Industrial electrostatic spinning machine spinning test device, method and system and storage medium

Abstract

The invention discloses an industrial electrostatic spinning machine spinning test device, method and system and a storage medium, the device comprises a working module and a detection module, the working module comprises an electrostatic spinning machine and a spinning recovery rod, the electrostatic spinning machine is used for generating electrostatic spinning fibers, and the spinning recovery rod comprises color partitions; the distance between the two spun yarns is greater than a preset value; the detection module comprises an industrial camera, an amplification device, a processing unit, a transmission unit and a calibration unit, the industrial camera is used for shooting the statically determinate spinning fiber to obtain a shot image, the amplification device is used for amplifying the shot image of the industrial camera, and the transmission unit is used for transmitting the shot image to the processing unit; the calibration unit is used for calibrating a difference parameter between a pixel size and an actual size in the shot image, and the processing unit is used for processing the shot image to extract fiber size information. According to the invention, automatic, high-precision and low-cost electrostatic spinning detection is realized, and the problems of low efficiency and high cost of a traditional method are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of image data processing, and more specifically, to a spinning test device, method, system and storage medium for an industrial electrospinning machine. Background Art

[0002] Electrospinning can produce fibers with different diameters and is widely used in fields such as air filtration, biomedicine, composite materials, environmental protection and the textile industry. Nanoscale fibers are used for air filtration and biomedicine, while micron-scale fibers are used for composite materials and environmental protection fields.

[0003] Currently, in traditional measurement methods, electrospinning measurement methods usually use electron microscopes or high-power microscopes, and perform size conversion through a scale and measurement software. This method is inefficient, requires high operating personnel, and has expensive test costs.

[0004] In response to this, patent application CN201910438296.8 proposes a target size measurement method based on deep learning, which collects images through a camera and uses a deep learning algorithm for size measurement; patent application CN202021678095.X proposes an area size measuring instrument based on rotating laser ranging, which quickly establishes an indoor map and generates useful data through point cloud matching; among them, although the disclosed prior art improves the measurement efficiency, it is still affected by camera focal length, angle and environmental lighting conditions, cannot perform measurements in complex environments, and depends on the external environment. Summary of the Invention

[0005] The purpose of the present invention is to provide a spinning test device, method, system and storage medium for an industrial electrospinning machine, which is used to solve the technical problem of how to perform automated measurement of electrospinning in the prior art.

[0006] The first aspect of the present invention provides a spinning test device for an industrial electrospinning machine, including:

[0007] A working module and a detection module, wherein,

[0008] The working module includes an electrospinning machine and a spinning recovery rod. The electrospinning machine is used to generate electrospinning fibers. The spinning recovery rod includes color partitions, and the distance between two spins is greater than a preset value;

[0009] The detection module includes an industrial camera, a magnifying device, a processing unit, a transmission unit, and a calibration unit. Among them, the industrial camera is used to capture an image of the static spinning fiber to obtain a captured image, the magnifying device is used to magnify the captured image of the industrial camera, the transmission unit is used to transmit the captured image to the processing unit, the calibration unit is used to calibrate the difference parameter between the pixel size and the actual size in the captured image, and the processing unit is used to process the captured image to extract fiber size information.

[0010] In this solution, the working module further includes a high-voltage power supply, a lighting device, and a movement control device. Among them, the high-voltage power supply is used to supply power to the electrospinning machine, the lighting device is used to provide lighting conditions, and the movement control device is used to move the spinning recovery rod.

[0011] The second aspect of the present invention further provides a spinning test method for an industrial electrospinning machine, which is applied to the spinning test device of an industrial electrospinning machine described in any one of the above. Among them, the method includes the following steps:

[0012] Obtain a pixel scale to initialize calibration parameters;

[0013] Obtain a captured image for image processing to obtain a target image;

[0014] Calculate the fiber pixel size based on the target image to obtain a measurement result;

[0015] Perform visual display and storage based on the measurement result, and synchronously generate a measurement report.

[0016] In this solution, the obtaining of the pixel scale to initialize the calibration parameters specifically includes:

[0017] Obtain several test images to calculate the pixel scale;

[0018] Set the focal length, magnification, and shooting angle during image shooting based on the pixel scale to complete the initialization of the calibration parameters.

[0019] In this solution, the obtaining of the captured image for image processing to obtain a target image specifically includes:

[0020] Perform preprocessing on the captured image. The preprocessing methods include grayscale conversion, histogram equalization, and Gaussian filtering;

[0021] Perform edge detection and enhancement on the preprocessed captured image. Among them, use wavelet modulus maxima edge detection operator for edge detection, and adopt adaptive threshold method to remove edge noise to complete the edge enhancement operation.

[0022] In this solution, calculating the fiber pixel size based on the target image to obtain the measurement result specifically includes:

[0023] Calculating the fiber pixel size in the target image through the Hough transform and the least squares method;

[0024] Converting the pixel size into the actual physical size based on the pixel scale to obtain the measurement result.

[0025] The third aspect of the present invention further provides a spinning test system for an industrial electrospinning machine, including a memory and a processor. The memory includes a program for the spinning test method of the industrial electrospinning machine. When the program for the spinning test method of the industrial electrospinning machine is executed by the processor, the following steps are implemented:

[0026] Obtaining the pixel scale to initialize the calibration parameters;

[0027] Obtaining the captured image for image processing to obtain the target image;

[0028] Calculating the fiber pixel size based on the target image to obtain the measurement result;

[0029] Performing visual display and storage based on the measurement result, and synchronously generating a measurement report.

[0030] In this solution, the obtaining the pixel scale to initialize the calibration parameters specifically includes:

[0031] Obtaining several test images to calculate the pixel scale;

[0032] Setting the focal length, magnification, and shooting angle during image shooting based on the pixel scale to complete the initialization of the calibration parameters.

[0033] In this solution, the obtaining the captured image for image processing to obtain the target image specifically includes:

[0034] Performing preprocessing on the captured image, and the preprocessing methods include grayscale conversion, histogram equalization, and Gaussian filtering;

[0035] Performing edge detection and enhancement on the preprocessed captured image. Among them, the wavelet modulus maximum edge detection operator is used for edge detection, and the adaptive threshold method is adopted to remove edge noise to complete the edge enhancement operation.

[0036] In this solution, the calculating the fiber pixel size based on the target image to obtain the measurement result specifically includes:

[0037] Calculating the fiber pixel size in the target image through the Hough transform and the least squares method;

[0038] Convert the pixel size to the actual physical size based on the pixel scale to obtain the measurement result.

[0039] A fourth aspect of the present invention provides a computer-readable storage medium, which includes a program for a spinning test method of an industrial electrospinning machine of a machine. When the program for the spinning test method of the industrial electrospinning machine is executed by a processor, the steps of a spinning test method of an industrial electrospinning machine as described in any one of the above are implemented.

[0040] An industrial electrospinning machine spinning test device, method, system and storage medium disclosed by the present invention realize automated, high-precision and low-cost electrospinning detection, solve the problems of low efficiency and high cost of traditional methods, and are applicable to various application scenarios. The specific beneficial effects are as follows:

[0041] 1. Automated detection is realized. After training and calibration, it can be directly used for the detection of electrospinning, especially the detection of size.

[0042] 2. The detection accuracy is improved. After training, the detection accuracy is improved, making the detection result more reliable.

[0043] 3. The structure is simple and the operation is simplified. In actual application, if a network signal is used, the result can be sent in real time.

[0044] 4. The detection cost is low, and convenient, fast and efficient detection can be realized. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 Shows the structural diagram of an industrial electrospinning machine spinning test device of the present invention;

[0046] Figure 2 Shows the structural diagram of an industrial electrospinning machine spinning test device of the present invention;

[0047] Figure 3 Shows the flowchart of an industrial electrospinning machine spinning test method of the present invention;

[0048] Figure 4 Shows the block diagram of an industrial electrospinning machine spinning test system of the present invention.

[0049] Description of Component Labels

[0050] 1 Electrospinning machine

[0051] 2 Spinning recovery rod

[0052] 3 Industrial camera

[0053] 4 Magnifying device

[0054] 5 Control device

[0055] 6 High-voltage power supply

[0056] 7 Lighting device

[0057] 8 Mobile control device Detailed implementation manners

[0058] In order to more clearly understand the above objects, features and advantages of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific implementation manners. It should be noted that, without conflict, the embodiments of the present application and the features in the embodiments can be combined with each other.

[0059] In the following description, many specific details are set forth in order to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited by the specific embodiments disclosed below.

[0060] Electrospinning can produce fibers with different diameters and has a wide range of uses. The diameter of nano-scale fibers ranges from dozens of nanometers to hundreds of nanometers. When used for air filtration, it can efficiently intercept tiny particles with a high specific surface area to ensure air quality; in the biomedical field, it can be used as a tissue engineering scaffold to guide cell growth. For example, nerve cells can smoothly extend axons on a PLGA nanofiber scaffold, and it can also be used as a drug sustained-release carrier. The diameter of micro-scale fibers is about "1-10" microns, which shines in many fields. In composite materials, glass microfibers strengthen the performance of epoxy resin, contributing to industries such as aerospace; in environmental protection, PAN microfibers can be modified to adsorb heavy metal ions to purify sewage; in the textile industry, it can be blended with conventional fibers to upgrade the functions of fabrics. Traditional electrospinning measurement often uses an electron microscope or a microscope with a magnification of more than "1000". According to the scale of the toroidal surface and then through measurement software to convert to the actual ratio. This method has low efficiency and high requirements for operators, who need to understand the software measurement principle and the use of the electron microscope, and the cost of each test is also relatively high.

[0061] To solve the above problems, patent application CN201910438296.8 discloses a method and system for measuring object size based on deep learning. The microcontroller of the front-end processing device controls a camera to collect images of the object to be measured and transmits the images to the back-end server through a network. In the back-end server, by introducing deep learning methods, the object is detected from the images, digital image processing methods are used to extract the contour features of the object, the minimum bounding rectangle of the object contour is calculated, and the two-dimensional pixel size of the object is calculated. According to the camera imaging principle, the actual two-dimensional size of the object is calculated. The back-end server transmits the size measurement results to the front-end processing device through a network, and the microcontroller of the front-end processing device controls the display to display the object size measurement results. In addition, patent application CN202021678095.X discloses an area size measuring instrument based on rotating laser ranging. Through the point cloud matching method of positioning and mapping, it can quickly establish an indoor map and generate practical data such as indoor graphics, area, perimeter, side length, radian, arc length, etc. and establish a data document.

[0062] The accuracy of the above traditional detection methods and devices may be affected by various factors, including camera focal length, angle, and environmental lighting conditions. Moreover, most of them cannot be measured in complex environments and are relatively dependent on the external environment. To solve the above problems, this application proposes an innovative method to automatically identify the area to be measured by constructing the relationship between basic contour segments and features, and quickly and automatically complete high-precision measurement.

[0063] Specifically, Figure 1 Fig. shows the structural diagram of a spinning test device for an industrial electrospinning machine according to this application.

[0064] As Figure 1 shown, this application discloses a spinning test device for an industrial electrospinning machine 1, and the device includes:

[0065] a working module and a detection module, wherein,

[0066] the working module includes an electrospinning machine 1 and a spinning recovery rod 2. The electrospinning machine 1 is used to generate electrospun fibers. The spinning recovery rod 2 includes color partitions, and the distance between two spins is greater than a preset value;

[0067] the detection module includes an industrial camera 3, a magnifying device 4, a processing unit, a transmission unit, and a calibration unit. Among them, the industrial camera 3 is used to take pictures of the static electrospun fibers to obtain a captured image. The magnifying device 4 is used to magnify the captured image of the industrial camera 3. The transmission unit is used to transmit the captured image to the processing unit. The calibration unit is used to calibrate the difference parameter between the pixel size and the actual size in the captured image, and the processing unit is used to process the captured image to extract fiber size information.

[0068] It should be noted that in this embodiment, the working module includes an electrospinning machine 1 and a spinning recovery rod 2. Among them, the electrospinning machine 1 is used to generate electrospinning fibers. Different from general spinning machines, the recovery rod for receiving spinning in the electrospinning machine 1 in this embodiment is specially made. Specifically, the spinning recovery rod 2 includes color partitions, and the feature is that the color differentiation is relatively high. High-brightness colors such as red are used to facilitate subsequent inspection of dimensions, and the distance between two spins is greater than a preset value. Correspondingly, the rotation speed of the spinning recovery rod 2 is adjusted so that the distance between two spins is greater than "3 mm".

[0069] Furthermore, the detection module includes an industrial camera 3, a magnifying device 4, a processing unit, a transmission unit, and a calibration unit. Among them, as Figure 2 shown, it shows another structural diagram of a spinning test device for an industrial electrospinning machine 1. Among them, the industrial camera 3 is used to photograph the static electrospinning fibers to obtain a photographed image, and the magnifying device 4 is used to magnify the photographed image of the industrial camera 3. Furthermore, the processing unit, the transmission unit, and the calibration unit are integrated in Figure 1 the control device 5. Among them, the transmission unit is used to transmit the photographed image to the processing unit, the calibration unit is used to calibrate the difference parameter between the pixel size and the actual size in the photographed image, the processing unit is used to process the photographed image to extract fiber size information, and the working module further includes a high-voltage power supply 6, a lighting device 7, and a movement control device 8. The high-voltage power supply 6 is used to supply power to the electrospinning machine 1, the lighting device 7 is used to provide lighting conditions, and the movement control device 8 is used to move the spinning recovery rod 2.

[0070] Furthermore, Figure 3 shows a flowchart of a spinning test method for an industrial electrospinning machine according to the present application.

[0071] As Figure 3 shown, the present application discloses a spinning test method for an industrial electrospinning machine, including the following steps:

[0072] S302, obtaining a pixel scale to initialize calibration parameters;

[0073] S304, obtaining a photographed image to perform image processing to obtain a target image;

[0074] S306, calculating the fiber pixel size based on the target image to obtain a measurement result;

[0075] S308, performing visual display and storage based on the measurement result, and synchronously generating a measurement report.

[0076] It should be noted that in this embodiment, when testing the spinning of an industrial electrospinning machine, the pixel scale is first confirmed, that is, a suitable magnifying device is selected to take multiple test images, and the ratio of the pixel scale to the actual distance is calculated. Then, an industrial camera is used to take pictures. After electrospinning is completed, the spun fiber together with the recovery rod is placed in the detection area, and the position is adjusted to start detection. Among them, the movement control device moves the position, and the industrial camera takes pictures at multiple positions and uses the transmission unit to transmit the captured images.

[0077] Further, after obtaining the captured images, image processing is performed to obtain the target image. Correspondingly, the image processing includes image grayscale conversion, histogram equalization, Gaussian filtering, and graphic edge enhancement. Then, based on the target image, the fiber pixel size is calculated to obtain the measurement result, that is, the actual physical fiber pixel size of the image is calculated through the conversion of the image pixel coordinates and the physical coordinate system to obtain the measurement result. Finally, based on the measurement result, visual display and storage are performed, and a measurement report is generated synchronously.

[0078] According to the embodiment of the present invention, the obtaining of the pixel scale to initialize the calibration parameters specifically includes:

[0079] Obtaining several test images to calculate the pixel scale;

[0080] Based on the pixel scale, set the focal length, magnification, and shooting angle during image shooting to complete the initialization of the calibration parameters.

[0081] It should be noted that in this embodiment, several test images are obtained to calculate the pixel scale. The formula is as follows: "(unit pixel): (actual distance)". Based on the pixel scale, parameters such as the focal length, magnification, and shooting angle of the industrial camera are set to ensure that the captured images can accurately reflect the physical size of the electrospun fiber.

[0082] Specifically, at the initial stage of the production line, the system needs to be calibrated to ensure accurate subsequent dimension measurement. Before the production line is started, the operator places a standard sample with a known size (such as a fiber with a diameter of "150" nanometers) in the detection area, uses the industrial camera to take multiple images, and obtains the pixel scale by calculating the proportional relationship between the pixels in the image and the actual size. For example, if "1 pixel corresponds to 0.1 nanometers" in the test image, the recorded scale is "1:0.1", thereby setting parameters such as the focal length, magnification, and shooting angle of the industrial camera to ensure that the captured images can accurately reflect the physical size of the fiber.

[0083] According to the embodiment of the present invention, the obtaining of the captured images to perform image processing to obtain the target image specifically includes:

[0084] Preprocess the captured image, and the preprocessing methods include grayscale conversion, histogram equalization, and Gaussian filtering;

[0085] Perform edge detection and enhancement on the preprocessed captured image. Among them, use the wavelet modulus maximum edge detection operator for edge detection, and adopt the adaptive threshold method to remove edge noise to complete the edge enhancement operation.

[0086] It should be noted that in this embodiment, the color image is converted into a grayscale image to reduce the computational complexity. Among them, the grayscale conversion formula is: Y = 0.299R + 0.587G + 0.114B, where Y represents the grayscale value, and R, G, and B represent the components of red, green, and blue respectively.

[0087] Furthermore, perform histogram equalization processing on the grayscale image to increase the dynamic range of the grayscale values between pixels and make the image clearer. The formula is as follows:

[0088]

[0089] where N is the total number of pixels, n j is the number of pixels at the j - th grayscale level, k is the grayscale level, and T(r k ) is the transformation function.

[0090] Furthermore, perform Gaussian filtering on the image to suppress noise and improve the image quality. Then perform edge detection and enhancement on the preprocessed captured image. Among them, use the wavelet modulus maximum edge detection operator for edge detection, and adopt the adaptive threshold method to remove edge noise to complete the edge enhancement operation.

[0091] According to the embodiment of the present invention, calculating the fiber pixel size based on the target image to obtain the measurement result specifically includes:

[0092] Calculate the fiber pixel size in the target image through the Hough transform and the least - squares method;

[0093] Convert the pixel size to the actual physical size based on the pixel scale to obtain the measurement result.

[0094] It should be noted that in this embodiment, the fiber pixel size is calculated through the Hough transform and the least - squares method, and according to the calibrated pixel scale, the pixel size is converted into the actual physical size. Among them, the formula is as follows:

[0095]

[0096] Wherein, (u, v) are the coordinates in the image pixel coordinate system, (x, y) are the coordinates in the image physical coordinate system, dx is the actual physical size corresponding to each pixel in the x direction, dy is the actual physical size corresponding to each pixel in the y direction, and (u0, v0) are the coordinates of the origin of the image pixel coordinate system in the image physical coordinate system.

[0097] Specifically, after edge detection, it is necessary to calculate the actual diameter of the fiber and compare it with the design specifications to ensure that the fiber meets the requirements. Among them, the fiber pixel size in the image is calculated by the Hough transform and the least squares method. For example, after detecting the edge of the fiber, the Hough transform is used to fit the contour of the fiber to calculate the pixel diameter of the fiber. According to the calibrated pixel scale, the pixel size is converted into the actual physical size. For example, if the measured diameter of the fiber in the image is "150" pixels and the scale is "1:0.1", the actual diameter of the fiber is calculated to be "15" nanometers. In actual applications, the calculated fiber diameter is compared with the design specifications (100 - 200 nanometers) to determine whether it meets the requirements.

[0098] Furthermore, after the detection is completed, the measurement results need to be displayed to the operator in real time and a detection report needs to be generated for subsequent analysis and use. Among them, the calculated actual size of the fiber is transmitted to the front-end processing device through the network, and the microcontroller of the front-end processing device controls the display to show the measurement results. For example, the display shows "Fiber diameter: 15 nanometers, meets the design requirements". Furthermore, the measurement results also need to be stored in the database and a detection report needs to be generated. For example, a report containing information such as fiber diameter, detection time, and detection location is generated for the quality management department to conduct subsequent analysis.

[0099] Figure 4 The block diagram of a spinning test system of an industrial electrospinning machine according to the present invention is shown.

[0100] As Figure 4 shown, the present invention discloses a spinning test system of an industrial electrospinning machine, including a memory and a processor, wherein the memory includes a spinning test method program for an industrial electrospinning machine. When the spinning test method program for the industrial electrospinning machine is executed by the processor, the following steps are implemented:

[0101] Obtain a pixel scale to initialize calibration parameters;

[0102] Obtain a captured image for image processing to obtain a target image;

[0103] Calculate the fiber pixel size based on the target image to obtain a measurement result;

[0104] Perform visual display and storage based on the measurement result, and synchronously generate a measurement report.

[0105] It should be noted that in this embodiment, when testing the spinning of an industrial electrospinning machine, the pixel scale is first confirmed, that is, a suitable magnifying device is selected to take multiple test images, and the ratio of the pixel scale to the actual distance is calculated. Then, an industrial camera is used to take pictures. After the electrospinning is completed, the spun fiber together with the recovery rod is placed in the detection area, and the position is adjusted to start the detection. Among them, the movement control device moves the position, and the industrial camera takes pictures at multiple positions and uses the transmission unit to transmit the captured images.

[0106] Further, after obtaining the captured images, image processing is performed to obtain the target image. Correspondingly, the image processing includes image grayscale conversion, histogram equalization, Gaussian filtering, and graphic edge enhancement. Then, based on the target image, the fiber pixel size is calculated to obtain the measurement result, that is, the actual physical fiber pixel size of the image is calculated through the conversion of the image pixel coordinates and the physical coordinate system to obtain the measurement result. Finally, based on the measurement result, visual display and storage are performed, and a measurement report is generated synchronously.

[0107] According to the embodiment of the present invention, obtaining the pixel scale to initialize the calibration parameters specifically includes:

[0108] Obtaining several test images to calculate the pixel scale;

[0109] Based on the pixel scale, set the focal length, magnification, and shooting angle during image shooting to complete the initialization of the calibration parameters.

[0110] It should be noted that in this embodiment, several test images are obtained to calculate the pixel scale. The formula is as follows: "(unit pixel):(actual distance)". Based on the pixel scale, parameters such as the focal length, magnification, and shooting angle of the industrial camera are set to ensure that the captured images can accurately reflect the physical size of the electrospun fiber.

[0111] Specifically, at the initial stage of the production line, the system needs to be calibrated to ensure accurate subsequent dimension measurement. Before the production line is started, the operator places a standard sample with a known size (such as a fiber with a diameter of "150" nanometers) in the detection area, uses the industrial camera to take multiple images, and obtains the pixel scale by calculating the proportional relationship between the pixels and the actual size in the image. For example, in the test image, "1 pixel corresponds to 0.1 nanometer", and the recorded scale is "1:0.1". Then, parameters such as the focal length, magnification, and shooting angle of the industrial camera are set to ensure that the captured images can accurately reflect the physical size of the fiber.

[0112] According to the embodiment of the present invention, obtaining the captured images to perform image processing to obtain the target image specifically includes:

[0113] Preprocess the captured image, and the preprocessing methods include grayscale conversion, histogram equalization, and Gaussian filtering;

[0114] Perform edge detection and enhancement on the preprocessed captured image. Among them, use the wavelet modulus maximum edge detection operator for edge detection, and adopt the adaptive threshold method to remove edge noise to complete the edge enhancement operation.

[0115] It should be noted that in this embodiment, the color image is converted into a grayscale image to reduce the computational complexity. Among them, the grayscale conversion formula is: Y = 0.299R + 0.587G + 0.114B, where Y represents the grayscale value, and R, G, and B represent the components of red, green, and blue respectively.

[0116] Furthermore, perform histogram equalization processing on the grayscale image to increase the dynamic range of the grayscale values between pixels and make the image clearer. The formula is as follows:

[0117]

[0118] Among them, N is the total number of pixels, n j is the number of pixels at the j-th grayscale level, k is the grayscale level, and T(r k ) is the transformation function.

[0119] Furthermore, perform Gaussian filtering on the image to suppress noise and improve the image quality. Then perform edge detection and enhancement on the preprocessed captured image. Among them, use the wavelet modulus maximum edge detection operator for edge detection, and adopt the adaptive threshold method to remove edge noise to complete the edge enhancement operation.

[0120] According to the embodiment of the present invention, calculating the fiber pixel size based on the target image to obtain the measurement result specifically includes:

[0121] Calculate the fiber pixel size in the target image through the Hough transform and the least squares method;

[0122] Convert the pixel size into the actual physical size based on the pixel scale to obtain the measurement result.

[0123] It should be noted that in this embodiment, the fiber pixel size is calculated through the Hough transform and the least squares method, and according to the calibrated pixel scale, the pixel size is converted into the actual physical size. Among them, the formula is as follows:

[0124]

[0125] Among them, (u, v) are the coordinates in the image pixel coordinate system, (x, y) are the coordinates in the image physical coordinate system, dx is the actual physical size corresponding to each pixel in the x direction, dy is the actual physical size corresponding to each pixel in the y direction, and (u0, v0) are the coordinates of the origin of the image pixel coordinate system in the image physical coordinate system.

[0126] Specifically, after edge detection, it is necessary to calculate the actual diameter of the fiber and compare it with the design specifications to ensure that the fiber meets the requirements. Among them, the pixel size of the fiber in the image is calculated by the Hough transform and the least squares method. For example, after detecting the edge of the fiber, the Hough transform is used to fit the contour of the fiber to calculate the pixel diameter of the fiber. According to the calibrated pixel scale, the pixel size is converted into the actual physical size. For example, if the measured diameter of the fiber in the image is "150" pixels and the scale is "1:0.1", the actual diameter of the fiber is calculated to be "15" nanometers. In actual applications, the calculated fiber diameter is compared with the design specifications (100 - 200 nanometers) to determine whether it meets the requirements.

[0127] Furthermore, after the detection is completed, it is necessary to display the measurement results to the operator in real time and generate a detection report for subsequent analysis and use. Among them, the calculated actual size of the fiber is transmitted to the front-end processing device through the network, and the microcontroller of the front-end processing device controls the display to show the measurement results. For example, the display shows "Fiber diameter: 15 nanometers, meets the design requirements". Furthermore, it is also necessary to store the measurement results in the database and generate a detection report. For example, a report containing information such as fiber diameter, detection time, and detection location is generated for the quality management department to conduct subsequent analysis.

[0128] The third aspect of the present invention provides a computer-readable storage medium, which includes a program for the spinning test method of an industrial electrospinning machine. When the program for the spinning test method of the industrial electrospinning machine is executed by a processor, the steps of a spinning test method of an industrial electrospinning machine as described in any one of the above are implemented.

[0129] An industrial electrospinning machine spinning test device, method, system, and storage medium disclosed by the present invention achieve automated, high-precision, and low-cost electrospinning detection, solve the problems of inefficiency and high cost of traditional methods, and are applicable to various application scenarios.

[0130] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined, or can be integrated into another system, or some features can be ignored, or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed with each other can be through some interfaces. The indirect coupling or communication connection of devices or units can be electrical, mechanical, or other forms.

[0131] The units described above as separate components may or may not be physically separated. The components shown as units may or may not be physical units; they can be located in one place or distributed to multiple network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0132] In addition, each functional unit in the embodiments of the present invention can be all integrated in a processing unit, or each unit can be separately regarded as a unit, or two or more units can be integrated in one unit; the above-mentioned integrated units can be implemented in the form of hardware, or in the form of a combination of hardware and software functional units.

[0133] Those of ordinary skill in the art can understand that all or part of the steps to implement the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps including the above method embodiments; and the foregoing storage medium includes: removable storage devices, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disks or optical discs and other various media that can store program codes.

[0134] Alternatively, if the above-mentioned integrated units of the present invention are implemented in the form of software function modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiments of the present invention, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present invention. And the foregoing storage medium includes: removable storage devices, ROM, RAM, magnetic disks or optical discs and other various media that can store program codes.

Claims

1. A spinning test device for an industrial electrospinning machine, characterized in that, The device includes: a working module and a detection module, where the working module includes an electrospinning machine and a spinning recovery rod. The electrospinning machine is used to generate electrospun fibers. The spinning recovery rod includes color partitions, and the distance between two spins is greater than a preset value; the detection module includes an industrial camera, a magnifying device, a processing unit, a transmission unit, and a calibration unit. Among them, the industrial camera is used to capture the static electrospun fibers to obtain a captured image. The magnifying device is used to magnify the captured image of the industrial camera. The transmission unit is used to transmit the captured image to the processing unit. The calibration unit is used to calibrate the difference parameter between the pixel size and the actual size in the captured image. The processing unit is used to process the captured image to extract fiber size information.

2. The spinning test device of an industrial electrospinning machine according to claim 1, wherein The working module further includes a high-voltage power supply, a lighting device, and a movement control device. Among them, the high-voltage power supply is used to supply power to the electrospinning machine. The lighting device is used to provide lighting conditions. The movement control device is used to move the spinning recovery rod.

3. A spinning test method for an industrial electrospinning machine, characterized in that, Applied to the spinning test device of an industrial electrospinning machine according to any one of claims 1-2, where the method includes the following steps: Obtain a pixel scale to initialize calibration parameters; Obtain a captured image for image processing to obtain a target image; Calculate the fiber pixel size based on the target image to obtain a measurement result; Based on the measurement result, perform visual display and storage, and synchronously generate a measurement report.

4. A spinning test method for an industrial electrospinning machine according to claim 3, characterized in that The obtaining of the pixel scale to initialize calibration parameters specifically includes: Obtain several test images to calculate the pixel scale; Based on the pixel scale, set the focal length, magnification, and shooting angle during image shooting to complete the initialization of calibration parameters.

5. A spinning test method for an industrial electrospinning machine according to claim 4, characterized in that, The obtaining of the captured image for image processing to obtain a target image specifically includes: Perform preprocessing on the captured image. The preprocessing methods include grayscale conversion, histogram equalization, and Gaussian filtering; Perform edge detection and enhancement on the preprocessed captured image. Among them, use the wavelet modulus maximum edge detection operator for edge detection, and adopt an adaptive threshold method to remove edge noise to complete the edge enhancement operation.

6. A spinning test method for an industrial electrospinning machine according to claim 5, characterized in that The calculating of the fiber pixel size based on the target image to obtain a measurement result specifically includes: Calculate the fiber pixel size in the target image through the Hough transform and the least squares method; Convert the pixel size to the actual physical size based on the pixel scale to obtain the measurement result.

7. An industrial electrospinning machine spinning test system, characterized in that Includes a memory and a processor. The memory includes a spinning test method program for an industrial electrospinning machine. When the spinning test method program for the industrial electrospinning machine is executed by the processor, the following steps are implemented: Obtain a pixel scale to initialize calibration parameters; Obtain a captured image for image processing to obtain a target image; Calculate the fiber pixel size based on the target image to obtain a measurement result; Based on the measurement result, perform visual display and storage, and synchronously generate a measurement report.

8. An industrial electrospinning machine spinning test system according to claim 7, characterized in that, The obtaining of the pixel scale to initialize calibration parameters specifically includes: Obtain several test images to calculate the pixel scale; Set the focal length, magnification, and shooting angle during image shooting based on the pixel scale to complete the initialization of the calibration parameters.

9. An industrial electrospinning machine spinning test system according to claim 8, characterized in that, The obtaining of the captured image for image processing to obtain the target image specifically includes: Perform preprocessing on the captured image, and the preprocessing methods include grayscale conversion, histogram equalization, and Gaussian filtering; Perform edge detection and enhancement on the preprocessed captured image. Among them, use the wavelet modulus maximum edge detection operator for edge detection, and adopt the adaptive threshold method to remove edge noise to complete the edge enhancement operation.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a program for the spinning test method of an industrial electrospinning machine. When the program for the spinning test method of the industrial electrospinning machine is executed by a processor, the steps of a spinning test method of an industrial electrospinning machine as described in any one of claims 3 to 6 are implemented.

Images