Non-defective product detection method and visual detection system for miniature pipes and storage medium

Abstract

The invention is suitable for the technical field of automatic detection of heating non-combustion equipment, and provides a good product detection method of a miniature pipe, a visual detection system and a storage medium, the method is applied to the visual detection system, and the visual detection system comprises a detection position. The method comprises the steps that a target end face image, collected by a first camera at a detection position in a first direction, of a to-be-detected miniature pipe is obtained, a target side face image, collected by a second camera at the detection position in a second direction, of the to-be-detected miniature pipe is obtained, and the first direction is perpendicular to the second direction; according to the target end face image and the target side face image, target pipe data of the to-be-detected miniature pipe are extracted, and the target pipe data are used for representing the structure of the to-be-detected miniature pipe; and determining a non-defective product detection result of the to-be-detected miniature pipe according to the difference between the target pipe data and the preset error data. According to the scheme, good product detection can be quickly and accurately carried out on the micro ceramic tube in a non-contact manner.

Description

Technical Field

[0001] This application belongs to the field of automated testing technology for heated non-combustible equipment, and particularly relates to a method for detecting the quality of micro-tubes, a visual inspection system, and a storage medium. Background Technology

[0002] In the production process of heated non-combustible equipment, the micro ceramic tubes, as the support and heat transfer carrier, often affect the assembly yield and user experience of the heated non-combustible equipment. Therefore, it is crucial to conduct good quality inspection on the micro ceramic tubes before assembling the heated non-combustible equipment to eliminate defective tubes.

[0003] Currently, the quality inspection solutions for micro-ceramic tubes often rely on manual sampling using tools such as calipers or micrometers, or placing sampled micro-ceramic tubes on the stage of an optical projector to magnify their structure through the projector's optical path for manual geometric parameter detection and evaluation. However, such inspection solutions require a large investment of manpower and have low efficiency and accuracy. Furthermore, sampling inspection cannot meet the needs of large-scale production lines that require the inspection of all micro-ceramic tubes. In addition, contact inspection may damage the micro-ceramic tubes, further increasing the inspection error.

[0004] Therefore, how to quickly, accurately, and non-contactly inspect the quality of micro ceramic tubes has become an urgent technical problem to be solved. Summary of the Invention

[0005] This application provides a method for inspecting the quality of micro-tubes, a visual inspection system, and a storage medium, which can solve the problem of how to quickly, accurately, and non-contactly inspect the quality of micro-ceramic tubes.

[0006] In a first aspect, embodiments of this application provide a method for inspecting the quality of miniature tubing, applied to a vision inspection system. The vision inspection system includes a detection position, at which a first camera and a second camera are configured. The method includes: The first camera acquires a target end face image of the microtube to be inspected at the detection position in a first direction, and the second camera acquires a target side image of the microtube to be inspected at the detection position in a second direction, wherein the first direction and the second direction are perpendicular to each other. Based on the target end face image and the target side image, the target pipe data of the micro pipe to be inspected is extracted. The target pipe data is used to represent the structure of the micro pipe to be inspected. Based on the difference between the target pipe data and the preset error data, the good product test result of the micro pipe to be inspected is determined.

[0007] In some embodiments, the visual inspection system further includes a first light source and a second light source, wherein the first light source is used to provide coaxial light or ring light to the first camera, and the second light source is used to provide backlight to the second camera.

[0008] In some embodiments, the visual inspection system further includes a sorting module and a conveying mechanism, with the inspection position opposite to the sorting module. The conveying mechanism passes through the inspection position and the sorting module, and is used to convey the micro-tube to be inspected to the inspection position. The method further includes: If the tube fails the quality inspection, the sorting module removes the micro-tube to be inspected from the conveying mechanism.

[0009] In some embodiments, the first camera is an area scan camera including a telecentric lens, and the second camera is an area scan camera or a line scan camera.

[0010] In some embodiments, target pipe data of the micro-pipe to be inspected is extracted based on the target end face image and the target side image, including: The contour data of the end face of the micro-tube to be inspected is identified from the target end face image. The contour data includes the first dimension parameter of the outer contour of the end face and the second dimension parameter of the inner contour. Based on the difference between the first dimension parameter and the second dimension parameter, the geometric feature parameters of the end face are determined. The geometric feature parameters are used to represent the deviation between the outer contour and the inner contour of the end face. The length data, contour data, geometric feature parameters, and length data of the micro-tube to be inspected are identified from the side image of the target as the target tube data.

[0011] In some embodiments, the preset error data includes a contour range, a length range, and a geometric parameter range. Based on the difference between the target pipe data and the preset error data, the yield inspection result of the micro-pipe to be inspected is determined, including: If at least one of the following conditions is met: the contour data exceeds the contour range, the length data exceeds the length range, or the geometric feature parameters exceed the geometric parameter range, the good product inspection result of the micro-tube to be inspected is determined to be a defective tube; or, If the contour data is within the contour range, the length data is within the length range, and the geometric feature parameters are within the geometric parameter range, the good product inspection result of the micro-tube to be inspected is determined to be a qualified tube.

[0012] In some embodiments, the method further includes: Identify defect information on the surface of the micro-tube to be inspected based on the target end face image; When the defect information meets the preset abnormal defect conditions, the good product inspection result of the micro-tube to be inspected is determined to be a defective tube. The preset abnormal defect conditions are used to indicate the maximum degree of defect on the surface of the micro-tube.

[0013] In some embodiments, the method further includes: The identification information of the micro-pipe to be inspected, the target pipe data, the target end face image and the target side image are associated and stored in the database. The database includes the identification information, pipe data, end face image and side image corresponding to the inspected micro-pipes. In response to the test report generation operation, a pipe test report is generated based on the identification information, pipe data, end face image and side image of at least one micro pipe in the database.

[0014] Secondly, embodiments of this application provide a visual inspection system, the system comprising: The first camera is used to acquire an image of the target end face of the micro-tube to be inspected in a first direction at the detection location; The second camera is used to acquire a target side image of the micro-tube to be inspected at the detection position in a second direction, wherein the first direction and the second direction are perpendicular to each other. An electronic device is used to acquire images of the target end face and the target side face; it is also used to extract target pipe data of the micro-tube to be inspected based on the target end face and target side face images, the target pipe data being used to represent the deformation of the structure of the micro-tube to be inspected; and it is also used to determine the good product inspection result of the micro-tube to be inspected based on the difference between the target pipe data and preset error data.

[0015] Thirdly, embodiments of this application provide an electronic device including a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it causes the electronic device to perform the method described in any of the embodiments of the first aspect.

[0016] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in any of the embodiments of the first aspect.

[0017] Fifthly, embodiments of this application provide a computer program product, including a computer program, which, when run, causes the method described in any embodiment of the first aspect to be executed.

[0018] The beneficial effects of the embodiments in this application compared with the prior art are: With the microtube under inspection located in the inspection position, images are acquired simultaneously from the end face and side face of the microtube by a first camera and a second camera positioned at different directions on the microtube. This results in clear images of the target end face and target side face, eliminating the need to flip the microtube, adjust the camera angle, or move it to another location for image acquisition from a different angle. This significantly improves the efficiency of acquiring end face and side face images. Target tube data is extracted from the two images taken from different angles, allowing simultaneous detection of deformation in different directions. The yield result, determined by the difference between the target tube data and preset error data, is an accurate result based on the deformation in both the end face and side face dimensions of the microtube. This enables multi-directional, high-efficiency, and high-precision non-contact non-destructive testing of microtubes, such as micro-ceramic tubes in heated non-combustible devices. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a schematic diagram of the structure of a visual inspection system provided in an embodiment of this application.

[0021] Figure 2 This is a frontal and top view structural diagram of a visual inspection system provided in an embodiment of this application.

[0022] Figure 3 This is a flowchart illustrating a method for inspecting the quality of micro-tubes provided in an embodiment of this application.

[0023] Figure 4 This is a flowchart illustrating another method for inspecting the quality of micro-tubes provided in this application embodiment.

[0024] Figure 5 This is a flowchart illustrating another method for inspecting the quality of micro-tubes provided in this application embodiment.

[0025] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0026] The technical solutions in the embodiments of this application will be described below with reference to the accompanying drawings.

[0027] Figure 1 This is a schematic diagram of the structure of a visual inspection system for a good product inspection method for micro-tubes provided in an embodiment of this application, as shown below. Figure 1 The visual inspection system 100 shown includes: The first camera 110 is used to acquire an image of the target end face of the micro-tube 130 to be inspected in a first direction at the detection position; The second camera 120 is used to acquire a target side image of the micro-tube 130 to be inspected at the detection position in a second direction, wherein the first direction and the second direction are perpendicular to each other. Electronic device 140 is used to acquire target end face image and target side image; it is also used to extract target pipe data of micro pipe 130 to be inspected based on the target end face image and target side image, the target pipe data being used to represent the deformation of the structure of micro pipe 130 to be inspected; it is also used to determine the good product inspection result of micro pipe 130 to be inspected based on the difference between the target pipe data and preset error data.

[0028] Both the first camera 110 and the second camera 120 are two-dimensional cameras, and both are spatially calibrated using a standard calibration plate. The standard calibration plate can be a black and white chessboard.

[0029] The micro-tube 130 to be inspected is a micro-tube required for the production of heated non-combustible equipment, such as a micro-ceramic tube, a micro-metal tube, or a microcrystalline glass tube. This application does not impose specific limitations on the embodiments. For convenience, a micro-ceramic tube is used as an example.

[0030] The end face of the microtube 130 to be inspected is the cross-sectional area formed after the microtube is cut or processed at both ends along its axial direction. This end face can be circular or elliptical. Therefore, in order to capture an image of the target end face, the position of the first camera 110 can be along the extension direction of the axis of the microtube to be inspected; that is, the first direction can be along the extension direction of the axis of the microtube to be inspected.

[0031] The side surface of the microtube 130 to be inspected, also referred to as the surface, is parallel to the axis of the microtube. Therefore, in order to obtain an image of the target side surface, the position of the first camera 110 can be perpendicular to the axis of the microtube to be inspected; that is, the second direction can be perpendicular to the axis of the microtube to be inspected.

[0032] Combination Figure 1 and Figure 2When the micro-tube 130 to be inspected is placed vertically, that is, with the end face facing up, and with the movement direction of the conveying mechanism 180 as the front, the first camera 110 is located above the micro-tube 130 to be inspected, and the second camera 120 is located to the right of the micro-tube 130 to be inspected.

[0033] Electronic device 140 can be a tablet computer, laptop computer, ultra-mobile personal computer (UMPC), netbook, or personal digital assistant (PDA), etc. This application embodiment does not impose any restrictions on the specific type of electronic device 140. It should be noted that the steps performed by the visual detection system in subsequent embodiments are the steps performed by the system through the electronic device, that is, by the electronic device itself.

[0034] In one implementation, the first camera 110 is an area array camera including a telecentric lens, and the second camera 120 is an area array camera or a line array camera. The area array camera 120 is a high-resolution area array camera to accurately capture the length information of the micro-tube to be inspected. A high-resolution area array camera refers to an area array camera with a resolution greater than or equal to a specified threshold, such as 5 megapixels or 12 megapixels, etc., which is not specifically limited in this embodiment. When the area array camera with the telecentric lens captures the end face of the micro-tube to be inspected, the telecentric lens can eliminate perspective errors, thereby ensuring that the dimensions of the end face of the micro-tube to be inspected remain unchanged in the target end face image. Subsequently, by combining the telecentric lens with a precision algorithm, the measurement accuracy and efficiency of the target tube data are improved, allowing the single-piece inspection time to be controlled within 1 second, meeting the full inspection requirements of the production line. By capturing the side of the micro-tube to be inspected using an area array camera or a line array camera, the entire appearance information of the side of the micro-tube to be inspected can be quickly captured, providing reliable data support for subsequent determination of the good product inspection results of the micro-tube to be inspected.

[0035] In one implementation, continue to combine Figure 1 The visual inspection system 100 also includes a first light source 150 and a second light source 160. The first light source 150 is used to provide coaxial light or ring light to the first camera 110, and the second light source 160 is used to provide backlight to the second camera 120.

[0036] The first light source 150 is located in the first direction of the micro-tube 130 to be inspected at the detection position, and the second light source 160 is located in the second direction of the micro-tube 130 to be inspected at the detection position.

[0037] Combination Figure 1 and Figure 2The first light source 150 is opposite to the first camera 110, and the two can be located at the upper and lower ends of the micro-tube 130 to be inspected, respectively. The second light source 160 is opposite to the second camera 120, and the two can be located on the left and right sides of the micro-tube 130 to be inspected, respectively.

[0038] When coaxial light illuminates a flat area on the end face of the micro-tube under inspection, most of the light is reflected back to the first camera 110, resulting in a bright image. However, at the edges of the end face, the light is scattered, resulting in a dark image. This abrupt change in high contrast between light and dark allows the edge of the end face to be clearly presented in the target end face image, achieving sub-pixel-level edge positioning and high-precision dimensional measurement. In this way, electronic equipment can accurately identify the edge of the end face, scratches, or dents in the end face from the target end face image, providing a reliable data basis for subsequent determination of good product inspection results.

[0039] Similarly, when the ring light illuminates the end face of the micro-tube to be inspected, it will also produce shadows on the edge of the end face, and next to the tiny depressions, protrusions or scratches in the end face. This enhances the contrast of the texture and defects of the end face during the imaging period of the first camera 110, so that the electronic device can identify the defects of the end face through the target end face image, and provide a reliable data basis for the subsequent determination of the good product inspection results.

[0040] When the backlight illuminates the side of the microtube under inspection, some of the light is blocked by the microtube. The light that is not blocked enters the second camera 120 and forms a bright image, while the surface of the microtube is relatively dark. Thus, the side image captured by the second camera 120 can include the projection of the microtube with clear boundaries. In this way, the electronic equipment can accurately identify the length of the side from the target side image, facilitating subsequent detection of whether the microtube is a good product.

[0041] In this technical solution, two light sources, one facing the first camera and the other facing the second camera, provide sufficient illumination when acquiring images of the target end face and the target side face of the micro-tube to be inspected. This enables the two cameras to acquire clear images with high contrast, thereby improving the accuracy of good product inspection of the micro-tube to be inspected.

[0042] In one implementation, continue to combine Figure 1 The visual inspection system 100 also includes a sorting module 170 and a conveying mechanism 180. The inspection position is opposite to the position of the sorting module 170. The conveying mechanism 180 passes through the inspection position and the sorting module 170. The conveying mechanism 180 is used to convey the micro-tubes 130 to be inspected to the inspection position. The electronic device 140 is also used to control the sorting module 170 to remove the micro-tubes 130 to be inspected from the conveying mechanism 180 when the good product inspection result is a defective tube.

[0043] In one implementation, the vision inspection system 100 includes a robotic arm for placing the micro-tube 130 to be inspected at the inspection position. A conveying mechanism 180, specifically configured to respond to a conveying command from the electronic device 140, moves the micro-tube 130 away from the inspection position so that it enters the sorting process of the sorting module 170. The electronic device 140 can send a conveying command to the conveying mechanism 180 after determining that the micro-tube 130 has passed quality inspection.

[0044] This technical solution automates the transport of microtubes to be inspected to different workstations via a conveyor mechanism. As the microtubes pass through the inspection station, image acquisition and quality assessment are automatically performed. Defective tubes are automatically removed as they pass through the sorting module. This achieves fully automated closed-loop control from feeding, positioning, inspection, judgment to sorting, significantly reducing manual intervention and improving the production efficiency of the heated non-combustible equipment. It also removes defective tubes from the conveyor mechanism, reducing the likelihood of them entering subsequent processes and improving the user experience of the heated non-combustible equipment. Furthermore, this assembly-line inspection mode can automatically perform quality inspection and screening for each microtube when there are many to be inspected. It provides fast, accurate, and non-contact quality inspection of micro-ceramic tubes, meeting the needs of large-scale production lines that require inspection of all micro-ceramic tubes.

[0045] The aforementioned visual inspection system achieves simultaneous imaging of the end face and side face of the micro-tube under inspection by using a first camera and a second camera located in the first and second directions (or orthogonally distributed) respectively. By providing a coaxial or ring light source as the first light source and a backlight source as the second light source, the contrast between the edges and the micro-tube itself in the images acquired by the two cameras is improved. This allows the electronic equipment to extract high-precision target tube data from the target end face and target side face images, and based on this, perform accurate good product inspection of the micro-tube under inspection in real time. Furthermore, combined with a conveying mechanism and sorting module to automatically remove defective tubes, the system ensures full inspection and zero omissions for all micro-tubes while avoiding manual parameters, significantly improving the efficiency and accuracy of good product inspection of micro-tubes, and significantly reducing labor costs and the risk of secondary damage.

[0046] Figure 3 This is a flowchart illustrating a method for inspecting the quality of micro-tubes applied to the aforementioned visual inspection system, as provided in this application embodiment. Figure 3 As shown, the method includes the following steps.

[0047] S101, acquire the target end face image of the micro-tube to be inspected captured by the first camera at the detection position in the first direction, and acquire the target side image of the micro-tube to be inspected captured by the second camera at the detection position in the second direction.

[0048] The visual inspection system includes a detection location, at which a first camera and a second camera are configured.

[0049] The first direction and the second direction are perpendicular to each other. The first direction can be the extension direction of the axis of the micro-tube to be inspected. The second direction can be a direction perpendicular to the axis of the micro-tube to be inspected.

[0050] The first camera located in the first direction can acquire images of the end face of the micro-tube to be inspected and send the acquired images to the electronic equipment in the vision inspection system. The second camera located in the second direction can acquire images of the surface, i.e. the side, of the micro-tube to be inspected and send the acquired images to the electronic equipment. In this way, the vision inspection system obtains the target end face image and the target side image through the electronic equipment.

[0051] To improve the reliability of subsequent target pipe data and reduce misjudgments (e.g., a qualified micro-pipe being judged as unqualified because it is misplaced) or missed judgments (e.g., an unqualified micro-pipe being judged as qualified because it is misplaced), it is necessary to ensure that the micro-pipe to be inspected is accurately placed at the inspection position. Therefore, in one implementation, when the micro-pipe to be inspected meets the placement conditions, the vision inspection system controls a first camera and a second camera to acquire images. These placement conditions include that the angle between the axis of the micro-pipe to be inspected and the surface where the inspection position is located is within a preset angle range, and the deviation between the center position of the end face of the micro-pipe to be inspected and the center position of the inspection position is within a preset position range.

[0052] The visual inspection system can still determine whether the micro-tube to be inspected meets the inspection placement conditions using images captured by the first and second cameras. Specifically, the visual inspection system also includes a robotic arm used to move the micro-tube to be inspected and, after moving the micro-tube to the inspection position, send a positioning request to the electronic device. The visual inspection system receives the positioning request through the electronic device and sends image acquisition commands to the first and second cameras. The first and second cameras respond to the image acquisition commands, acquire images, and send them to the electronic device. The visual inspection system then obtains the first positioning image captured by the first camera and the second positioning image captured by the second camera through the electronic device. Based on the outline of the micro-tube to be inspected in the first and second positioning images, the visual inspection system determines whether the micro-tube to be inspected meets the inspection placement conditions.

[0053] For example, the visual inspection system uses electronic devices to identify whether the outline of the end face of the micro-tube to be inspected exists in the first positioning image; if the outline exists, the system determines the center position of the end face based on the identified outline, and determines the difference between the center position and the center position of the detection position. The visual inspection system also uses electronic devices to identify the slope difference (also called parallelism) between the slopes of the two edges of the side of the micro-tube to be inspected in the second positioning image, and determines the angle corresponding to the slope difference based on the correspondence between the slope difference and a preset slope angle. This angle is used as the angle between the axis of the micro-tube to be inspected and the surface where the detection position is located. The visual inspection system uses electronic devices to determine whether this angle is within a preset angle range and whether the determined difference is within a preset position range. If the angle is within the preset angle range and the determined difference is within the preset position range, the system determines that the micro-tube to be inspected meets the detection placement conditions, and sends image acquisition commands to the first and second cameras again through electronic devices to obtain the target end face image and the target side face image. If the included angle is not within the preset included angle range, the determined difference is not within the preset position range, or the end face of the micro-tube to be inspected is not present in the first positioning image, then it is determined that the micro-tube to be inspected does not meet the inspection placement conditions. The electronic device outputs a position adjustment command to the robot arm, which responds to the position adjustment command to adjust the position of the micro-tube to be inspected and sends a positioning request until the vision inspection system determines through the electronic device that the micro-tube to be inspected meets the inspection placement conditions, or the number of adjustments exceeds the preset number.

[0054] When the vision inspection system determines through electronic devices that the number of adjustments has exceeded the preset number, it will also output a prompt message indicating that the micro-pipe to be inspected has failed to be successfully placed in the inspection position multiple times. This allows for manual adjustment of the micro-pipe's position.

[0055] S102, extract the target pipe data of the micro pipe to be inspected based on the target end face image and the target side image.

[0056] The target pipe data is used to represent the structural accuracy of the micro-pipe to be inspected. Specifically, the target pipe data may include dimensional and geometrical tolerance information to represent structural accuracy, such as roundness, coaxiality, wall thickness uniformity, or average wall thickness.

[0057] The visual inspection system uses electronic devices to identify the contour of the end face of the micro-tube under inspection from the target end face image and the contour of the side surface of the micro-tube under inspection from the target side image. Based on the identified end face and side surface contours, the system calculates the dimensions and geometric tolerances of the target tube, thus obtaining the target tube data. Depending on the shape of the micro-tube under inspection, the target tube data can include different data. For example, when the micro-tube is round, the target tube data can include the average inner diameter, average outer diameter, average wall thickness, roundness, coaxiality, and the length of the side surface. When the micro-tube is elliptical, the target tube data can include the major and minor axes of the inner and outer ellipses, wall thickness uniformity, coaxiality, morphological tolerances of the inner ellipse, and the length of the side surface, etc.

[0058] In one implementation, such as Figure 4 As shown, based on the target end face image and the target side image, the target pipe data of the micro pipe to be inspected is extracted, including the following S201 to S203.

[0059] S201, Identify the contour data of the end face of the micro-tube to be inspected from the target end face image.

[0060] The contour data includes the first dimension parameter of the outer contour of the end face and the second dimension parameter of the inner contour.

[0061] The visual inspection system performs image preprocessing on the target end face image using electronic devices to obtain a processed end face image; it then extracts pixels on the inner contour edge of the end face of the micro-tube to be inspected from the processed end face image to obtain an inner contour edge point set, and extracts pixels on the outer contour edge of the end face of the micro-tube to be inspected to obtain an outer contour edge point set; based on the position of each pixel in the inner contour edge point set, it determines a second size parameter, and based on the position of each pixel in the outer contour edge point set, it determines a first size parameter, and the first size parameter and the second size parameter are used as contour data.

[0062] Image preprocessing operations include at least one of the following: filtering and noise reduction, contrast enhancement, or binarization. Filtering and noise reduction primarily eliminates image noise using Gaussian filtering algorithms; contrast enhancement mainly strengthens the contrast between contours and background in the image through histogram equalization; and binarization mainly converts the image into a black-and-white binary image through automatic thresholding for easier contour extraction.

[0063] By performing image preprocessing on the target end face image, the inner and outer contour features of the end face of the micro-tube to be inspected in the target end face image can be enhanced, thereby obtaining accurate contour data from the processed end face image, providing a reliable data basis for determining the subsequent good product inspection results.

[0064] In one implementation, depending on the shape of the micro-tube to be inspected, the visual inspection system uses electronic equipment to determine the second and first dimension parameters using different strategies. Specifically, when the micro-tube to be inspected is a circular tube, the visual inspection system uses electronic equipment to fit the positions of each pixel in the inner contour edge point set using a least squares circle fitting algorithm to obtain a reference circle for the inner contour. The radius of this reference circle is used as the average inner diameter of the end face, and the center of this reference circle is used as the center of the inner contour. For the outer contour edge point set, the visual inspection system performs a similar process using electronic equipment, obtaining the average outer diameter of the end face using a least squares fitting algorithm, and using the center of the reference circle of the outer contour fitted by the least squares fitting algorithm as the center of the outer contour. The determined average inner and average outer diameters of the end face are used as contour data.

[0065] When the micro-tube to be inspected is an elliptical tube, the visual inspection system uses an electronic device to fit the position of each pixel in the inner contour edge point set using an ellipse fitting algorithm (e.g., least squares ellipse fitting algorithm) to obtain a reference ellipse for the inner contour. The major and minor axes of this reference ellipse are used as the major and minor axes of the inner contour of the end face. For the outer contour edge point set, the visual inspection system performs a similar process using an electronic device to obtain the major and minor axes of the outer contour of the end face. The determined major axis, minor axis, major axis, and minor axis of the inner contour of the end face are used as contour data.

[0066] In the above technical solution, different fitting algorithms can be adaptively adopted to obtain the contour data of the end face of the micro-tubes to be inspected, depending on the different tube shapes. This enables non-contact, high-precision measurement of the relevant structural parameters of different tube shapes during the good product inspection process of micro-tubes. This reduces the equipment cost and complexity of the vision inspection system, and also reduces systematic errors caused by mismatch in fitting algorithms. It greatly enhances the versatility and automation of the inspection method and has strong compatibility.

[0067] S202, Determine the geometric feature parameters of the end face based on the difference between the first dimension parameter and the second dimension parameter.

[0068] Among them, geometric feature parameters are used to represent the deviation between the outer contour and the inner contour of the end face.

[0069] The visual inspection system uses electronic devices to calculate the difference between the second dimensional parameter and the first dimensional parameter to determine the geometric feature parameters of the end face. Different data are included for the geometric feature parameters depending on the tube shape. For example, when the micro-tube to be inspected is round, the geometric feature parameters may include average wall thickness, roundness, and coaxiality; when the micro-tube to be inspected is elliptical, the geometric feature parameters may include wall thickness uniformity, morphological tolerance, and coaxiality.

[0070] Specifically, when the micro-tube to be inspected is a round tube, the visual inspection system uses electronic equipment to take the difference between the average inner diameter and the average outer diameter as the average wall thickness, and calculates the distance between each pixel in the inner contour edge point set and the center of the inner contour reference circle, and the distance between each pixel in the outer contour edge point set and the center of the outer contour reference circle. The difference between the largest and smallest of the calculated distances is taken as the roundness of the end face, and the distance between the center of the inner contour reference circle and the center of the outer contour reference circle is taken as the coaxiality of the end face.

[0071] When the microtube to be inspected is an elliptical tube, the visual inspection system calculates the difference between the major axis of the outer contour and the major axis of the inner contour (or the difference between the minor axis of the outer contour and the minor axis of the inner contour) using electronic equipment. The difference between half of this difference and the nominal wall thickness is used as the wall thickness uniformity of the microtube to be inspected. Furthermore, the system calculates a first ratio between the major and minor axes of the inner contour and a second ratio between a preset standard major axis and a preset standard minor axis. The difference between the first and second ratios is used as the morphological tolerance, and the distance between the center of the reference ellipse of the inner contour and the center of the reference ellipse of the outer contour is used as the coaxiality of the end face. The nominal wall thickness can be 1 mm, and the preset standard major axis and preset standard minor axis can be 10 mm and 7.5 mm, respectively. The specific nominal wall thickness, preset standard major axis, and preset standard minor axis can be determined based on the design parameters of each microtube in the production batch of the microtube to be inspected; this embodiment does not impose any limitations.

[0072] S203, Identify the length data of the micro-tube to be inspected from the side image of the target.

[0073] Among them, the contour data, geometric feature parameters, and length data are used as the target pipe data.

[0074] The visual inspection system uses electronic devices to preprocess the side image of the target, obtaining a processed side image. It then identifies pixels on the edges of the two end faces of the micro-tube under inspection from this processed image. Based on the positions of these pixels and the calibration parameters of the second camera, the system calculates the average distance between the edges of the two end faces as the length data. It can be understood that regardless of whether the micro-tube under inspection is elliptical or circular, the length data can be obtained through the same process.

[0075] In the technical solutions S201 to S203, contour data and length data are extracted from the target end face image and the target side image, respectively. The geometric feature parameters of the end face are determined based on the contour data. The information in the target end face image and the target side image is transformed into complementary quantitative parameters. This enables comprehensive detection of the specific structural precision data of the micro-tube to be inspected, reduces the field of view limitations when inspecting from a single perspective, and provides a reliable and interconnected data foundation for subsequent accurate good product inspection. This significantly improves the comprehensive judgment capability and reliability of the visual inspection system.

[0076] S103, based on the difference between the target pipe data and the preset error data, determine the good product test result of the micro pipe to be inspected.

[0077] The visual inspection system uses electronic devices to determine whether each data point in the target pipe exceeds its corresponding error range. If any data point exceeds the error range, the pipe is determined to be a defective product. If each data point falls within the error range (including the endpoints), the pipe is determined to be a qualified product.

[0078] In one implementation, the preset error data includes a contour range, a length range, and a geometric parameter range. Based on the difference between the target pipe data and the preset error data, the good product inspection result of the micro-pipe to be inspected is determined, including: if at least one of the following conditions is met, the good product inspection result of the micro-pipe to be inspected is determined to be a non-conforming pipe; or, if the contour data is within the contour range, the length data is within the length range, and the geometric feature parameters are within the geometric parameter range, the good product inspection result of the micro-pipe to be inspected is determined to be a qualified pipe.

[0079] The contour range, length range, and geometric parameter range can be set according to the design parameters of each micro-tube in the production batch of the micro-tube to be inspected. The specific implementation of this application does not impose any specific limitations.

[0080] The visual inspection system uses electronic devices to judge various contour data, geometric feature parameters and length data in the target pipe data. If any one of them exceeds its corresponding range, the good product inspection result is determined to be unqualified pipe. Only when all data are within its corresponding range (including the endpoints) is the good product inspection result determined to be qualified pipe. This realizes comprehensive good product inspection based on multiple parameters for the micro pipe to be tested, and improves the reliability of good product inspection results.

[0081] For example, when the micro-tube to be inspected is a round tube, the vision inspection system can determine the good product inspection result based on Table 1 below using electronic equipment. The acceptable ranges for the average inner diameter and average outer diameter constitute the contour range; the acceptable ranges for the average wall thickness, roundness, and coaxiality constitute the geometric parameter range; and the acceptable range for the length is the length range. If the target tube data has an average inner diameter of 4.5 mm, an average outer diameter of 5.2 mm, an average wall thickness of 0.48 mm, a roundness of 0.01, a coaxiality of 0.034, and a length of 15.3 mm, then the vision inspection system determines the good product inspection result of the micro-tube to be inspected as a qualified tube using electronic equipment; if the roundness is 0.02, then the target tube data contains data that does not meet the geometric parameter range, and the good product inspection result of the micro-tube to be inspected is determined as a non-qualified tube.

[0082] Table 1. Good Product Inspection Standards for Micro-tubes to be Inspected When the Micro-tubes to be Inspected are Round Tubes

[0083] For example, when the micro-tube to be inspected is an elliptical tube, the vision inspection system can determine the good product inspection result based on Table 2 below using electronic equipment. The acceptable ranges of the minor axis, major axis, minor axis, and major axis of the inner contour constitute the contour range; the acceptable ranges of coaxiality, morphological tolerance, and wall thickness uniformity constitute the geometric parameter range; and the acceptable range of length is the length range. If the target tube data has an inner contour minor axis of 7.6 mm, an inner contour major axis of 10.1 mm, an outer contour minor axis of 8.5 mm, an outer contour major axis of 12.1 mm, a coaxiality of 0.028, a morphological tolerance of 0.015, a wall thickness uniformity of 0.02, and a length of 12 mm, then the vision inspection system determines the good product inspection result of the micro-tube to be inspected as a qualified tube. If the inner contour minor axis is 7.8 mm, then the target tube data contains data that does not meet the contour range, and the good product inspection result of the micro-tube to be inspected is determined as a non-qualified tube.

[0084] Table 2. Good Product Inspection Standards for Miniature Tubes to be Inspected as Elliptical Tubes

[0085] In this embodiment, when the microtube to be inspected is located at the inspection position, images are acquired simultaneously from the end face and side face of the microtube by a first camera and a second camera positioned at different directions on the microtube. This results in clear images of the target end face and target side face, eliminating the need to flip the microtube or adjust the camera angle, or to move the microtube to another position for image acquisition from a different angle. This significantly improves the efficiency of acquiring end face and side face images of the microtube. Target tube data is extracted from the two images taken from different angles, allowing simultaneous detection of deformation in different directions. The product inspection result, determined by the difference between the target tube data and preset error data, is an accurate result determined from the deformation in both the end face and side face dimensions of the microtube. This achieves multi-directional, high-efficiency, and high-precision non-contact non-destructive testing of microtubes, such as micro-ceramic tubes in heated non-combustible devices. It reduces human interference, resulting in highly reliable product inspection results and fast testing efficiency.

[0086] Figure 5 This is a flowchart illustrating another method for inspecting the quality of micro-tubes provided in this application, as shown in the embodiments. Figure 4 As shown, the method further includes the following steps S301 to S302.

[0087] S301, identify the defect information on the surface of the micro-tube to be inspected based on the target end face image and the target side image.

[0088] The defect information may include the defect type and the number of defects for each defect type. The number of defects may be the total number of defects or the total number of defects per unit area. The defect type may include at least one of scratches, cracks, or contamination spots.

[0089] A visual inspection system can use edge detection algorithms or texture analysis algorithms to identify defects in the end face image and side face image of the target, respectively, and obtain defect information. For example, the visual inspection system uses electronic equipment to identify cracks with a maximum length ≤0.1mm as scratches, cracks with a depth ≤5μm as fissures, and points with an area ≤0.01mm² as contamination points in the end face image and side face image of the target.

[0090] S302, when the defect information meets the preset abnormal defect conditions, the good product inspection result of the micro pipe to be inspected is determined to be a defective pipe.

[0091] The preset abnormal defect condition is used to indicate the maximum degree of defect on the surface of the micro-tube to be inspected. The preset abnormal defect condition may include a defect number less than a preset number or a defect distribution density greater than or equal to a preset density. For example, a preset number or defect distribution density greater than or equal to a preset density.

[0092] When the visual inspection system determines, through electronic devices, that the defect information meets the preset abnormal defect conditions, it updates the good product inspection result determined in S103 to a non-conforming pipe. When it determines that the defect information does not meet the preset abnormal defect conditions, it keeps the good product inspection result determined in S103 unchanged.

[0093] In one implementation, the vision inspection system further includes a sorting module and a conveying mechanism. The inspection position is opposite to the position of the sorting module. The conveying mechanism passes through the inspection position and the sorting module. The conveying mechanism is used to convey the micro-tubes to be inspected to the inspection position. The method further includes: if the good product inspection result is a defective tube, controlling the sorting module to remove the micro-tubes to be inspected from the conveying mechanism.

[0094] The conveying mechanism can be a conveyor belt or a conveyor rail; for convenience, we will take a conveyor rail as an example.

[0095] The sorting module can be a purging device or a robotic arm, etc. For convenience, we will take the purging device as an example.

[0096] When the visual inspection system determines that a good product has been inspected but is actually a defective tube, it sends a sorting instruction to the sorting module via electronic equipment. The sorting module then responds to this instruction by removing the micro-tube to be inspected from the conveyor mechanism. This automatically removes defective tubes from the conveyor mechanism, preventing them from flowing into the next process.

[0097] In one implementation, the vision inspection system also includes a clamp to stabilize the microtube at the inspection location, preventing it from wobbling during inspection. This clamp can be made of materials such as ceramic or alloy and can be designed with a V-groove or a custom contoured structure to suit different tube shapes.

[0098] In one implementation, the method further includes: storing the identification information, target pipe data, target end face image, and target side image of the micro-pipe to be inspected in a database, where the database includes the identification information, pipe data, end face image, and side image corresponding to the inspected micro-pipes; and responding to a test report generation operation, generating a pipe inspection report based on the identification information, pipe data, end face image, and side image corresponding to at least one micro-pipe in the database. This technical solution stores the identification information, target pipe data, target end face image, and target side image of each inspected micro-pipe in the database, ensuring a record of the inspection process. This facilitates the generation of pipe inspection reports based on the identification information, pipe data, end face image, and side image corresponding to at least one micro-pipe in the database, enabling quality traceability and production statistical analysis.

[0099] In this embodiment, defect information in the micro-tube under inspection is automatically detected based on the target end face image and the target side image, and the defect information is combined with preset abnormal defect conditions to determine whether the micro-tube under inspection is qualified in real time. Combined with the target tube data of the micro-tube under inspection, the micro-tube under inspection is inspected from two dimensions: surface defects and structural precision of the tube itself. This can improve the comprehensiveness and reliability of the good product inspection, not only reducing manual intervention, but also capturing microscopic defects on the surface of the micro-tube under inspection through images from two different angles. The sorting module automatically removes unqualified tubes to prevent them from flowing into subsequent processes. In addition, the data storage and report generation functions can further realize the full-process recording and traceability of the good product inspection of the micro-tube under inspection, thereby optimizing the production efficiency and product reliability of the heating non-combustion equipment while ensuring high-precision good product inspection.

[0100] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 6 As shown, the electronic device of this embodiment includes: at least one processor 60 ( Figure 6 (Only one is shown in the diagram) a processor, a memory 61, and a computer program 62 stored in the memory 61 and executable on the at least one processor 60, wherein the processor 60 executes the computer program 62 to implement the steps in any of the above method embodiments.

[0101] The electronic device may be a desktop computer, laptop, handheld computer, or cloud server, etc. This electronic device may include, but is not limited to, a processor 60 and a memory 61. Those skilled in the art will understand that... Figure 6This is merely an example of an electronic device and does not constitute a limitation on electronic devices. It may include more or fewer components than shown in the illustration, or combinations of certain components, or different components. For example, it may also include input / output devices, network access devices, etc.

[0102] The processor 60 may be a Central Processing Unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0103] In some embodiments, the memory 61 may be an internal storage unit of the electronic device, such as a hard drive or memory. In other embodiments, the memory 61 may be an external storage device of the electronic device, such as a plug-in hard drive, smart media card (SMC), secure digital (SD) card, flash card, etc. Furthermore, the memory 61 may include both internal and external storage units of the electronic device. The memory 61 is used to store the operating system, applications, bootloader, data, and other programs, such as the program code of the computer program. The memory 61 can also be used to temporarily store data that has been output or will be output.

[0104] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0105] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0106] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps described in the various method embodiments above.

[0107] This application provides a computer program product that, when run on an electronic device, enables the electronic device to perform the steps described in the various method embodiments above.

[0108] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to a photographing device / terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electrical carrier signals or telecommunication signals.

[0109] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0110] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0111] Furthermore, in the description of this application and the appended claims, the terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized. In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0112] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0113] In the embodiments provided in this application, it should be understood that the disclosed apparatus, computer equipment, and methods can be implemented in other ways. For example, the apparatus and computer equipment embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0114] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for detecting the quality of miniature tubing, characterized in that, Applied to a visual inspection system, the visual inspection system includes a detection position, at which a first camera and a second camera are configured, the method includes: The first camera acquires a target end face image of the microtube to be inspected at the detection position in a first direction, and the second camera acquires a target side image of the microtube to be inspected at the detection position in a second direction, wherein the first direction and the second direction are perpendicular to each other. Based on the target end face image and the target side face image, target pipe data of the micro pipe to be inspected is extracted, and the target pipe data is used to represent the structure of the micro pipe to be inspected; The good product test result of the micro-pipe to be inspected is determined based on the difference between the target pipe data and the preset error data.

2. The method as described in claim 1, characterized in that, The visual inspection system further includes a first light source and a second light source. The first light source is used to provide coaxial light or ring light to the first camera, and the second light source is used to provide backlight to the second camera.

3. The method as described in claim 1 or 2, characterized in that, The visual inspection system further includes a sorting module and a conveying mechanism. The inspection position is opposite to the position of the sorting module. The conveying mechanism passes through the inspection position and the sorting module, and is used to convey the micro-tube to be inspected to the inspection position. The method further includes: If the product inspection result is a defective tube, the sorting module is controlled to remove the micro-tube to be inspected from the conveying mechanism.

4. The method as described in claim 3, characterized in that, The first camera is an area scan camera including a telecentric lens, and the second camera is an area scan camera or a line scan camera.

5. The method as described in claim 1 or 2, characterized in that, The step of extracting target pipe data of the micro-pipe to be inspected based on the target end face image and the target side image includes: The contour data of the end face of the micro-tube to be inspected is identified from the target end face image, and the contour data includes a first dimension parameter of the outer contour of the end face and a second dimension parameter of the inner contour. Based on the difference between the first dimension parameter and the second dimension parameter, the geometric feature parameters of the end face are determined, and the geometric feature parameters are used to represent the deviation between the outer contour and the inner contour of the end face; The length data of the micro-tube to be inspected is identified from the side image of the target, and the contour data, the geometric feature parameters, and the length data are used as the target tube data.

6. The method as described in claim 5, characterized in that, The preset error data includes contour range, length range, and geometric parameter range. Determining the good product inspection result of the micro-tube to be inspected based on the difference between the target tube data and the preset error data includes: If at least one of the following conditions is met: the contour data exceeds the contour range, the length data exceeds the length range, or the geometric feature parameter exceeds the geometric parameter range, the good product inspection result of the micro-tube to be inspected is determined to be a defective tube; or, If the contour data is within the contour range, the length data is within the length range, and the geometric feature parameters are within the geometric parameter range, the good product inspection result of the micro-tube to be inspected is determined to be a qualified tube.

7. The method as described in claim 6, characterized in that, The method further includes: Based on the target end face image, identify the defect information on the surface of the micro-tube to be inspected; When the defect information meets the preset abnormal defect conditions, the good product inspection result of the micro-tube to be inspected is determined to be a defective tube. The preset abnormal defect conditions are used to indicate the maximum degree of defect on the surface of the micro-tube to be inspected.

8. The method as described in claim 1, characterized in that, The method further includes: The identification information of the micro-pipe to be inspected, the target pipe data, the target end face image and the target side image are associated and stored in the database. The database includes the identification information, pipe data, end face image and side image corresponding to the inspected micro-pipe. In response to the test report generation operation, a pipe test report is generated based on the identification information, pipe data, end face image and side image corresponding to at least one micro pipe in the database.

9. A visual inspection system, characterized in that, The system includes: The first camera is used to acquire an image of the target end face of the micro-tube to be inspected in a first direction at the detection location; A second camera is used to acquire a target side image of the microtube to be inspected at the detection location in a second direction, wherein the first direction and the second direction are perpendicular to each other. An electronic device is used to acquire the target end face image and the target side image; it is also used to extract target pipe data of the micro-pipe to be inspected based on the target end face image and the target side image, the target pipe data being used to represent the deformation of the structure of the micro-pipe to be inspected; and it is also used to determine the good product inspection result of the micro-pipe to be inspected based on the difference between the target pipe data and preset error data.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 8.

Images