Real-time online detection method and system for glue hanging of dispensing nozzle

Abstract

The invention relates to the technical field of dispensing, in particular to a real-time online detection method and system for glue hanging of a dispensing nozzle, and the method comprises the steps: moving the nozzle to a glue hanging detection platform for image collection before dispensing to obtain a first image, and processing the first image to obtain a first circle center coordinate and four detection areas; starting a flow based on preset dispensing times, and moving the dispensed nozzle to a glue hanging detection platform for image acquisition to obtain a second image; processing the second image to obtain a target area of the dispensing nozzle, and detecting whether the state of the current nozzle is normal or not based on the target area; if the first circle center coordinate is normal, four detection areas are mapped on the target area through affine transformation based on the first circle center coordinate, area segmentation is carried out to obtain four target detection areas, and if the first circle center coordinate is abnormal, an alarm is given; and respectively extracting glue in the four target detection areas to obtain corresponding glue areas, adding the areas of all the glue areas, comparing the added areas with a preset value, and carrying out glue hanging detection on the dispensing nozzle according to a comparison result.

Description

Technical Field

[0001] The invention relates to the technical field of glue dispensing, and in particular to a real-time online detection method for glue hanging on a glue dispensing nozzle and a detection system thereof. Background Art

[0002] In the glue dispensing industry, glue hanging on the nozzle is a relatively common problem. When the viscosity of the glue is high and the fluidity is poor, it is easy for the glue to remain at the nozzle and gradually accumulate to form glue hanging; the inner diameter of the nozzle is too small, the outlet shape is irregular or the inner wall is not smooth, which will increase the probability of glue hanging on the wall; excessive glue dispensing pressure or too fast speed will cause the glue to form a large impact force in the nozzle, causing the glue to splash and hang on the nozzle. On the contrary, if the pressure is too low or the speed is too slow, the glue will not flow out smoothly and it is easy to accumulate at the nozzle. Continuous and long-term glue dispensing operations will cause the nozzle to contact with the glue for a long time, increasing the possibility of glue hanging; and if the glue dispensing frequency is too high, the nozzle will not have enough time to empty the residual glue, which will also cause glue hanging.

[0003] In order to solve the above problems, the existing technology can monitor the glue hanging on the nozzle through high-resolution cameras and advanced image processing algorithms, achieve high-precision detection, and accurately identify the tiny glue hanging on the nozzle. In addition, laser detection technology is used to scan the nozzle surface through a laser beam, and the presence of glue hanging is judged according to the change of reflected light, which has the characteristics of non-contact and high precision. These solutions usually require stopping the needle for glue hanging detection, and are not combined with the dispensing operation process, which affects the working efficiency and yield rate of the dispensing machine; for the glue hanging detection of nozzle glue, the color contrast between the glue and the nozzle or the surrounding environment is extremely low, and it is difficult for the human eye or ordinary visual detection system to clearly distinguish the boundary between the glue and the background, making it difficult to accurately identify the glue hanging. In addition, the glue has a strong ability to absorb light, and there may be uneven reflection. This will cause the brightness of the glue hanging area to be not significantly different from the surrounding area during image acquisition, which increases the difficulty of image processing and analysis, and is prone to misjudgment or omission. Summary of the invention

[0004] The present invention aims to solve at least one of the technical problems existing in the prior art.

[0005] To this end, the present invention provides a real-time online detection method for glue coating on a glue dispensing nozzle, which has high detection accuracy, high efficiency and high yield rate of glue dispensing products.

[0006] According to the real-time online detection method for glue coating on a dispensing nozzle according to an embodiment of the present invention, the method comprises the following steps: S1, before dispensing glue, move the nozzle to the glue detection platform, collect an image of the nozzle to obtain a first image, process the first image, and obtain the first center coordinates (x1, y1) of the nozzle before dispensing glue and four detection areas; S2, starting the glue coating detection process based on the preset glue dispensing times, moving the nozzle after glue dispensing to the glue coating detection platform for image acquisition, and obtaining a second image; S3, processing the second image based on the Blob analysis method to obtain a target area of ​​the nozzle after dispensing, and detecting whether the current state of the nozzle is normal based on the target area; If the current state of the nozzle is normal, then based on the first circle center coordinate (x1, y1), the four detection areas are mapped on the target area through affine transformation, and the area is segmented to obtain the four target detection areas of the nozzle after dispensing, and then proceed to the next step. If the current state of the nozzle is abnormal, an alarm is issued to remind that manual processing is required; S4, extracting the glue in the four target detection areas to obtain corresponding glue areas, adding up the areas of all glue areas and comparing them with a preset value, and implementing glue hanging detection on the glue dispensing nozzle according to the comparison result.

[0007] The beneficial effect of the present invention is that the real-time online detection method for glue sticking on the glue dispensing nozzle of the present invention first obtains the center coordinates and detection area of ​​the nozzle before glue dispensing, then obtains the nozzle image after glue dispensing, processes the nozzle image after glue dispensing, and combines the affine transformation technology to obtain the target detection area, performs glue extraction on each target detection area, obtains the glue area of ​​different target detection areas, and then calculates the area of ​​all glue areas. The glue sticking detection of the glue dispensing nozzle is performed based on the area of ​​all glue areas. The accuracy of the nozzle glue sticking detection is high, and while ensuring the detection accuracy, the glue of the four target detection areas can be extracted together, thereby improving the detection efficiency. In addition, since the glue sticking detection process is started based on the preset number of glue dispensing times, the nozzle glue sticking can be discovered in time, the yield rate of the glue dispensing product is improved, and the life cycle of the nozzle can be better maintained and monitored.

[0008] According to one embodiment of the present invention, in step S1, the first image is processed by a Blob analysis method to extract the first circle center coordinates (x1, y1); The first image is displayed through a human-computer interaction interface, and area division is performed to obtain four detection areas, which are respectively a nozzle port area, a nozzle side wall area, a nozzle plane area, and a nozzle out-of-plane area.

[0009] According to an embodiment of the present invention, in step S3, mapping the four detection areas on the target area through affine transformation based on the center coordinates of the nozzle specifically includes: The second image is processed by Blob analysis method to extract the center coordinates (xi, yi) of the nozzle after dispensing; Positioning the second image based on the first circle center coordinates (x1, y1) and the circle center coordinates (xi, yi) of the nozzle after dispensing; The first circle center coordinate (x1, y1) is mapped to the second image to obtain the affine transformation matrix for glue detection and positioning. The calculation formula is expressed as:

[0010] Among them, the rotation matrix R and the translation vector T; The four detection areas are mapped on the target area through the glue detection positioning affine transformation matrix, and the area is segmented to obtain four target detection areas of the nozzle after dispensing. The four target detection areas correspond one by one to the four detection areas, namely: nozzle port target detection area, nozzle side wall target detection area, nozzle plane target detection area and nozzle out of plane target detection area.

[0011] According to one embodiment of the present invention, the glue extraction of the four target detection areas in step S4 includes: glue extraction of the nozzle port target detection area, glue extraction of the nozzle side wall target detection area, glue extraction of the nozzle plane target detection area, and glue extraction of the nozzle beyond the plane target detection area.

[0012] According to one embodiment of the present invention, extracting glue from the target detection area of ​​the nozzle port includes: Extracting the bright ring of the nozzle port through grayscale threshold segmentation according to the reflection characteristics of the glue, judging whether the target detection area of ​​the nozzle port is glued based on the roundness of the bright ring, and if glue is attached, extracting the glue in the target detection area of ​​the nozzle port through the grayscale value of the glue outside the bright ring to obtain a first glue area; The number of pixels in the first glue area is calculated to obtain the area of ​​the first glue area.

[0013] According to one embodiment of the present invention, extracting glue from the target detection area on the side wall of the nozzle includes: Extracting the dark area of ​​the nozzle side wall target detection area by dynamic threshold segmentation, and processing the dark area by morphological operation, wherein the processed dark area is the second glue area; or Extracting the glue-free distribution area of ​​the nozzle side wall target detection area by dynamic threshold segmentation, connecting all the glue-free areas by combining global threshold segmentation and morphological operation, and then subtracting all the glue-free areas from the nozzle side wall to obtain the second glue area; The number of pixels in the second glue area is calculated to obtain the area of ​​the second glue area.

[0014] According to one embodiment of the present invention, the glue extraction of the plane target detection area of ​​the nozzle and the glue extraction of the nozzle beyond the plane target detection area include: The nozzle plane target detection area and the bright area where the nozzle exceeds the plane target detection area are respectively extracted by global threshold segmentation to obtain the third glue area and the fourth glue area; The number of pixels in the third glue region and the fourth glue region are calculated respectively to obtain the area of ​​the third glue region and the area of ​​the fourth glue region.

[0015] According to one embodiment of the present invention, if the total area of ​​all glue areas is greater than a preset value, it is determined that the current nozzle is glued, an alarm is issued, and a manual eraser is prompted to erase the glue or a glue eraser unit is controlled to erase the glue.

[0016] According to an embodiment of the present invention, processing the first image by using a Blob analysis method to extract the first circle center coordinates (x1, y1) specifically includes: Performing sharpening processing on the first image, and filtering the sharpened image by using a low-pass filter; Performing enhancement processing on the filtered image to obtain an enhanced image; The enhanced image is processed by binarization to obtain a region with the largest area; The largest area is processed through morphological operations and regional morphological operations to obtain the target area; The maximum inscribed circle of the target area is calculated, and the first center coordinate (x1, y1) is obtained through the area_center operator.

[0017] According to an embodiment of the present invention, a real-time online detection system for glue coating on a dispensing nozzle includes: A glue detection platform is configured for image acquisition; A host computer, the host computer is connected to the glue coating detection platform, and the host computer is configured to execute the above-mentioned real-time online detection method for glue coating of the glue dispensing nozzle; The glue detection platform includes: an industrial camera, an industrial lens, a corner prism and a ring-shaped shadowless light source; The industrial camera, the industrial lens and the corner prism are coaxially arranged in sequence; The corner prism and the annular shadowless light source are arranged opposite to each other; When the glue coating of the glue dispensing nozzle is detected online in real time, the glue dispensing nozzle is moved to the annular shadowless light source so that the axis of the glue dispensing nozzle and the axis of the annular shadowless light source are in the same straight line.

[0018] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description, claims and drawings.

[0019] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The present invention is further described below in conjunction with the accompanying drawings and embodiments.

[0021] Figure 1 It is a schematic diagram of the method flow of embodiment 1 of the present invention.

[0022] Figure 2 It is a schematic diagram of the detection area division according to the first embodiment of the present invention.

[0023] Figure 3 It is a second image schematic diagram of the first embodiment of the present invention.

[0024] Figure 4 Schematic diagram of the target detection area image of the nozzle port of the first embodiment of the present invention.

[0025] Figure 5 Schematic diagram of the bright ring of the nozzle port in the first embodiment of the present invention.

[0026] Figure 6 It is a structural schematic diagram of a glue coating detection platform according to the second embodiment of the present invention.

[0027] Figure 7 It is a schematic diagram of a computer device according to Embodiment 3 of the present invention.

[0028] In the figure: 11, industrial camera; 12, industrial lens; 13, corner prism; 14, annular shadowless light source; 10, computer equipment; 1002, processor; 1004 memory; 1006, transmission device. DETAILED DESCRIPTION

[0029] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, which only illustrate the basic structure of the present invention in a schematic manner, and therefore only show the components related to the present invention.

[0030] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In addition, features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, "multiple" means two or more.

[0031] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" 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 it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0032] Example 1 The present application embodiment provides a real-time online detection method for glue coating on a glue dispensing nozzle, such as Figure 1 As shown, the method comprises the following steps: S1, before dispensing, move the nozzle to the glue detection platform, collect images of the nozzle, obtain the first image, process the first image, obtain the first center coordinates (x1, y1) of the nozzle before dispensing and four detection areas; further, process the first image by Blob analysis method, extract the first center coordinates (x1, y1); display the first image through the human-computer interaction interface, and divide the area to obtain four detection areas, such as Figure 2 As shown, the four detection areas are the nozzle port area, the nozzle side wall area, the nozzle plane area and the nozzle out-of-plane area.

[0033] S2, based on the preset number of dispensing times, starts the glue-hanging detection process, moves the nozzle after dispensing glue to the glue-hanging detection platform for image acquisition, and obtains the second image, see Figure 3 As shown; if the preset number of dispensing times is 3 times, when the nozzle is detected to have dispensed glue 3 times, the glue hanging detection is started, so that real-time online detection is realized and the manual start process is avoided, and the detection efficiency is fast.

[0034] S3, based on the Blob analysis method, the second image is processed to obtain the target area of ​​the nozzle after dispensing, and based on the target area, whether the current state of the nozzle is normal is detected; if the current state of the nozzle is normal, based on the first circle center coordinates (x1, y1), four detection areas are mapped on the target area through affine transformation, and the area is segmented to obtain four target detection areas of the nozzle after dispensing, and then proceed to the next step. If the current state of the nozzle is abnormal, an alarm is issued to remind that manual processing is required.

[0035] S4, extracting glue from four target detection areas to obtain corresponding glue areas, adding up the areas of all glue areas and comparing them with a preset value, and implementing glue detection on the glue dispensing nozzle according to the comparison result.

[0036] In this embodiment, the nozzle in step S3 may not appear in the second image due to motion control or mechanical errors. The state of the current nozzle is detected based on the target area to determine whether it is normal, that is, whether the current nozzle is in the second image. The target area of ​​the nozzle is extracted through threshold segmentation, and the area of ​​the target area is determined to determine whether it is in a reasonable position.

[0037] Furthermore, mapping the detection area on the target area through affine transformation based on the center coordinates of the nozzle specifically includes: The second image is processed by Blob analysis method to extract the center coordinates (xi, yi) of the nozzle after dispensing.

[0038] The second image is positioned based on the first circle center coordinates (x1, y1) and the circle center coordinates (xi, yi) of the nozzle after dispensing.

[0039] Map the coordinates of the first circle center (x1, y1) to the second image to obtain the affine transformation matrix for glue detection and positioning. The affine transformation matrix for glue detection and positioning is a rigid affine transformation calculated based on the point correspondence and two corresponding angles, that is, a transformation composed of a rotation matrix R and a translation vector T, and returns it as a homogeneous transformation matrix HomMat2D. The calculation formula for the affine transformation matrix for glue detection and positioning is expressed as:

[0040] Among them, the rotation matrix R and the translation vector T.

[0041] Through the glue hanging detection and positioning affine transformation matrix, four detection areas are mapped on the target area, and the area is segmented to obtain four target detection areas of the nozzle after dispensing. The four target detection areas correspond to the four detection areas one by one, namely: nozzle port target detection area, nozzle side wall target detection area, nozzle plane target detection area and nozzle out of plane target detection area.

[0042] In this embodiment, the glue extraction of the four target detection areas in step S4 includes: glue extraction of the nozzle port target detection area, glue extraction of the nozzle side wall target detection area, glue extraction of the nozzle plane target detection area, and glue extraction of the nozzle beyond the plane target detection area. When extracting glue, the four target detection areas can be processed synchronously to increase the extraction speed of the glue area, thereby improving the detection efficiency.

[0043] Specifically, Figure 4 The nozzle port target detection area is shown, and the glue extraction of the nozzle port target detection area includes: According to the reflection characteristics of the glue, the bright ring of the nozzle port is extracted by grayscale threshold segmentation, such as Figure 5 As shown, whether the nozzle port target detection area is glued is determined based on the roundness of the bright ring. If glue is attached, the glue in the nozzle port target detection area is extracted through the grayscale value of the glue outside the bright ring to obtain the first glue area.

[0044] The number of pixels in the first glue area is calculated to obtain the area of ​​the first glue area.

[0045] It should be noted that the bright ring of normal glue in the nozzle is close to a standard circle, while the bright ring is elliptical when glue is applied to the nozzle port. The roundness of the bright ring is obtained by the ratio of the area of ​​the bright ring and the approximate minimum circumscribed circle area of ​​the bright ring obtained by the smallest_circle operator. If the roundness value of the bright ring is closer to 1, the shape of the area is closer to a circle, and the target detection area of ​​the nozzle port is not glued; otherwise, the target detection area of ​​the nozzle port is glued.

[0046] Glue extraction from the target inspection area on the nozzle side wall includes: When there is less glue on the nozzle side wall, the dark area of ​​the nozzle side wall target detection zone is extracted by dynamic threshold segmentation, and the dark area is processed by morphological operation. The processed dark area is the second glue area; or when there is more glue on the nozzle side wall, the area without glue distribution in the nozzle side wall target detection area is extracted by dynamic threshold segmentation, and all glue-free areas are connected by combining global threshold segmentation and morphological operation, and then all glue-free areas are subtracted from the nozzle side wall area to obtain the second glue area.

[0047] The number of pixels in the second glue region is calculated to obtain the area of ​​the second glue region.

[0048] Through morphological operations, the interference of impurities and residual glue marks on the side wall itself can be eliminated, thereby improving the detection accuracy.

[0049] Glue extraction from the nozzle plane target detection area and glue extraction from the nozzle beyond the plane target detection area include: The nozzle plane target detection area and the bright area where the nozzle exceeds the plane target detection area are extracted respectively through global threshold segmentation to obtain the third glue area and the fourth glue area.

[0050] The number of pixels in the third glue region and the fourth glue region are calculated respectively to obtain the area of ​​the third glue region and the area of ​​the fourth glue region.

[0051] Add the area of ​​the first glue area, the area of ​​the second glue area, the area of ​​the third glue area and the area of ​​the fourth glue area to get the total area of ​​the glue area. If the total area of ​​the glue area is greater than the preset value, the current nozzle is glued and an alarm is issued to prompt manual glue erasing or control the glue erasing unit to erase the glue.

[0052] In this embodiment, the first image is processed by the Blob analysis method to extract the first circle center coordinates (x1, y1) including the following steps: The first image is sharpened, and the sharpened image is filtered using a low-pass filter.

[0053] The filtered image is enhanced to obtain an enhanced image.

[0054] The image is enhanced by binarization to obtain the largest area.

[0055] The region with the largest area is processed through morphological operations and regional morphological operations to obtain the target region.

[0056] Calculate the maximum inscribed circle of the target area, and obtain the first center coordinates (x1, y1) through the area_center operator. Further, calculate the maximum inscribed circle of the target area through the halcon operator.

[0057] It should be noted that the steps for obtaining the center coordinates (xi, yi) of the nozzle after dispensing are the same as the steps for obtaining the first center coordinates (x1, y1), which will not be repeated here for the sake of brevity.

[0058] This embodiment is suitable for the detection of glue hanging on glue nozzles of other colors except transparent glue nozzles, such as black, white, etc. It only needs to adapt the corresponding light source on the glue hanging detection platform so that the glue can be imaged quickly and the glue can be highlighted in the collected image, which can improve the detection accuracy and efficiency.

[0059] The real-time online detection method for glue sticking on the glue dispensing nozzle of this embodiment first obtains the center coordinates and detection area of ​​the nozzle before glue dispensing, then obtains the nozzle image after glue dispensing, processes the nozzle image after glue dispensing, and combines the affine transformation technology to obtain the target detection area, performs glue extraction on each target detection area, obtains the glue area of ​​different target detection areas, and then calculates the area of ​​all glue areas. The glue sticking detection of the glue dispensing nozzle is performed based on the area of ​​all glue areas. The accuracy of the nozzle glue sticking detection is high, and while ensuring the detection accuracy, the glue of the four target detection areas can be extracted together, thereby improving the detection efficiency. In addition, since the glue sticking detection process is started based on the preset number of glue dispensing times, the nozzle glue sticking can be detected in time, the yield rate of the glue dispensing product is improved, and the life cycle of the nozzle can be better maintained and monitored.

[0060] Example 2 The present application embodiment provides a real-time online detection system for glue coating on a dispensing nozzle, the system comprising: The glue detection platform is configured for image acquisition.

[0061] The host computer is connected to the glue hanging detection platform, and the host computer is configured to execute the above-mentioned real-time online detection method for glue hanging on the dispensing nozzle.

[0062] Further, such as Figure 6 As shown, the glue detection platform includes: an industrial camera 11, an industrial lens 12, a corner prism 13 and an annular shadowless light source 14.

[0063] The industrial camera 11, the industrial lens 12 and the corner prism 13 are coaxially arranged in sequence.

[0064] The corner prism 13 and the annular shadowless light source 14 are arranged opposite to each other.

[0065] When the glue coating of the glue dispensing nozzle is detected online in real time, the glue dispensing nozzle is moved to the annular shadowless light source 14 so that the axis of the glue dispensing nozzle and the axis of the annular shadowless light source 14 are in the same straight line.

[0066] For example, if the glue to be detected is black glue, the color adapted by the annular shadowless light source 14 is red, so that the black glue can be quickly imaged, the glue can be highlighted in the collected image, and the color contrast between the black glue and the nozzle or the surrounding environment is improved.

[0067] The foregoing Figure 1The various variations and specific examples of the real-time online detection method for glue sticking on a dispensing nozzle in Example 1 are also applicable to a real-time online detection system for glue sticking on a dispensing nozzle in this embodiment. Through the above detailed description of the real-time online detection method for glue sticking on a dispensing nozzle, those skilled in the art can clearly know the implementation method of the real-time online detection system for glue sticking on a dispensing nozzle in this embodiment. Therefore, for the sake of brevity of the specification, it will not be described in detail here.

[0068] Example 3 An embodiment of the present application provides a computer device, which includes a processor and a memory, in which at least one instruction or at least one program is stored. The at least one instruction or the at least one program is loaded and executed by the processor to implement a real-time online detection method for glue coating on a dispensing nozzle as provided in the above method embodiment.

[0069] Figure 7 The hardware structure diagram of a device for implementing a real-time online detection method for glue coating on a glue dispensing nozzle provided in an embodiment of the present application is shown. The device may participate in or include the device or system provided in an embodiment of the present application. Figure 7 As shown, the computer device 10 may include one or more processors 1002 (the processor may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 1004 for storing data, and a transmission device 1006 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 7 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 7 More or fewer components as shown, or with Figure 7 Different configurations are shown.

[0070] It should be noted that the one or more processors and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer device 10 (or mobile device). As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0071] The memory 1004 can be used to store software programs and modules of application software, such as a program instruction / data storage device corresponding to a real-time online detection method for glue coating of a dispensing nozzle in an embodiment of the present application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory 1004, that is, realizing the above-mentioned method. The memory 1004 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 1004 may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the computer device 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0072] The transmission device 1006 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer device 10. In one example, the transmission device 1006 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 1006 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0073] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer device 10 (or mobile device).

[0074] Example 4 An embodiment of the present application also provides a computer-readable storage medium, which can be set in a server to store at least one instruction or at least one program related to a real-time online detection method for glue coating on a dispensing nozzle in a method embodiment. The at least one instruction or the at least one program is loaded and executed by the processor to implement a real-time online detection method for glue coating on a dispensing nozzle provided in the above method embodiment.

[0075] Optionally, in this embodiment, the storage medium may be located in at least one of the multiple network servers of the computer network. Optionally, in this embodiment, the storage medium may include, but is not limited to, various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk, or an optical disk.

[0076] Example 5 The embodiment of the present invention further provides a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes a real-time online detection method for glue coating on a dispensing nozzle provided in the above various optional embodiments.

[0077] It should be noted that the above-mentioned sequence of the embodiments of the present application is for description only and does not represent the advantages and disadvantages of the embodiments. The above-mentioned specific embodiments of the present application are described. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0078] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment and storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0079] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware or by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0080] Based on the above ideal embodiments of the present invention, the relevant staff can make various changes and modifications without departing from the technical concept of the present invention through the above description. The technical scope of the present invention is not limited to the contents of the specification, but must be determined according to the scope of the claims.

Claims

1. A real-time online detection method for glue coating on a dispensing nozzle, characterized in that: The method comprises the following steps: S1, before dispensing glue, move the nozzle to the glue detection platform, collect an image of the nozzle to obtain a first image, process the first image, and obtain the first center coordinates (x1, y1) of the nozzle before dispensing glue and four detection areas; S2, starting the glue coating detection process based on the preset glue dispensing times, moving the nozzle after glue dispensing to the glue coating detection platform for image acquisition, and obtaining a second image; S3, processing the second image based on the Blob analysis method to obtain a target area of ​​the nozzle after dispensing, and detecting whether the current state of the nozzle is normal based on the target area; If the current state of the nozzle is normal, based on the first circle center coordinate (x1, y1), the four detection areas are mapped on the target area through affine transformation, and the area is segmented to obtain the four target detection areas of the nozzle after dispensing, and then proceed to the next step. If the current state of the nozzle is abnormal, an alarm is issued to remind that manual processing is required; S4, extracting the glue in the four target detection areas to obtain corresponding glue areas, adding up the areas of all glue areas and comparing them with a preset value, and implementing glue hanging detection on the glue dispensing nozzle according to the comparison result.

2. The real-time online detection method for glue coating on a dispensing nozzle according to claim 1, characterized in that: In step S1, the first image is processed by Blob analysis method to extract the first circle center coordinates (x1, y1); The first image is displayed through a human-computer interaction interface, and area division is performed to obtain four detection areas, which are respectively a nozzle port area, a nozzle side wall area, a nozzle plane area, and a nozzle out-of-plane area.

3. The real-time online detection method for glue coating on a dispensing nozzle according to claim 1, characterized in that: In the step S3, mapping the four detection areas on the target area through affine transformation based on the center coordinates of the nozzle specifically includes: The second image is processed by Blob analysis method to extract the center coordinates (xi, yi) of the nozzle after dispensing; Positioning the second image based on the first circle center coordinates (x1, y1) and the circle center coordinates (xi, yi) of the nozzle after dispensing; The first circle center coordinate (x1, y1) is mapped to the second image to obtain the affine transformation matrix for glue detection and positioning. The calculation formula is expressed as: Among them, the rotation matrix R and the translation vector T; The four detection areas are mapped on the target area through the glue detection positioning affine transformation matrix, and the area is segmented to obtain four target detection areas of the nozzle after dispensing. The four target detection areas correspond one by one to the four detection areas, namely: nozzle port target detection area, nozzle side wall target detection area, nozzle plane target detection area and nozzle out of plane target detection area.

4. The real-time online detection method for glue coating on a glue dispensing nozzle according to claim 1, characterized in that: Extracting glue from the four target detection areas in step S4 includes: extracting glue from the nozzle port target detection area, extracting glue from the nozzle side wall target detection area, extracting glue from the nozzle plane target detection area, and extracting glue from the nozzle beyond the plane target detection area.

5. The real-time online detection method for glue coating on a glue dispensing nozzle according to claim 4, characterized in that: Extracting glue from the nozzle port target detection area includes: Extracting the bright ring of the nozzle port through grayscale threshold segmentation according to the reflection characteristics of the glue, judging whether the target detection area of ​​the nozzle port is glued based on the roundness of the bright ring, and if glue is attached, extracting the glue in the target detection area of ​​the nozzle port through the grayscale value of the glue outside the bright ring to obtain a first glue area; The number of pixels in the first glue area is calculated to obtain the area of ​​the first glue area.

6. The real-time online detection method for glue coating on a glue dispensing nozzle according to claim 4, characterized in that: Extracting glue from the target detection area on the side wall of the nozzle includes: Extracting the dark area of ​​the nozzle side wall target detection area by dynamic threshold segmentation, and processing the dark area by morphological operation, wherein the processed dark area is the second glue area; or Extracting the glue-free distribution area of ​​the nozzle side wall target detection area by dynamic threshold segmentation, connecting all the glue-free areas by combining global threshold segmentation and morphological operation, and then subtracting all the glue-free areas from the nozzle side wall to obtain the second glue area; The number of pixels in the second glue area is calculated to obtain the area of ​​the second glue area.

7. The real-time online detection method for glue coating on a glue dispensing nozzle according to claim 4, characterized in that: Extracting glue from the plane target detection area of ​​the nozzle and extracting glue from the nozzle beyond the plane target detection area include: The nozzle plane target detection area and the bright area where the nozzle exceeds the plane target detection area are respectively extracted by global threshold segmentation to obtain the third glue area and the fourth glue area; The number of pixels in the third glue region and the fourth glue region are calculated respectively to obtain the area of ​​the third glue region and the area of ​​the fourth glue region.

8. The real-time online detection method for glue coating on a glue dispensing nozzle according to claim 1, characterized in that: If the total area of ​​all glue areas is larger than the preset value, it is determined that the current nozzle is glued, an alarm is issued, and a manual operation is prompted to erase the glue or the glue erasing unit is controlled to erase the glue.

9. The real-time online detection method for glue coating on a glue dispensing nozzle according to claim 1, characterized in that: Processing the first image by using the Blob analysis method to extract the first circle center coordinates (x1, y1) specifically includes: Performing sharpening processing on the first image, and filtering the sharpened image by using a low-pass filter; Performing enhancement processing on the filtered image to obtain an enhanced image; The enhanced image is processed by binarization to obtain a region with the largest area; The largest area is processed through morphological operations and regional morphological operations to obtain the target area; The maximum inscribed circle of the target area is calculated, and the first center coordinate (x1, y1) is obtained through the area_center operator.

10. A real-time online detection system for glue coating on a dispensing nozzle, characterized in that: A glue detection platform is configured for image acquisition; A host computer, the host computer is connected to the glue coating detection platform, and the host computer is configured to execute the real-time online detection method for glue coating on a dispensing nozzle according to any one of claims 1 to 9; The glue detection platform comprises: an industrial camera (11), an industrial lens (12), a corner prism (13) and an annular shadowless light source (14); The industrial camera (11), the industrial lens (12), and the corner prism (13) are coaxially arranged in sequence; The corner prism (13) and the annular shadowless light source (14) are arranged relative to each other; When the glue coating of the glue dispensing nozzle is detected online in real time, the glue dispensing nozzle is moved onto the annular shadowless light source (14) so ​​that the axis of the glue dispensing nozzle and the axis of the annular shadowless light source (14) are in the same straight line.

Images