Inkjet head detection method, system and 3D printer

Abstract

The present invention provides an inkjet nozzle detection method, system and 3D printer, comprising: first, collecting a first detection image of the inkjet nozzle to be tested, the first detection image being used to characterize a detection printing model of the inkjet nozzle to be tested sprayed according to a standard nozzle detection diagram. The standard nozzle detection diagram corresponds to a standard detection template, and the standard detection template includes: a detection frame and identification information. 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, and the number of target pixel points of the detection frame in the mapped second detection image is determined. Finally, when the number of target pixel points is less than a preset pixel point number threshold, it is determined that the nozzle corresponding to the detection frame corresponding to the target pixel point number has an abnormality, and the identification information of the detection frame is output. In this way, the efficiency and accuracy of inkjet nozzle detection 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 adhesives 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 inkjet nozzle's nozzle (or 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 usually manifest as broken lines, defects or quality degradation in printed images or 3D printed products, seriously affecting the final product effect.

[0003] Therefore, to ensure the print quality of inkjet 3D printing, timely inspection of inkjet heads is necessary. Traditional inspection methods typically control the inkjet heads to print a test pattern on paper or other substrates. Based on the test pattern, manual visual inspection and experience are then used to determine whether the inkjet head nozzles are abnormal.

[0004] However, this manual inspection method is not only time-consuming and susceptible to human error, but also prone to misjudgment or missed judgment, 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] To solve the above technical problems, the present invention provides an inkjet head detection method, system and 3D printer, which specifically adopt the following technical solutions:

[0007] In a first aspect, the present invention provides an inkjet head inspection method, comprising: first, capturing a first inspection image of an inkjet head to be inspected, the first inspection image being used to represent an inspection print model ejected by the inkjet head to be inspected according to a standard nozzle orifice inspection pattern. The standard nozzle orifice inspection pattern corresponds to a standard inspection template, the standard inspection template comprising: inspection frames corresponding one-to-one to multiple nozzles of the inkjet head to be inspected, and identification information of the inspection frames. Then, performing image preprocessing and binarization on the first inspection image to obtain a second inspection image. Next, mapping the standard inspection template onto the second inspection image to obtain a mapped second inspection image. Determining the number of target pixels corresponding to the inspection frames in the mapped second inspection image, the target pixel number being the number of target pixels in the second inspection image within the inspection frames, the target pixels being used to represent the inspection print model. Finally, if the number of target pixels is less than a preset pixel number threshold, determining that the nozzles corresponding to the inspection frames corresponding to the target pixel number have an abnormality, and outputting identification information of the inspection frames corresponding to the target pixel number for use in identifying the nozzles with the abnormality.

[0008] In this method, a test image of a test print model representing the inkjet head under test spraying according to a standard nozzle test pattern is first captured. The test image is then preprocessed and binarized to highlight the line features of the test print model. Finally, valid pixel detection is performed based on the binarized test image and a standard detection template corresponding to the standard nozzle test pattern to determine whether the inkjet head's nozzles are abnormal. Furthermore, the nozzles with abnormalities can be identified based on the identification information of the output detection frame. This effectively improves the efficiency and accuracy of inkjet head testing.

[0009] In combination with the first aspect, in an optional implementation, the method further includes: first, when the number of target pixel points is greater than or equal to a preset pixel point number threshold, determining the center of mass position corresponding to the detection frame in the mapped second detection image, the center of mass position being the position of the center of mass of the target pixel points in the second detection image within the detection frame. Then, based on the center of mass position corresponding to the detection frame and the preset reference center of mass position, determining 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, determining that the nozzle corresponding to the detection frame corresponding to the horizontal coordinate offset and the vertical coordinate offset has an abnormality, and outputting 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 points of the inkjet nozzles are detected, the centroid position of the detection frame corresponding to the mapped second detection image can be determined to perform centroid detection, thereby further determining whether the inkjet nozzles have abnormal conditions such as unstable or intermittent jetting. This can further improve the accuracy of inkjet nozzle detection.

[0011] In conjunction with the first aspect, in an optional implementation, the method further includes: first, when the horizontal axis offset is less than or equal to a first offset threshold and the vertical axis offset is less than or equal to a second offset threshold, or when the horizontal axis offset is greater than the first offset threshold and the vertical axis 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 for the detection frame corresponding to the number of connected lines.

[0012] In this implementation, after the centroid of the inkjet nozzles is detected, the number of connected lines corresponding to the detection frame in the mapped second detection image can be determined to perform line continuity detection, thereby further determining whether the inkjet nozzles have exhibited abnormalities such as intermittent spraying. This can further improve the accuracy of inkjet nozzle detection.

[0013] In conjunction 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 for 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 inkjet head nozzles have passed line continuity testing, the angle difference corresponding to the detection frame in the mapped second test image can be determined to perform angle testing, further determining whether the inkjet head nozzles have abnormal spray angles or other abnormalities. This can further improve the accuracy of inkjet head testing.

[0015] In conjunction 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. Next, 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 adopts a median filtering method, the image enhancement process adopts a high-pass filtering method, and the geometric correction adopts a perspective transformation method.

[0018] In conjunction with the first aspect, in one optional implementation, the standard nozzle inspection image includes: multiple inspection lines, a gap area, and auxiliary correction marks. The multiple inspection lines correspond one-to-one to the multiple nozzles of the inkjet head to be tested, and the inspection lines are used to indicate the patterns ejected by the nozzles corresponding to the inspection lines; the gap area is used to separate the multiple inspection lines; and the auxiliary correction marks are used to perform geometric correction on the first inspection 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. Figure 4 The four cross lines at the corners, or respectively located at the standard nozzle detection Figure 4 Four calibration points of each corner.

[0020] In the second aspect, the present invention provides an inkjet nozzle detection system, comprising: 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 a plurality of 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 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 a mapped second detection image. And determine the number of target pixel points corresponding to the detection frame in the mapped second detection image, the target pixel point number is the number of target pixel points in the second detection image within the detection frame, and the target pixel points are used to characterize the detection printing model. The detection module is also 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 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 be used to determine the nozzle with the abnormality.

[0021] In a third aspect, the present invention provides a 3D printer comprising: a printing system and an inkjet head detection system. The printing system is configured to print a target model using the inkjet head to be tested. The inkjet head detection system is configured to execute the method described in the first aspect and any of the optional implementations.

[0022] In a fourth aspect, the present invention provides an electronic device comprising: a memory, 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, enables the electronic device to execute the method provided in the second aspect above.

[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 of 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 the 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 this application Figure 1 ;

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

[0028] Figure 4 Schematic diagram of the standard nozzle detection diagram provided in the embodiment of this 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 mapped second detection image provided in an embodiment of the present application;

[0031] Figure 7 A schematic diagram of the structure of the 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, with examples illustrated in the accompanying drawings. When the following description refers to the drawings, identical numbers in different figures represent identical or similar elements unless otherwise indicated. The embodiments described in the following embodiments are not intended to represent all possible implementations consistent with the present application. They are merely examples of systems and methods consistent with certain 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 adhesives 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 inkjet nozzle's nozzle (or 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 usually manifest as broken lines, defects or quality degradation in printed images or 3D printed products, seriously affecting the final product effect.

[0035] Therefore, to ensure the print quality of inkjet 3D printing, timely inspection of inkjet heads is necessary. Traditional inspection methods typically control the inkjet heads to print a test pattern on paper or other substrates. Based on the test pattern, manual visual inspection and experience are then used to determine whether the inkjet head nozzles are abnormal.

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

[0037] To address the above-mentioned issues, embodiments of the present application provide an inkjet nozzle detection method, system, and 3D printer. The method first captures a test image of a test print model used to characterize the inkjet nozzle to be tested, as it sprays according to a standard nozzle detection diagram. Then, based on the test image and the standard detection template corresponding to the standard nozzle detection diagram, it is possible to determine whether the nozzle of the inkjet nozzle to be tested has an abnormality. Furthermore, the nozzle with an abnormality can 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 following describes the solution provided by the embodiments of the present application 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 head 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 represent a test print pattern ejected by the inkjet head under test according to a standard nozzle test pattern. Specifically, first, the inkjet head under test can eject the test print pattern according to the standard nozzle test pattern. Then, an image of the test print pattern is captured 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. The standard nozzle detection diagram can be used to indicate the pattern of nozzles spraying 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 this application Figure 1 ,like Figure 2 As shown, the standard nozzle inspection diagram 200 includes: multiple inspection lines 201 , a gap area 202 , and an auxiliary calibration mark 203 .

[0044] The multiple test lines correspond one-to-one to the nozzles of the inkjet head under test, and the test lines can be used to indicate the spray pattern of the nozzles corresponding to the test lines. Specifically, each nozzle in the inkjet head under test corresponds to an independent test line in the standard nozzle test map, ensuring that the spray status of each nozzle can be individually detected and identified.

[0045] The arrangement of multiple detection lines ensures that they are clearly distinguishable and avoids mutual interference. Specifically, multiple detection lines can be staggered to ensure full coverage of the detection area, and appropriate gaps can be reserved to separate multiple detection lines to avoid mutual interference between adjacent detection lines, so that the status of each nozzle can be accurately distinguished. In cases where multiple detection lines are difficult to distinguish, they 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 one-to-one to the nozzle holes 300.

[0047] In another example, multiple detection lines can be subdivided and arranged in a staggered manner. Figure 3 As shown in (b), the test lines can also be arranged in two rows, with the first and second rows of test lines corresponding to the nozzles in an alternating pattern. Specifically, test line 301A corresponds to nozzle 300A, test line 301B corresponds to nozzle 300B, test line 301C corresponds to nozzle 300C, test line 301D corresponds to nozzle 300D, and so on. This ensures that the subsequent test images collected can clearly and accurately determine the spray status of the nozzles.

[0048] In some embodiments, multiple test lines can be set to different lengths to facilitate user identification of test lines. Furthermore, this facilitates rapid determination and adjustment of a standard test template corresponding to a standard nozzle test pattern, so that the standard test template meets the needs of the test application.

[0049] For example, Figure 2 As shown, the length of detection line 201A is longer than detection line 201B, detection line 201C, detection line 201D, and detection line 201E. This facilitates quick differentiation and positioning of detection lines to the left of detection line 201A (e.g., detection line 201B and detection line 201C) and to the right of detection line 201A (e.g., detection line 201D and 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, as Figure 2 As shown, the auxiliary calibration mark 203 can 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 this 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 cross lines at each corner (cross line 203C, cross line 203D, cross line 203E and cross line 203F). Or, as 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 spraying in the first detection image to further determine the spraying 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 inspection template 500 includes: an inspection frame 501 corresponding one-to-one to the multiple nozzles of the inkjet head to be tested, and identification information 502 for the inspection frame 501. The identification information may include, for example, a digital number, coordinate information, etc. Because there is a one-to-one mapping relationship between the inspection frame and the nozzles, there is also a one-to-one mapping relationship between the identification information and the nozzles. This means that the nozzles in the inkjet head to be tested can be effectively and accurately located using the identification information. In this way, the identification information can be used to precisely locate abnormal nozzles in the inkjet head to be tested.

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

[0055] Next, the captured first test image can be processed to remove noise, perform region extraction, perform geometric correction, and perform binarization to obtain a second test image, which is a binary image. This allows for more accurate determination of the ejection status of the nozzles in the inkjet head under test based on the second test image, thereby improving test 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, median filtering can be used for noise reduction. This method can be used to reduce noise in the first detection image, particularly noise caused by dust particles. By replacing the grayscale value of a pixel with the median of the grayscale values ​​within its neighborhood, median filtering effectively removes salt and pepper noise and other random noise, improving the clarity of the first detection image.

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

[0060] Specifically, image enhancement can utilize high-pass filtering. To highlight the characteristics of the nozzle jet, high-pass filtering can be used to enhance the noise-reduced detection image. High-pass filtering can extract edge and detail information from the noise-reduced detection image, thereby enhancing the characteristics of the nozzle jet and facilitating subsequent feature extraction and analysis.

[0061] S1023: Extract the region of interest (ROI) from the enhanced detection image to obtain a region-extracted detection image.

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

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

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

[0065] For example, first, four corresponding points can be selected from the identification pattern A and the identification pattern B, respectively. For example, if the auxiliary correction mark is four calibration points, the corresponding points can be four calibration points. Then, based on the coordinate information of the four corresponding points, the perspective transformation matrix H is calculated using a direct linear transform (DLT) algorithm. Finally, the perspective transformation matrix H is applied to each pixel in the detection image after region extraction to obtain a transformed image, i.e., a corrected detection image.

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

[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 with 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 selected threshold is used to divide the corrected detection image into two parts, the foreground and the background, to generate a binary image, that is, to obtain the second detection image.

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

[0072] Specifically, a standard inspection template corresponding to the standard nozzle inspection image is mapped onto the second inspection image to produce a mapped second inspection image. That is, the printed lines ejected by each nozzle in the second inspection image along the inspection line are calibrated based on the inspection frame in the standard inspection template. The mapped second inspection image can include the same inspection frame as that corresponding to the standard inspection template, as well as its identification information. This allows for rapid and accurate detection of abnormalities in the corresponding nozzle based on the printed lines within the inspection 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 target pixel number is the number of target pixels in the second detection image within the detection frame, i.e., the number of target pixels within the calibration area of ​​the detection frame in the second detection image. The target pixels are used to represent the detection print model, i.e., the printed lines ejected by the nozzles.

[0075] For example, Figure 6 A schematic diagram of the second detection image after mapping provided in an embodiment of the present application is shown as follows: Figure 6 As shown, white area 601 in the mapped second detection image represents the detection print model, that is, the printed lines ejected by each nozzle. Black area 602 in the second detection image represents the background. Detection box 603 represents the detection box corresponding to printed line 601A, and the target pixels are white pixels. That is, the number of target pixels corresponding to detection box 603 is the total number of white pixels within detection box 603.

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

[0077] Furthermore, the target number of pixels is compared with a preset pixel number threshold to determine whether the print line (i.e., valid pixels) ejected by the nozzle corresponding to the detection frame corresponding to the target number of pixels 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 impose 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 for determining the nozzle with the abnormality.

[0079] If the number of target pixels is less than a preset pixel threshold, it can be determined that the effective pixels 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 has failed. At the same time, the identification information of the detection frame corresponding to the target pixel number can be output. Since the detection frame corresponds to the nozzle one-to-one, the nozzle with the abnormality can be quickly located based on the output detection frame identification information, allowing maintenance personnel to quickly address the abnormal nozzle.

[0080] In some embodiments, as Figure 1 As shown, the method further includes 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, if the number of target pixels is greater than or equal to a preset pixel number threshold, it can be determined that the effective pixels ejected by the nozzle corresponding to the detection frame corresponding to the target pixel number meet the application requirements. Next, the center of mass position corresponding to the detection frame in the mapped second detection image can be determined for center of mass detection. The center of mass position is the position of the center of mass of the target pixel in the second detection image within the detection frame.

[0083] Center of mass detection helps to accurately identify the spray deviation of the nozzle, especially when the nozzle is blocked or has other abnormalities, the center of mass position will change significantly. Specifically, the calculation expression of the center of mass position can be:

[0084]

[0085] Among them, (X C , Y C ) represents the center of mass position, N pixels Indicates 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 center of mass position corresponding to the detection frame and the preset reference center of mass position.

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

[0088] Offset X =X C -X0;

[0089] Offset Y =Y C -Y0;

[0090] Among them, Offset X Indicates the horizontal coordinate offset, Offset Y represents the vertical coordinate offset, and (X0, Y0) 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 coordinate offset is less than or equal to a first offset threshold, and whether the vertical coordinate offset is less than or equal to a second offset threshold.

[0092] Furthermore, 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, if at least one of the horizontal and vertical offsets 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 offset requirements. In this case, it can be determined that the nozzle corresponding to the detection frame corresponding to the coordinate offset is abnormal, that is, the nozzle is experiencing unstable or intermittent jetting. At the same time, identification information of the detection frame corresponding to the horizontal and vertical offsets can be output, so that the nozzle with the abnormality can be quickly located based on the output identification information of the detection frame, allowing maintenance personnel to quickly address the abnormal nozzle.

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

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

[0098] Specifically, if both the horizontal and vertical offsets are less than or equal to corresponding offset thresholds, 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 offset requirements. Next, the number of connected lines corresponding to the detection frame in the mapped second detection image can be determined for line continuity testing. The number of connected lines refers to the number of connected lines in the second detection image within the detection frame.

[0099] Line continuity detection is to check whether the printed line ejected by the nozzle is continuous and whether there are breaks or multiple lines. Specifically, first, the second detection image can be processed by morphological dilation and erosion operations to fill small breaks. Second, the number of connected lines L can be counted 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 requirement for the number of connected lines. The preset line number threshold can be preset based on prior knowledge and actual application requirements, and this application does not impose specific limitations 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 an abnormality exists in the nozzle corresponding to the detection frame corresponding to the number of connected lines, 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 LIf the number of connected lines is too high, it can be determined that the print lines ejected by the nozzle corresponding to the detection frame corresponding to the number of connected lines do not meet the application requirement for 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 is abnormal, that is, the nozzle is intermittently ejecting. At the same time, identification information of the detection frame corresponding to the number of connected lines can be output. This output identification information of the detection frame can be used to quickly locate the nozzle with the abnormality, allowing maintenance personnel to quickly address the abnormal nozzle.

[0104] In some embodiments, as Figure 1 As shown, the method further includes 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, if the number of connected lines is less than or equal to a preset line number threshold, it can be determined that the printed line ejected by the nozzle corresponding to the detection frame corresponding to the number of connected lines meets the application requirement for 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 line of the target pixel point in the second detection image within the detection frame and the preset direction.

[0107] For example, taking the preset direction as the vertical direction (90°), first, the target pixel points in the second detection image within the detection frame can be fitted into 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] Furthermore, the angle difference is compared with a preset angle threshold to determine whether the printed line ejected by the nozzle corresponding to the detection frame corresponding to the angle difference meets the application angle requirement. The preset angle threshold can be preset based on prior knowledge and actual application requirements, and this application does not impose specific limitations 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, if the angle difference exceeds a 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 application angle requirements. In this case, it can be determined that the nozzle corresponding to the detection frame corresponding to the number of connected lines is abnormal, that is, the nozzle has an abnormal injection angle. At the same time, 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 based on the output detection frame identification information, allowing maintenance personnel to quickly address the abnormal nozzle.

[0112] S117 : When the angle difference is less than or equal to the 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, if the angle difference is less than or equal to a 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 meets the application angle requirement. 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 normal operation.

[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 spraying according to a standard nozzle detection diagram. 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 diagram. Furthermore, centroid detection, line continuity detection and angle detection can also be performed to determine whether the nozzle of the inkjet nozzle has abnormal conditions. Moreover, the nozzle with abnormal conditions 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 head 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 detection process: This method realizes the automation of the detection process of inkjet printheads without manual intervention, which greatly shortens the time required for detection.

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

[0119] 2. Significantly 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 status 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. Achieve a comprehensive assessment of printhead status and guide maintenance decisions:

[0123] 3.1 Independent nozzle detection: This method can independently detect the working status of each nozzle and obtain accurate data for each nozzle, thus avoiding the situation where some normal nozzles are mistaken for abnormal nozzles and improving the accuracy of detection.

[0124] 3.2 Quantitative evaluation of printhead performance: This method can not only determine whether the nozzle is working properly, but also quantitatively evaluate the overall performance of the printhead by calculating the overall status of the printhead and the preset status 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, making it easier for maintenance personnel to carry out targeted maintenance, shortening maintenance time and reducing maintenance costs.

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

[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 detection results can be fed back to the printing control system of the inkjet print head to achieve closed-loop control of the printing process, thereby further improving the printing quality.

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

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

[0137] The acquisition module 701 can be used to acquire a first test image of the inkjet head to be tested. The first test image is used to represent a test print model of the inkjet head to be tested sprayed according to a standard nozzle test pattern. The standard nozzle test pattern corresponds to a standard test template, which includes: a detection frame corresponding to each of the nozzles of the inkjet head to be tested, and identification information of the detection frame.

[0138] The preprocessing module 702 may be configured 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 configured to map the standard detection template onto the second detection image to obtain a mapped second detection image. The number of target pixels corresponding to the detection frame in the mapped second detection image is determined. The target pixel number is the number of target pixels in the second detection image within the detection frame. The target pixels are used to represent the detection print 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 be used to determine the nozzle with the abnormality.

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

[0142] The inkjet nozzle detection system provided by the embodiment of the present application can be used to collect a detection image of a detection print model that is used to characterize the inkjet nozzle to be tested according to the standard nozzle detection diagram through an acquisition module. Then, the detection image can be preprocessed and binarized by 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 diagram. Furthermore, centroid detection, line continuity detection and angle detection can be performed to determine whether the nozzle of the inkjet nozzle has abnormal conditions. In addition, the detection module can also output identification information of the detection frame to facilitate the identification of nozzles 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 using 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, memory, and processor are coupled. The memory is used to store computer program code, which includes computer instructions. When the processor executes the computer instructions, the electronic device can perform the various methods or steps performed in the above-mentioned inkjet head detection method embodiment. Of course, the electronic device includes but is not limited to the above-mentioned display screen, 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 to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of such features. In the description of the present invention, "plurality" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0149] In the present invention, unless otherwise specified or limited, the terms "installed," "connected," "connect," "fixed," etc. should be understood in a broad sense. For example, they can refer to fixed connection, detachable connection, or integration; mechanical connection, electrical connection; direct connection, or indirect connection through an intermediate medium; internal communication between two components, or interaction between two components, unless otherwise specified. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0150] In the description of this specification, the reference terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" mean 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 can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of 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 overall concept of this application and do not constitute a limitation on the scope of protection of this application. For those skilled in the art, any other implementation methods expanded based on the scheme of this application without expending creative work shall fall within the scope of protection of this application.

Claims

1. A method for detecting an inkjet head, characterized in that: include: Acquire a first test image of the inkjet head to be tested, the first test image being used to represent a test print model ejected by the inkjet head to be tested according to a standard nozzle orifice test pattern; wherein the standard nozzle orifice test pattern corresponds to a standard test template, and the standard test template includes: detection frames corresponding one-to-one to multiple nozzles of the inkjet head to be tested, and identification information of the detection frames; 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; Determining 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 represent the detection print model; When the number of target pixels is less than a preset pixel number threshold, determining that an abnormality exists in the nozzle corresponding to the detection frame corresponding to the target pixel number, and outputting identification information of the detection frame corresponding to the target pixel number for use in determining the nozzle with the abnormality; When the number of target pixels is greater than or equal to the preset pixel number threshold, determining a centroid position corresponding to a detection frame in the mapped second detection image, where the centroid position is a position within the detection frame of the centroid of the target pixels 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 center of mass position corresponding to the detection frame and a preset reference center of mass 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 there is an abnormality 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.

2. The method according to claim 1, 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.

3. The method according to claim 2, 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 corresponding to the detection frame in the mapped second detection image, where the angle difference is an angle between a fitted 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.

4. The method according to any one of claims 1 to 3, characterized in that The performing image preprocessing on the first detection image includes: Performing noise reduction processing on the first detection image to obtain a noise-reduced detection image; Performing image enhancement processing on the noise-reduced detection image to obtain an image-enhanced detection image; Extracting a region of interest (ROI) from the enhanced detection image to obtain a region-extracted detection image; Performing geometric correction on the detection image after the region extraction to obtain a corrected detection image.

5. The method according to claim 4, 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.

6. 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.

7. The method according to claim 6, characterized in that The auxiliary correction identifier is: Two parallel straight lines respectively located above and below the standard nozzle test map, or four cross lines respectively located at the four corners of the standard nozzle test map, or four calibration points respectively located at the four corners of the standard nozzle test map.

8. An inkjet head detection system, characterized in that: include: Acquisition module, pre-processing module and detection module; among them, The acquisition module is configured to acquire a first test image of the inkjet head to be tested, the first test image being used to represent a test print model ejected by the inkjet head to be tested according to a standard nozzle orifice test pattern; wherein the standard nozzle orifice test pattern corresponds to a standard test template, and the standard test template includes: detection frames corresponding one-to-one to a plurality of 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 configured to map the standard detection template onto the second detection image to obtain a mapped second detection image, and determine the number of target pixels corresponding to a 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 represent the detection print model; The detection module is further configured to, when the number of target pixels is less than a preset pixel number threshold, determine that an abnormality exists in the nozzle corresponding to the detection frame corresponding to the target number of pixels, and output identification information of the detection frame corresponding to the target number of pixels, so as to determine the nozzle with the abnormality; The detection module is further configured to determine, when the number of target pixels is greater than or equal to the preset pixel number threshold, a centroid position corresponding to a detection frame in the mapped second detection image, where the centroid position is a position within the detection frame of the centroid of the target pixels 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 center of mass position corresponding to the detection frame and a preset reference center of mass 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 there is an abnormality 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.

9. 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 to 7.

Images