to store computer program code, and the computer program code includes computer instructions. When the processor executes the computer instructions, the electronic device can execute the various methods or steps executed in the above-mentioned inkjet nozzle detection method embodiment. Of course, the electronic device includes but is not limited to the above-mentioned display screen, the memory, and one or more processors.

[0146] An embodiment of the present invention further provides a computer-readable storage medium for storing computer instructions for executing the above-mentioned inkjet head detection method.

[0147] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0148] In the description of the present invention, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0149] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0150] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0151] Similar parts between the embodiments provided in this application can be referenced to each other. The specific implementation methods provided above are only a few examples under the general concept of this application and do not constitute a limitation on the protection scope of this application. For those skilled in the art, any other implementation methods expanded based on the scheme of this application without creative work belong to the protection scope of this application.

Claims

1. A method for detecting an inkjet head, characterized in that: include: Collecting a first test image of the inkjet head to be tested, wherein the first test image is used to characterize a test print model of the inkjet head to be tested sprayed according to a standard nozzle test diagram; wherein the standard nozzle test diagram corresponds to a standard test template, and the standard test template includes: a test frame corresponding to a plurality of nozzles of the inkjet head to be tested, and identification information of the test frame; Performing image preprocessing and binarization processing on the first detection image to obtain a second detection image; Mapping the standard detection template to the second detection image to obtain a mapped second detection image; Determine the number of target pixels corresponding to the detection frame in the mapped second detection image, where the number of target pixels is the number of target pixels in the second detection image within the detection frame, and the target pixels are used to characterize the detection print model; When the target pixel number is less than a preset pixel number threshold, it is determined that an abnormality exists in the nozzle corresponding to the detection frame corresponding to the target pixel number, and identification information of the detection frame corresponding to the target pixel number is output to determine the nozzle with the abnormality.

2. The method according to claim 1, characterized in that The method further comprises: When the number of target pixels is greater than or equal to the preset pixel number threshold, determine the centroid position corresponding to the detection frame in the mapped second detection image, where the centroid position is the position of the centroid of the target pixel in the second detection image within the detection frame; Determining a horizontal coordinate offset and a vertical coordinate offset corresponding to the detection frame according to a centroid position corresponding to the detection frame and a preset reference centroid position; When the horizontal axis offset is greater than the first offset threshold, or the vertical axis offset is greater than the second offset threshold, or the horizontal axis offset is greater than the first offset threshold and the vertical axis offset is greater than the second offset threshold, it is determined that an abnormality exists in the nozzle corresponding to the detection frame corresponding to the horizontal axis offset and the vertical axis offset, and identification information of the detection frame corresponding to the horizontal axis offset and the vertical axis offset is output.

3. The method according to claim 2, characterized in that The method further comprises: When the horizontal coordinate offset is less than or equal to the first offset threshold, and the vertical coordinate offset is less than or equal to the second offset threshold, determining the number of connected lines corresponding to the detection box in the mapped second detection image; When the number of connected lines is greater than a preset line number threshold, it is determined that an abnormality exists in the nozzle corresponding to the detection frame corresponding to the number of connected lines, and identification information of the detection frame corresponding to the number of connected lines is output.

4. The method according to claim 3, characterized in that The method further comprises: When the number of connected lines is less than or equal to the preset line number threshold, determining an angle difference value corresponding to the detection frame in the mapped second detection image, wherein the angle difference value is an angle between a fitting straight line of the target pixel point in the second detection image within the detection frame and a preset direction; When the angle difference is greater than a preset angle threshold, determining that an abnormality exists in the nozzle corresponding to the detection frame corresponding to the angle difference, and outputting identification information of the detection frame corresponding to the angle difference; When the angle difference is less than or equal to a preset angle threshold, it is determined that the nozzle corresponding to the detection frame corresponding to the angle difference is in a normal working state.

5. The method according to any one of claims 1 to 4, characterized in that: The performing image preprocessing on the first detection image comprises: Performing noise reduction processing on the first detection image to obtain a noise-reduced detection image; Performing image enhancement processing on the denoised detection image to obtain an image enhanced detection image; Extracting a region of interest (ROI) from the image enhanced detection image to obtain a detection image after region extraction; The detection image after the region extraction is geometrically corrected to obtain a corrected detection image.

6. The method according to claim 5, characterized in that The noise reduction process adopts a median filtering method, the image enhancement process adopts a high-pass filtering method, and the geometric correction adopts a perspective transformation method.

7. The method according to claim 1, characterized in that The standard nozzle inspection diagram includes: multiple inspection lines, gap areas, and auxiliary correction marks; Among them, the multiple detection lines correspond one-to-one to the multiple nozzles of the inkjet head to be tested, and the detection lines are used to indicate the patterns sprayed by the nozzles corresponding to the detection lines; the gap area is used to separate the multiple detection lines; and the auxiliary correction mark is used to perform geometric correction on the first detection image.

8. The method according to claim 7, characterized in that The auxiliary correction mark is: Two parallel straight lines respectively located above and below the standard nozzle detection diagram, or four cross lines respectively located at the four corners of the standard nozzle detection diagram, or four calibration points respectively located at the four corners of the standard nozzle detection diagram.

9. An inkjet head detection system, characterized in that: include: Acquisition module, preprocessing module and detection module; among them, The acquisition module is used to acquire a first detection image of the inkjet head to be tested, wherein the first detection image is used to characterize a detection printing model of the inkjet head to be tested sprayed according to a standard nozzle detection diagram; wherein the standard nozzle detection diagram corresponds to a standard detection template, and the standard detection template includes: detection frames corresponding to multiple nozzles of the inkjet head to be tested, and identification information of the detection frames; The preprocessing module is used to perform image preprocessing and binarization processing on the first detection image to obtain a second detection image; The detection module is used to map the standard detection template to the second detection image to obtain the mapped second detection image, and determine the number of target pixels corresponding to the detection frame in the mapped second detection image, wherein the number of target pixels is the number of target pixels in the second detection image within the detection frame, and the target pixels are used to characterize the detection print model; The detection module is further used to determine that there is an abnormality in the nozzle corresponding to the detection frame corresponding to the target number of pixels when the target number of pixels is less than a preset pixel number threshold, and output identification information of the detection frame corresponding to the target number of pixels to determine the nozzle with the abnormality.

10. A 3D printer, characterized in that: include: Printing system and inkjet head detection system; wherein, The printing system is used to print the target model through the inkjet nozzle to be tested; The inkjet head detection system is used to execute the method according to any one of claims 1-8.

Images