Detection methods, apparatus, equipment and storage media

Abstract

This application provides a detection method, apparatus, device, and storage medium that acquires image information of the flared opening of an air conditioner dual-unit expansion tube; determines the image contours in the image information; calculates the center and diameter of the minimum circumcircle of each image contour; removes interfering contours based on the center and diameter to obtain the target contour of the flared opening; determines the corresponding compensation correction value of the target contour based on the grayscale value of the ring background with a preset pixel width outside each target contour; compensates the diameter of the corresponding target contour based on the compensation correction value to obtain the diameter of each flared opening; and detects the flared opening based on the diameter of each flared opening and a preset standard diameter range. This method can remove detection interference, complete automated detection of the flared opening, improve detection efficiency, and enhance detection accuracy.

Description

Technical Field

[0001] This application relates to the field of air conditioning technology, and in particular to a detection method, apparatus, equipment and storage medium. Background Technology

[0002] In the production of air conditioner heat exchanger and evaporator components, to ensure the performance quality and welding pass rate of the heat exchangers and evaporators, it is necessary to inspect the diameter of the flared end after tube expansion and flaring. Related technologies employ measurement methods such as measuring tapes or vernier calipers, with production staff conducting visual self-inspection and inspectors performing specialized checks. Inspection methods mainly involve first-pass inspection and random sampling, which is labor-intensive and carries the risk of missed inspections, potentially leading to product quality abnormalities. Furthermore, in related visual inspection methods, image acquisition using area array cameras is employed. However, commonly used area array camera image acquisition schemes have low resolution and image edge distortion, failing to meet dimensional measurement accuracy requirements. For evaporators with irregularly shaped side plates, the diameter measurement error is significant for flared ends that connect directly to the fins without penetrating the side plate, leading to misjudgments. Additionally, punch holes on the side plate not used for tube penetration are easily misidentified as flared ends due to their similar shape. In short, the existing inspection methods have a high false detection rate. Summary of the Invention

[0003] To address the aforementioned problems, this application provides a detection method, apparatus, device, and storage medium that can improve the detection accuracy of the horn mouth quality and increase detection efficiency.

[0004] This application provides a detection method, including:

[0005] Obtain image information of the flared end of the air conditioner dual-unit expansion tube;

[0006] Determine the image contours in the image information, and calculate the center and diameter of the smallest circumcircle of each image contour;

[0007] Based on the center and diameter, the interference contour is removed to obtain the target contour of the horn mouth;

[0008] The compensation and correction values ​​corresponding to the target contours are determined based on the grayscale values ​​of the circular background with a preset pixel width outside each target contour.

[0009] The diameter of the corresponding target contour is compensated based on the compensation correction value to obtain the diameter of each flared opening;

[0010] The horn openings are tested based on their diameters and a preset standard diameter range.

[0011] In some embodiments, determining the compensation correction value corresponding to the target contour based on the grayscale value of the circular background with a preset pixel width outside each target contour includes:

[0012] Extract the grayscale value of the circular background with a preset pixel width outside each target contour;

[0013] Calculate the average gray level based on the gray level values;

[0014] Based on the average grayscale value and the pre-established correspondence, the compensation correction value corresponding to the target contour is determined, wherein the correspondence includes the correspondence between the average grayscale value of the sample and the compensation correction value of the sample.

[0015] In some embodiments, the method further includes:

[0016] Obtain a sample dataset, wherein each sample data in the sample dataset includes: the average gray value of the sample corresponding to the sample funnel and the sample compensation correction value;

[0017] The diameter of the sample horn opening is compensated based on the sample compensation correction value;

[0018] Based on the feedback information regarding whether the user installation was successful, determine whether the average gray value of the sample matches the sample compensation and correction value.

[0019] If the average gray value of the sample matches the sample compensation correction value, record the matching data;

[0020] Establish a correspondence between the average gray value of the samples and the sample compensation correction value based on the matching data.

[0021] In some embodiments, establishing the correspondence between the average grayscale value of the samples and the sample compensation correction value based on the matching data includes:

[0022] Based on the matching data, linear regression processing is performed to obtain a linear regression function;

[0023] The correspondence between the average gray value of the sample and the sample compensation correction value is determined based on the linear regression function.

[0024] In some embodiments, determining the image contour in the image information includes:

[0025] The image information is preprocessed;

[0026] The preprocessed image is binarized to obtain a binarized image;

[0027] Extract the image contour from the binarized image.

[0028] In some embodiments, acquiring image information of the flared end of the air conditioner dual-unit expansion tube includes:

[0029] Image information of the flared opening of the dual-unit expansion tube of an air conditioner is acquired using a line scan camera.

[0030] In some embodiments, the step of removing the interference contour based on the center and diameter to obtain the target contour of the horn mouth includes:

[0031] The screening diameter range is determined based on the standard diameter range and the diameter deviation value;

[0032] Remove contours whose diameter is outside the range of the selected diameter;

[0033] Remove the contours whose center deviates from the average height of each row of flared mouths to obtain the target contour of the flared mouths.

[0034] This application provides a detection device, including:

[0035] The acquisition module is used to acquire image information of the flared end of the air conditioner dual-unit expansion tube;

[0036] The first determining module is used to determine the image contours in the image information and calculate the center and diameter of the smallest circumcircle of each image contour.

[0037] The filtering module is used to remove interfering contours based on the center and diameter of the circle to obtain the target contour of the horn mouth;

[0038] The second determining module is used to determine the compensation correction value corresponding to the target contour based on the gray value of the circular background with a preset pixel width outside each target contour.

[0039] The compensation module is used to compensate the diameter of the corresponding target contour based on the compensation correction value to obtain the diameter of each flared opening;

[0040] The detection module is used to detect the horn openings based on the diameter of each horn opening and a preset standard diameter range.

[0041] This application provides an electronic device, including a memory and a processor. The memory stores a computer program, which, when executed by the processor, performs the detection method described in any of the above-mentioned embodiments.

[0042] This application provides a computer-readable storage medium storing a computer program that can be executed by one or more processors and can be used to implement the detection method described above.

[0043] This application provides a detection method, apparatus, device, and storage medium that acquires image information of the flared opening of an air conditioner dual-unit expansion tube; determines the image contours in the image information; calculates the center and diameter of the minimum circumcircle of each image contour; removes interfering contours based on the center and diameter to obtain the target contour of the flared opening; determines the corresponding compensation correction value of the target contour based on the grayscale value of the ring background with a preset pixel width outside each target contour; compensates the diameter of the corresponding target contour based on the compensation correction value to obtain the diameter of each flared opening; and detects the flared opening based on the diameter of each flared opening and a preset standard diameter range. This method can remove detection interference, complete automated detection of the flared opening, improve detection efficiency, and enhance detection accuracy. Attached Figure Description

[0044] The present application will be described in more detail below based on embodiments and with reference to the accompanying drawings.

[0045] Figure 1 A schematic diagram illustrating the implementation flow of a detection method provided in an embodiment of this application;

[0046] Figure 2 A schematic diagram of a flared opening provided for an embodiment of this application;

[0047] Figure 3 A schematic flowchart of a detection method provided in an embodiment of this application;

[0048] Figure 4 This is a schematic diagram of the composition structure of the electronic device provided in the embodiments of this application.

[0049] In the accompanying drawings, the same parts are referred to by the same reference numerals, and the drawings are not drawn to scale. Detailed Implementation

[0050] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limitations on this application. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0051] In the following description, references are made to “some embodiments,” which describe a subset of all possible embodiments. However, it is understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0052] If the application documents contain similar descriptions such as "first, second, third", the following explanation shall be added: In the following description, the terms "first, second, third" are used only to distinguish similar objects and do not represent a specific order of objects. It is understood that "first, second, third" may be interchanged in a specific order or sequence where permitted, so that the embodiments of this application described herein can be implemented in an order other than that illustrated or described herein.

[0053] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0054] Based on the problems existing in related technologies, this application provides a detection method, which is applied to electronic devices, such as computers, mobile terminals, etc., and the mobile terminals may include mobile phones, tablet computers, etc.

[0055] The detection method provided in this application can achieve its function by having the processor of an electronic device call program code, wherein the program code can be stored in a computer storage medium.

[0056] This application provides a detection method. Figure 1 This is a schematic diagram illustrating the implementation flow of a detection method provided in an embodiment of this application, as shown below. Figure 1 As shown, it includes:

[0057] Step S101: Obtain image information of the flared end of the air conditioner dual-unit expansion tube.

[0058] In this embodiment, the flared opening is obtained by flaring the expansion tube of the air conditioner dual-unit. The image information can be a picture.

[0059] In some embodiments, the electronic device can communicate with a line scan camera to acquire image information of the flared opening of the air conditioner's dual-unit expansion pipe. The communication connection can be achieved through various communication methods, including local area networks (LANs), direct communication, and internet communication. LANs can include wireless LANs and wired LANs. Wireless LANs include Wireless Fidelity (WiFi) and Zigbee. Direct communication includes Bluetooth, acoustic communication, and device-to-device (D2D) communication based on mobile networks. Internet communication can be achieved using protocols such as Message Queuing Telemetry Transport (MQTT) and Hypertext Transfer Protocol (HTTP).

[0060] In this embodiment, a line scan camera can be positioned in the image acquisition area of ​​the horn opening to capture images from the horn opening side. The line scan camera can acquire images line by line.

[0061] In some embodiments, the electronic device can communicate with an input device to input image information of the flare opening of the air conditioner dual-unit expansion pipe.

[0062] In some embodiments, the electronic device can obtain image information of the flared end of the air conditioner dual-unit expansion pipe from the Internet.

[0063] Step S102: Determine the image contours in the image information, and calculate the center and diameter of the smallest circumcircle of each image contour.

[0064] In this embodiment, the image contour in the image may include: the contour of the flared opening and the contour of the punched hole. In this embodiment, the image contour in the image information can be determined by a contour extraction algorithm.

[0065] In some embodiments, determining the image contour in the image information can be achieved through the following steps:

[0066] Step S1021: Preprocess the image information.

[0067] In this embodiment of the application, preprocessing the image information may include: translating the image to adjust its orientation to match that of the actual object, so as to facilitate comparison and verification with the actual object when visualizing the image.

[0068] In some embodiments, image information preprocessing further includes: cropping the image to obtain the actual detection area from the image information. Obtaining the actual detection area through cropping can improve image processing speed and reduce detection complexity.

[0069] In some embodiments, image preprocessing further includes performing operations such as filtering and morphological processing on the image information to remove noise points in the image and make the boundaries of the contours in the image smoother.

[0070] Step S1022: Binarize the preprocessed image to obtain a binarized image.

[0071] In this embodiment, image binarization converts the image into a grayscale image. Pixel values ​​in an image are determined by three RGB components, each with 0-255 (256 possible values). Therefore, a single pixel can have 16 million possible values ​​(256*256*256). A grayscale image, on the other hand, has only 256 possible values ​​for each pixel, as all three RGB components are the same. Therefore, in image processing, various images are often first converted to grayscale for subsequent processing, reducing computational load. Grayscale refers to an image containing only brightness information, not color information. A black and white photograph is a grayscale image, characterized by a continuous transition from dark to light. Like color images, grayscale images still reflect the overall and local distribution and characteristics of chromaticity and brightness levels. Binarization facilitates subsequent image processing.

[0072] Step S1023: Extract the image contours from the binarized image.

[0073] In this embodiment, image contours in a binarized image can be extracted using a contour extraction algorithm. After extracting the image contours, the center and diameter of the minimum circumcircle of each image contour can be calculated.

[0074] Step S103: Remove the interfering contour based on the center and diameter to obtain the target contour of the horn mouth.

[0075] In this embodiment of the application, since the extracted contour contains not only the actual horn opening but also interference from extra side plate punching holes, it is necessary to filter the contour.

[0076] In this embodiment of the application, step S103 can be implemented through the following steps:

[0077] Step S1031: Determine the screening diameter range based on the standard diameter range and the diameter deviation value.

[0078] In this embodiment, the standard diameter range and diameter deviation value may differ for different products. Users can preset the standard diameter range and diameter deviation value for each product. The diameter deviation value can be 20% of the standard diameter range.

[0079] The lower limit of the screening diameter range can be obtained by subtracting the diameter deviation value from the minimum value of the standard diameter range, and the upper limit of the screening diameter range can be obtained by adding the diameter deviation value to the maximum value of the standard diameter range. Based on the lower limit and the upper and lower limits of the screening diameter range, the screening diameter range can be obtained.

[0080] Step S1032: Remove contours whose diameter is not within the range of the selected diameter.

[0081] In this embodiment of the application, if the diameter of an image contour is within the range of the filtering diameter, it is not removed; if the diameter of an image contour is within the range of the filtering diameter, it needs to be removed.

[0082] Step S1033: Remove the contours whose center deviates from the average height of each row of flared mouths to obtain the target contour of the flared mouths.

[0083] The method provided in this application determines the screening diameter range based on the standard diameter range and the diameter deviation value; removes contours whose diameter is not within the screening diameter range; and removes contours whose center deviates from the average height of each row of flared mouths to obtain the target contour of the flared mouth, which can remove the interference of the punching on the side plate.

[0084] Step S104: Determine the compensation correction value corresponding to the target contour based on the gray value of the circular background with a preset pixel width outside each target contour.

[0085] In this embodiment, after determining each target contour, a circular background with a preset pixel width outside the target contour can be determined. Then, the compensation correction value corresponding to the target contour is determined using the grayscale value of the circular background.

[0086] In this embodiment, the compensation correction value is used to correct the diameter of the target contour.

[0087] For example, Figure 2 A schematic diagram of a flared opening provided in an embodiment of this application is shown below. Figure 2 As shown, based on the minimum circumcircle of the contour being O2 (theoretically, the edges of the contour are irregular, not shown here, only O2 is used as an example to represent the minimum circumcircle of the acquired image contour), the calculated diameter is L2. Due to the influence of irregularly shaped fins and flanged holes in the background, L2 is not accurate; that is, the actual size of the expansion tube opening is as shown. Figure 2 The circle shown in O1 indicates that the diameter of the target contour needs to be corrected.

[0088] In some embodiments, step S104 can be implemented through the following steps:

[0089] Step S1041: Extract the grayscale value of the circular background with a preset pixel width outside each target contour.

[0090] The preset pixel width can be set. For example, a preset pixel width of M pixels can be used to sample a circular background. Continuing from the example above, see [link to example]. Figure 2 O3 represents the ambient background, and the grayscale values ​​of the circular background with a preset pixel width outside the contour of each target are extracted. For example, the sampling is X1 to X4.

[0091] Step S1042: Calculate the average grayscale value based on the grayscale value.

[0092] Continuing with the example above, X = (X1 + X2 + X3 + X4) / 4, where X is the average grayscale value.

[0093] Step S1043: Based on the average gray value and the pre-established correspondence, determine the compensation correction value corresponding to the target contour, wherein the correspondence includes the correspondence between the average gray value of the sample and the compensation correction value of the sample.

[0094] For example, the correspondence between the average gray value of a sample and the sample compensation correction value includes: the correspondence between X and l, where the compensation correction value corresponding to X is l. The compensation correction value is the length value.

[0095] In this embodiment of the application, the correspondence may be pre-established.

[0096] In some embodiments, prior to step S104, the method further includes:

[0097] Step S1: Obtain the sample dataset, wherein each sample data in the sample dataset includes: the average gray value of the sample corresponding to the sample funnel and the sample compensation correction value.

[0098] In this embodiment of the application, the sample dataset may include multiple sample data. Each sample data can be considered as an initial correspondence.

[0099] Step S2: Compensate the diameter of the sample horn based on the sample compensation correction value.

[0100] In this embodiment, the diameter of the sample horn opening can be compensated by subtracting the sample compensation correction value from the diameter of the horn opening.

[0101] Step S3: Based on the feedback information regarding whether the user installation was successful, determine whether the average gray value of the sample matches the sample compensation correction value.

[0102] In this embodiment, the user can perform installation verification based on the compensated diameter and provide feedback on whether the electronic device installation was successful.

[0103] In this embodiment of the application, if the installation is unsuccessful, the average gray value of the sample will not match the sample compensation correction value; if the installation is successful, the average gray value of the sample will match the sample compensation correction value.

[0104] Step S4: If the average gray value of the sample matches the sample compensation correction value, record the matching data.

[0105] In this embodiment of the application, matching sample data can be recorded to obtain matching data.

[0106] Step S5: Establish the correspondence between the average gray value of the samples and the sample compensation correction value based on the matching data.

[0107] In this embodiment of the application, step S5 can be implemented through the following steps:

[0108] Step S51: Perform linear regression processing on the matching data to obtain a linear regression function;

[0109] Step S52: Determine the correspondence between the average gray value of the sample and the sample compensation correction value based on the linear regression function.

[0110] For example, when matching data exists, based on the statistical distribution characteristics and mathematical linear regression theory, the corresponding value ranges of the compensation correction lengths la, lb, lc and Xa, Xb, Xc are determined. For example, Table 1 is a schematic diagram of one such correspondence provided in an embodiment of this application, as shown in Table 1:

[0111] Horn mouth name Average gray value of the background Compensation correction length Actual assembly results A 110 0.28mm success B 115 0.24mm success C 120 0.22mm success ... ... ... ... N1 150 0.18mm success N2 160 0.1mm success N3 175 0.09mm success ... ... ... ...

[0112] Step S105: Based on the compensation correction value, compensate for the diameter of the corresponding target contour to obtain the diameter of each horn opening.

[0113] In this embodiment, the diameter of each horn opening can be obtained by subtracting the compensation correction value corresponding to each target contour from the diameter of each target contour.

[0114] Step S106: Detect the horn openings based on the diameter of each horn opening and a preset standard diameter range.

[0115] In this embodiment, the diameter of each horn opening can be determined to be within a preset standard diameter range to detect the horn opening. If the diameter of each horn opening is within the preset standard diameter range, it indicates that the size of the horn opening meets the standard; otherwise, it does not meet the standard. This feedback is used to optimize the detection algorithm and diameter estimation, thereby achieving horn opening quality detection.

[0116] This application provides a detection method that involves acquiring image information of the flared opening of an air conditioner dual-unit expansion tube; determining the image contours in the image information; calculating the center and diameter of the minimum circumcircle of each image contour; removing interfering contours based on the center and diameter to obtain the target contour of the flared opening; determining the corresponding compensation correction value of the target contour based on the grayscale value of the ring background with a preset pixel width outside each target contour; compensating the diameter of the corresponding target contour based on the compensation correction value to obtain the diameter of each flared opening; and detecting the flared opening based on the diameter of each flared opening and a preset standard diameter range. This method can remove detection interference, complete automated detection of the flared opening, improve detection efficiency, and enhance detection accuracy.

[0117] Based on the foregoing embodiments, this application further provides a detection method. This method uses a line scan camera to acquire images of the flared end, performs image preprocessing, extracts image contour features based on a set binarization threshold, and filters the flared end diameter to remove interfering contours that are inconsistent in size or position. Next, for flared ends that are directly connected to the fins without passing through the side plate, the measured diameter is compensated and corrected based on the average grayscale value of the flared end background pixels. Referring to statistical distribution rules and based on the accuracy of the data feedback, the compensation and correction value for the expansion tube diameter is determined, thus completing the estimation of the expansion tube diameter and realizing a quality detection method for the flared ends of the expansion tubes in air conditioning units.

[0118] The method provided in this application embodiment is based on a computer vision scheme and achieves distortion-free image acquisition through a line scan image acquisition scheme. For evaporators using irregularly shaped side plates, the diameter of the flared end can also be accurately measured. This realizes the automated full inspection of the flared end diameter after the expansion and forming of the air conditioner's two components. It is easy to operate, has a wide monitoring range, and has high detection efficiency and accuracy. It can quickly locate the location of product quality abnormalities and effectively monitor the flared end quality of the air conditioner's two components.

[0119] Figure 3 This is a schematic diagram illustrating the implementation flow of a detection method provided in an embodiment of this application, as shown below. Figure 3 As shown, it includes:

[0120] Obtain the image of the horn opening.

[0121] In this embodiment, a horn-mouth image acquisition area is set according to the line scan camera image acquisition device, and images of the horn-mouth sides of the two devices are captured. The line scan camera acquires images line by line. After the computer acquires the images, it performs preprocessing. First, the images are translated and adjusted to match the orientation of the actual objects, facilitating comparison and verification with the actual objects during image visualization. The actual detection area is cropped from the image, improving image processing speed and reducing detection complexity. Filtering and morphological processing are performed on the images to remove noise points and smooth boundaries.

[0122] Quality inspection of the horn mouth.

[0123] In this embodiment of the application, the flared mouth quality inspection includes: removing punching interference and detecting the diameter of the flared mouth connected to the fins, wherein removing punching interference includes:

[0124] The preprocessed image is binarized, and image contours are extracted based on the binarized image. The minimum circumcenter and diameter of each image contour are calculated. Since the extracted image contours contain interference from redundant edge plate punching holes in addition to the real horn opening, contour filtering is required.

[0125] Since the flared mouths of qualified products are uniform in size and regularly distributed, i.e., the diameter is within the standard range, and the Y-coordinate of the center of each row of flared mouths is also within the standard range, the upper and lower limits of the standard range of diameter and Y-coordinate of the center can be widened by 20% respectively. Based on this, interference contours that are too large or too small in diameter, or whose center deviates from the average height of each row, can be removed, i.e., interference from punching holes on the side plate can be removed.

[0126] After removing the outline of the punched holes on the side plate, what remains is the extracted flared mouth outline. However, this also includes the outline of the flared mouth that is directly connected to the fin without passing through the side plate. The extraction results of these flared mouth outlines are greatly affected by the background pixels. The grayscale value of the background has a great influence on the diameter specification detection of the flared mouth. By establishing the correspondence between the background grayscale and the flared mouth image, that is, finding the influence of the background grayscale value on the flared mouth, the error in diameter detection can be effectively solved and the detection accuracy can be improved.

[0127] In this embodiment of the application, the detection of the fin-connected flared opening includes:

[0128] Flare diameter correction:

[0129] See also Figure 3 The diameter is calculated as L2 based on the minimum circumcircle of the contour, which is O2 (theoretically, the edges of the contour are irregular, not shown here, but O2 is used as an example to represent the minimum circumcircle of the acquired image contour). However, due to the influence of irregularly shaped fins and flanged holes in the background, L2 is not accurate, meaning the actual size of the expansion tube opening is less than the actual size. Figure 3 The circle shown in O1.

[0130] Assuming the flared opening is a standard circle, and the standard diameter here is (maximum standard diameter + minimum standard diameter) / 2, within a circular background M pixels wide, such as... Figure 3 For O3, take its average gray value. Here, the average value X can be calculated by sampling various gray values ​​in the environment, such as X = (X1 + X2 + X3 + X4) / 4, where X1 to X4 represent the various environmental gray values ​​sampled from the surrounding environment. In this case, take the compensation correction length corresponding to X as l, where the value of l depends on the range of X. That is, the final diameter of the flared opening is L = L2 - l. If in practice L = L1, where L1 represents the actual radius of the flared opening, such as... Figure 3 The presence of O1 indicates that the compensation is relatively correct, thus establishing the correspondence between X and l.

[0131] To ensure the accuracy of the final compensation for L, the determination of la is crucial, and the criteria used are as follows:

[0132] For the marked horn opening O1, when the difference between the compensated L and the manually measured value is less than 0.2mm (to determine whether the compensation value is appropriate, i.e., the issue of confirmation, the criterion is feedback and correction; the specific standard is only an example), assembly is considered successful, indicating that L is relatively accurate after compensation. At this time, the correspondence between the average gray value X of the background in S221 and l is recorded. Through the above data processing, when there are a large number of marked horn openings A, B, C..., based on the statistical distribution characteristics and mathematical linear regression theory, the corresponding value ranges of the compensation correction lengths la, lb, lc and Xa, Xb, Xc are determined. See the table below:

[0133] Horn mouth name Average gray value of the background Compensation correction length Actual assembly results A 110 0.28mm success B 115 0.24mm success C 120 0.22mm success ... ... ... ... N1 150 0.18mm success N2 160 0.1mm success N3 175 0.09mm success ... ... ... ...

[0134] When the actual assembly fails, it indicates that the length of the compensation correction does not match the background pixels. Based on the data clustering and the verification of the set success rate threshold, the correspondence between Xn and ln is established, and the length correction of the diameter can be performed during the horn mouth image detection process.

[0135] The above-described detection and diameter compensation strategy can detect the diameter and contour interference of all flared mouths. Based on the process parameters of the two instruments, a preset standard diameter range for the flared mouth is established. The calculated flared mouth diameter is compared with this preset standard diameter range. If the calculated value is within the preset standard diameter range, the flared mouth size conforms to the standard; otherwise, it does not. This feedback is used to optimize the detection algorithm and diameter estimation, thus achieving flared mouth quality inspection.

[0136] The method provided in this application utilizes image contour extraction to remove punching interference and applies a compensation correction logic to the measured diameter based on the average grayscale value of the background pixels at the flared opening. The compensation correction value is determined based on statistical distribution and result verification feedback, thereby detecting the diameter of the flared opening connected to the fins in the evaporator and reducing the false detection rate. This solves the problems of low efficiency, inconvenient operation, and large inspection errors associated with traditional manual sampling. Specifically, image processing methods are used to extract and compare the contours of the flared opening, removing detection interference and automating the detection of the flared opening, thus improving production efficiency and reducing false detections.

[0137] Based on the foregoing embodiments, this application provides a detection device. The modules and units included in the device can be implemented by a processor in a computer device; of course, they can also be implemented by specific logic circuits. In the implementation process, the processor can be a central processing unit (CPU), a microprocessor (MPU), a digital signal processor (DSP), or a field programmable gate array (FPGA), etc.

[0138] This application provides a detection device, including:

[0139] The acquisition module is used to acquire image information of the flared end of the air conditioner dual-unit expansion tube;

[0140] The first determining module is used to determine the image contours in the image information and calculate the center and diameter of the smallest circumcircle of each image contour.

[0141] The filtering module is used to remove interfering contours based on the center and diameter of the circle to obtain the target contour of the horn mouth;

[0142] The second determining module is used to determine the compensation correction value corresponding to the target contour based on the gray value of the circular background with a preset pixel width outside each target contour.

[0143] The compensation module is used to compensate the diameter of the corresponding target contour based on the compensation correction value to obtain the diameter of each flared opening;

[0144] The detection module is used to detect the horn openings based on the diameter of each horn opening and a preset standard diameter range.

[0145] In some embodiments, determining the compensation correction value corresponding to the target contour based on the grayscale value of the circular background with a preset pixel width outside each target contour includes:

[0146] Extract the grayscale value of the circular background with a preset pixel width outside each target contour;

[0147] Calculate the average gray level based on the gray level values;

[0148] Based on the average grayscale value and the pre-established correspondence, the compensation correction value corresponding to the target contour is determined, wherein the correspondence includes the correspondence between the average grayscale value of the sample and the compensation correction value of the sample.

[0149] In some embodiments, the detection device is further configured to:

[0150] Obtain a sample dataset, wherein each sample data in the sample dataset includes: the average gray value of the sample corresponding to the sample funnel and the sample compensation correction value;

[0151] The diameter of the sample horn opening is compensated based on the sample compensation correction value;

[0152] Based on the feedback information regarding whether the user installation was successful, determine whether the average gray value of the sample matches the sample compensation and correction value.

[0153] If the average gray value of the sample matches the sample compensation correction value, record the matching data;

[0154] Establish a correspondence between the average gray value of the samples and the sample compensation correction value based on the matching data.

[0155] In some embodiments, establishing the correspondence between the average grayscale value of the samples and the sample compensation correction value based on the matching data includes:

[0156] Based on the matching data, linear regression processing is performed to obtain a linear regression function;

[0157] The correspondence between the average gray value of the sample and the sample compensation correction value is determined based on the linear regression function.

[0158] In some embodiments, determining the image contour in the image information includes:

[0159] The image information is preprocessed;

[0160] The preprocessed image is binarized to obtain a binarized image;

[0161] Extract the image contour from the binarized image.

[0162] In some embodiments, acquiring image information of the flared end of the air conditioner dual-unit expansion tube includes:

[0163] Image information of the flared opening of the dual-unit expansion tube of an air conditioner is acquired using a line scan camera.

[0164] In some embodiments, the step of removing the interference contour based on the center and diameter to obtain the target contour of the horn mouth includes:

[0165] The screening diameter range is determined based on the standard diameter range and the diameter deviation value;

[0166] Remove contours whose diameter is outside the range of the selected diameter;

[0167] Remove the contours whose center deviates from the average height of each row of flared mouths to obtain the target contour of the flared mouths.

[0168] It should be noted that, in the embodiments of this application, if the above-described detection method is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiments of this application, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), magnetic disks, or optical disks. Thus, the embodiments of this application are not limited to any specific hardware and software combination.

[0169] Accordingly, embodiments of this application provide a computer-readable storage medium storing a computer program thereon, characterized in that the computer program, when executed by a processor, implements the steps in the detection method provided in the above embodiments.

[0170] This application provides an electronic device; Figure 4 This is a schematic diagram of the composition structure of the electronic device provided in the embodiments of this application, such as... Figure 4 As shown, the electronic device 500 includes: a processor 501, at least one communication bus 502, a user interface 503, at least one external communication interface 504, and a memory 505. The communication bus 502 is configured to enable communication between these components. The user interface 503 may include a control panel, and the external communication interface 504 may include standard wired and wireless interfaces. The processor 501 is configured to execute a program of a detection method stored in the memory to implement the steps of the detection method, wherein a detection method includes:

[0171] Obtain image information of the flared end of the air conditioner dual-unit expansion tube;

[0172] Determine the image contours in the image information, and calculate the center and diameter of the smallest circumcircle of each image contour;

[0173] Based on the center and diameter, the interference contour is removed to obtain the target contour of the horn mouth;

[0174] The compensation and correction values ​​corresponding to the target contours are determined based on the grayscale values ​​of the circular background with a preset pixel width outside each target contour.

[0175] The diameter of the corresponding target contour is compensated based on the compensation correction value to obtain the diameter of each flared opening;

[0176] The horn openings are tested based on their diameters and a preset standard diameter range.

[0177] In some embodiments, determining the compensation correction value corresponding to the target contour based on the grayscale value of the circular background with a preset pixel width outside each target contour includes:

[0178] Extract the grayscale value of the circular background with a preset pixel width outside each target contour;

[0179] Calculate the average gray level based on the gray level values;

[0180] Based on the average grayscale value and the pre-established correspondence, the compensation correction value corresponding to the target contour is determined, wherein the correspondence includes the correspondence between the average grayscale value of the sample and the compensation correction value of the sample.

[0181] In some embodiments, the method further includes:

[0182] Obtain a sample dataset, wherein each sample data in the sample dataset includes: the average gray value of the sample corresponding to the sample funnel and the sample compensation correction value;

[0183] The diameter of the sample horn opening is compensated based on the sample compensation correction value;

[0184] Based on the feedback information regarding whether the user installation was successful, determine whether the average gray value of the sample matches the sample compensation and correction value.

[0185] If the average gray value of the sample matches the sample compensation correction value, record the matching data;

[0186] Establish a correspondence between the average gray value of the samples and the sample compensation correction value based on the matching data.

[0187] In some embodiments, establishing the correspondence between the average grayscale value of the samples and the sample compensation correction value based on the matching data includes:

[0188] Based on the matching data, linear regression processing is performed to obtain a linear regression function;

[0189] The correspondence between the average gray value of the sample and the sample compensation correction value is determined based on the linear regression function.

[0190] In some embodiments, determining the image contour in the image information includes:

[0191] The image information is preprocessed;

[0192] The preprocessed image is binarized to obtain a binarized image;

[0193] Extract the image contour from the binarized image.

[0194] In some embodiments, acquiring image information of the flared end of the air conditioner dual-unit expansion tube includes:

[0195] Image information of the flared opening of the dual-unit expansion tube of an air conditioner is acquired using a line scan camera.

[0196] In some embodiments, the step of removing the interference contour based on the center and diameter to obtain the target contour of the horn mouth includes:

[0197] The screening diameter range is determined based on the standard diameter range and the diameter deviation value;

[0198] Remove contours whose diameter is outside the range of the selected diameter;

[0199] Remove the contours whose center deviates from the average height of each row of flared mouths to obtain the target contour of the flared mouths.

[0200] It should be noted that the descriptions of the storage medium and device embodiments above are similar to the descriptions of the method embodiments above, and have similar beneficial effects. For technical details not disclosed in the storage medium and device embodiments of this application, please refer to the descriptions of the method embodiments of this application for understanding.

[0201] It should be understood that the phrase "one embodiment" or "an embodiment" throughout the specification means that a specific feature, structure, or characteristic related to the embodiment is included in at least one embodiment of this application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. It should be understood that in the various embodiments of this application, the sequence numbers of the above-described processes do not imply a sequential order of execution; the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application. The sequence numbers of the above-described embodiments are merely descriptive and do not represent the superiority or inferiority of the embodiments.

[0202] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0203] In the several embodiments provided in this 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 units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the controlled or discussed components can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0204] The units described above as separate components may or may not be physically separate. The components controlled by the units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0205] In addition, each functional unit in the various embodiments of this application can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0206] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media that can store program code, such as mobile storage devices, read-only memory (ROM), magnetic disks, or optical disks.

[0207] Alternatively, if the integrated units described above are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a controller to execute all or part of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROMs, magnetic disks, or optical disks.

[0208] The above description is merely an embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A detection method, characterized in that, include: Obtain image information of the flared end of the air conditioner dual-unit expansion tube; Determine the image contours in the image information, and calculate the center and diameter of the smallest circumcircle of each image contour; wherein, the image contours in the image information include: the contour of the flared mouth and the contour of the punched hole; determining the image contours in the image information includes: The image information is preprocessed, including: the image is translated to align with the orientation of the actual object, so as to facilitate comparison and verification with the actual object during image visualization; The preprocessed image is binarized to obtain a binarized image; Extract the image contour from the binarized image; Based on the center and diameter, the interference contour is removed to obtain the target contour of the horn mouth; The compensation and correction values ​​corresponding to the target contours are determined based on the grayscale values ​​of the circular background with a preset pixel width outside each target contour; including: Extract the grayscale value of the circular background with a preset pixel width outside each target contour; Calculate the average gray level based on the gray level values; Based on the average gray value and the pre-established correspondence, the compensation correction value corresponding to the target contour is determined, wherein the correspondence includes: the correspondence between the average gray value of the sample and the compensation correction value of the sample; The diameter of the corresponding target contour is compensated based on the compensation correction value to obtain the diameter of each flared opening; The horn openings are tested based on their diameters and a preset standard diameter range.

2. The method according to claim 1, characterized in that, The method further includes: Obtain a sample dataset, wherein each sample data in the sample dataset includes: the average gray value of the sample corresponding to the sample funnel and the sample compensation correction value; The diameter of the sample horn opening is compensated based on the sample compensation correction value; Based on the feedback information regarding whether the user installation was successful, determine whether the average gray value of the sample matches the sample compensation and correction value. If the average gray value of the sample matches the sample compensation correction value, record the matching data; Establish a correspondence between the average gray value of the samples and the sample compensation correction value based on the matching data.

3. The method according to claim 2, characterized in that, The process of establishing the correspondence between the average grayscale value of the samples and the sample compensation correction value based on the matching data includes: Based on the matching data, linear regression processing is performed to obtain a linear regression function; The correspondence between the average gray value of the sample and the sample compensation correction value is determined based on the linear regression function.

4. The method according to claim 1, characterized in that, The acquisition of image information of the flared end of the air conditioner dual-unit expansion tube includes: Image information of the flared opening of the dual-unit expansion tube of an air conditioner is acquired using a line scan camera.

5. The method according to claim 1, characterized in that, The process of removing interference contours based on the center and diameter to obtain the target contour of the horn-shaped opening includes: The screening diameter range is determined based on the standard diameter range and the diameter deviation value; Remove contours whose diameter is outside the range of the selected diameter; Remove the contours whose center deviates from the average height of each row of flared mouths to obtain the target contour of the flared mouths.

6. A detection device, characterized in that, include: The acquisition module is used to acquire image information of the flared end of the air conditioner dual-unit expansion tube; The first determining module is used to determine the image contours in the image information and calculate the center and diameter of the smallest circumcircle of each image contour; wherein, the image contours in the image information include: the contour of a flared mouth and the contour of a punch; determining the image contours in the image information includes: The image information is preprocessed, including: the image is translated to align with the orientation of the actual object, so as to facilitate comparison and verification with the actual object during image visualization; The preprocessed image is binarized to obtain a binarized image; Extract the image contour from the binarized image; The filtering module is used to remove interfering contours based on the center and diameter of the circle to obtain the target contour of the horn mouth; The second determining module is used to determine the compensation correction value corresponding to the target contour based on the grayscale value of the annular background with a preset pixel width outside each target contour; wherein, determining the compensation correction value corresponding to the target contour based on the grayscale value of the annular background with a preset pixel width outside each target contour includes: Extract the grayscale value of the circular background with a preset pixel width outside each target contour; Calculate the average gray level based on the gray level values; Based on the average gray value and the pre-established correspondence, the compensation correction value corresponding to the target contour is determined, wherein the correspondence includes: the correspondence between the average gray value of the sample and the compensation correction value of the sample; The compensation module is used to compensate the diameter of the corresponding target contour based on the compensation correction value to obtain the diameter of each flared opening; The detection module is used to detect the horn openings based on the diameter of each horn opening and a preset standard diameter range.

7. An electronic device, characterized in that, It includes a memory and a processor, wherein the memory stores a computer program that, when executed by the processor, performs the detection method as described in any one of claims 1 to 5.

8. A storage medium, characterized in that, The computer program stored in the storage medium can be executed by one or more processors and can be used to implement the detection method as described in any one of claims 1 to 5.

Images