Elbow screening method and device, elbow screening and classifying system and storage medium

Abstract

The invention discloses an elbow screening method and device, an elbow screening and classifying system, a storage medium and a computer program product, and is provided with a visual system which comprises a first camera and a second camera; the first camera is used for collecting a side view image of the elbow; the second camera is used for collecting a look-up image of the elbow; the method comprises the following steps: determining measurement data of the elbow according to the side view image and the upward view image, and determining whether the elbow is a qualified product or a defective product according to the measurement data. According to the scheme, the visual system is arranged to calculate the actual measurement data of the elbows, whether the elbows are qualified or not is judged according to the actual measurement data, automatic classification and screening of the elbows are achieved, the automatic production efficiency of air conditioners is improved, defective elbows are prevented from being installed on the air conditioners, and it is ensured that the air conditioners have high product quality.

Description

Technical Field

[0001] The present invention belongs to the technical field of air conditioner manufacturing, and specifically relates to a method and device for screening elbows, an elbow screening and classification system, a storage medium and a computer program product. Background Art

[0002] The two devices of an air conditioner usually refer to the evaporator and condenser in the air conditioning system, which are the two core components in the air conditioning refrigeration cycle. In the automated production process of the two devices, pipe installation (i.e., inserting elbows into the two devices) is an extremely important link, and this process is seriously affected by the incoming elbow materials. The reason is that the incoming materials of the industrial production line are complex and diverse, and the shapes and sizes of the elbows are different. Various defects are easy to occur during the insertion process of the elbows, especially the poor sealing caused by the misalignment of the insertion and the missing of the elbow pipe mouth. This will not only cause the feeding mechanism of the automatic elbow insertion machine to get stuck, but more seriously, it will reduce the sealing of the pipeline connection, leading to the leakage of refrigerant in the refrigerant system, corrosion of electrical components and other problems, which directly affects the production quality of air conditioning manufacturing. Therefore, for the situation where the shapes and sizes of elbows are different, it is usually necessary to rely on manual visual discrimination, which is not only inefficient and prone to errors, but also has high labor costs.

[0003] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The purpose of the present invention is to provide a method and device for screening elbows, an elbow screening and classification system, a storage medium and a computer program product, so as to solve the problem in the related scheme that in the automated production process of two devices of an air conditioner, the accuracy of the elbow insertion process is reduced and the sealing quality of the two-device pipelines is seriously reduced due to the different shapes and sizes of the elbows. By setting up a visual system to calculate the actual measurement data of the elbows, it is determined whether the elbows are qualified according to the actual measurement data, thereby realizing automatic classification and screening of elbows, improving the efficiency of automated production of air conditioners, preventing defective elbows from being installed on air conditioners, and ensuring that the air conditioners have a high product quality effect.

[0005] The present invention provides a method for screening elbows, which is provided with a visual system, wherein the visual system comprises: a first camera and a second camera; the first camera is used to collect a side view image of the elbow; the second camera is used to collect an upward view image of the elbow; the method comprises: obtaining a side view image of the elbow collected by the first camera and an upward view image of the elbow collected by the second camera; determining measurement data of the elbow according to the side view image and the upward view image; and determining whether the elbow is a qualified product or a defective product according to the measurement data.

[0006] In some embodiments, the measurement data includes: the height of the elbow, the circumferential weld height of the elbow, the pipe mouth diameter of the elbow, and the pipe mouth center distance of the elbow; determining the measurement data of the elbow according to the side view image and the top view image includes: determining the height of the elbow and the circumferential weld height of the elbow according to the side view image, and determining the pipe mouth diameter of the elbow and the pipe mouth center distance of the elbow according to the top view image.

[0007] In some embodiments, determining the height of the elbow and the height of the ring weld of the elbow according to the side view image includes: performing distortion correction on the side view image; locating the features and position of the elbow in the side view image, and correcting the position of the elbow using preset correction parameters; selecting the bottom ROI area of ​​the elbow to determine the pixel coordinates of the reference straight line at the bottom of the elbow; selecting the top ROI area of ​​the elbow to determine the pixel coordinates of the vertex of the elbow; respectively selecting the left ring weld ROI area and the right ring weld ROI area of ​​the elbow to determine the pixel coordinates of the first point and the second point of the left ring weld, and the pixel coordinates of the first point and the second point of the right ring weld. The pixel coordinates of the two points; the pixel coordinates of the vertex of the elbow and the pixel coordinates of the reference straight line at the bottom of the elbow are substituted into the preset elbow height calculation formula to obtain the pixel coordinates of the height of the elbow; the pixel coordinates of the first point and the second point of the left ring weld, the pixel coordinates of the first point and the second point of the right ring weld, and the pixel coordinates of the reference straight line at the bottom of the elbow are substituted into the preset ring weld height calculation formula to obtain the pixel coordinates of the ring weld height of the elbow; the pixel coordinates of the height of the elbow and the pixel coordinates of the ring weld height of the elbow are respectively converted into world coordinates to obtain the height of the elbow and the ring weld height of the elbow.

[0008] In some embodiments, determining the pipe mouth diameter and the pipe mouth center distance of the elbow according to the upward view image includes: performing distortion correction on the upward view image; locating the features and position of the elbow in the upward view image, and correcting the position of the elbow using preset correction parameters; respectively selecting the inner circle and outer circle ROI areas of the first pipe mouth and the inner circle and outer circle ROI areas of the second pipe mouth of the elbow, and determining the pixel coordinates of the center of the first pipe mouth, the pixel coordinates of the center of the second pipe mouth, and the pixel coordinates of the pipe mouth diameter of the elbow; determining the pixel coordinates of the pipe mouth center distance of the elbow according to the pixel coordinates of the center of the first pipe mouth and the pixel coordinates of the center of the second pipe mouth; respectively converting the pixel coordinates of the pipe mouth diameter of the elbow and the pixel coordinates of the pipe mouth center distance of the elbow into world coordinates to obtain the pipe mouth diameter and the pipe mouth center distance of the elbow.

[0009] In some embodiments, determining whether the elbow is a qualified product or a defective product based on the measurement data includes: respectively judging the size relationship between the height of the elbow and a preset elbow height value, the size relationship between the circumferential weld height of the elbow and a preset circumferential weld height value, the size relationship between the pipe mouth diameter of the elbow and a preset pipe mouth diameter value, and the size relationship between the pipe mouth center distance of the elbow and a preset pipe mouth center distance value; if the absolute value of the difference between the height of the elbow and the preset elbow height value is less than a preset first tolerance, and the absolute value of the difference between the circumferential weld height of the elbow and the preset circumferential weld height value is less than a preset second tolerance, and the pipe mouth diameter of the elbow and the preset pipe mouth diameter value If the absolute value of the difference between the value of the preset third tolerance is less than the preset third tolerance, and the absolute value of the difference between the center distance of the pipe mouth of the elbow and the preset center distance of the pipe mouth is less than the preset fourth tolerance, the elbow is determined to be a qualified product; if the absolute value of the difference between the height of the elbow and the preset elbow height value is greater than or equal to the preset first tolerance, or the absolute value of the difference between the circumferential welding height of the elbow and the preset circumferential welding height value is greater than or equal to the preset second tolerance, or the absolute value of the difference between the pipe mouth diameter of the elbow and the preset pipe mouth diameter value is greater than or equal to the preset third tolerance, or the absolute value of the difference between the pipe mouth center distance of the elbow and the preset pipe mouth center distance value is greater than or equal to the preset fourth tolerance, the elbow is determined to be a defective product.

[0010] In some embodiments, the method further includes: after determining that the elbow is a qualified product, using the measurement data to adjust a preset elbow height value, a preset ring weld height value, a preset pipe mouth diameter value, and a preset pipe mouth center distance value.

[0011] Matching the above method, the present invention provides a screening device for elbows on the other hand, which is provided with a visual system, and the visual system includes: a first camera and a second camera; the first camera is used to collect a side view image of the elbow; the second camera is used to collect an upward view image of the elbow; the device includes: an acquisition unit, configured to acquire the side view image of the elbow collected by the first camera and the upward view image of the elbow collected by the second camera; a determination unit, configured to determine the measurement data of the elbow according to the side view image and the upward view image; the determination unit is also configured to determine whether the elbow is a qualified product or a defective product according to the measurement data.

[0012] In some embodiments, the measurement data includes: the height of the elbow, the circumferential weld height of the elbow, the pipe mouth diameter of the elbow, and the pipe mouth center distance of the elbow; the determination unit determines the measurement data of the elbow according to the side view image and the top view image, including: determining the height of the elbow and the circumferential weld height of the elbow according to the side view image, and determining the pipe mouth diameter of the elbow and the pipe mouth center distance of the elbow according to the top view image.

[0013] In some embodiments, the determination unit determines the height of the elbow and the ring weld height of the elbow according to the side view image, including: performing distortion correction on the side view image; locating the features and position of the elbow in the side view image, and correcting the position of the elbow using preset correction parameters; selecting the bottom ROI area of ​​the elbow to determine the pixel coordinates of the reference straight line at the bottom of the elbow; selecting the top ROI area of ​​the elbow to determine the pixel coordinates of the vertex of the elbow; respectively selecting the left ring weld ROI area and the right ring weld ROI area of ​​the elbow to determine the pixel coordinates of the first point and the second point of the left ring weld, and the pixel coordinates of the first point of the right ring weld; The pixel coordinates of the first and second points of the elbow are obtained; the pixel coordinates of the vertex of the elbow and the pixel coordinates of the reference straight line at the bottom of the elbow are substituted into the preset elbow height calculation formula to obtain the pixel coordinates of the height of the elbow; the pixel coordinates of the first point and the second point of the left ring weld, the pixel coordinates of the first point and the second point of the right ring weld, and the pixel coordinates of the reference straight line at the bottom of the elbow are substituted into the preset ring weld height calculation formula to obtain the pixel coordinates of the ring weld height of the elbow; the pixel coordinates of the height of the elbow and the pixel coordinates of the ring weld height of the elbow are respectively converted into world coordinates to obtain the height of the elbow and the ring weld height of the elbow.

[0014] In some embodiments, the determination unit determines the nozzle diameter and the nozzle center distance of the elbow according to the upward view image, including: performing distortion correction on the upward view image; locating the features and position of the elbow in the upward view image, and correcting the position of the elbow using preset correction parameters; respectively selecting the inner circle and outer circle ROI areas of the first nozzle and the inner circle and outer circle ROI areas of the second nozzle of the elbow, and determining the pixel coordinates of the center of the first nozzle, the pixel coordinates of the center of the second nozzle, and the pixel coordinates of the nozzle diameter of the elbow; determining the pixel coordinates of the nozzle center distance of the elbow according to the pixel coordinates of the first nozzle center and the pixel coordinates of the second nozzle center; respectively converting the pixel coordinates of the nozzle diameter of the elbow and the pixel coordinates of the nozzle center distance of the elbow into world coordinates to obtain the nozzle diameter and the nozzle center distance of the elbow.

[0015] In some embodiments, the determination unit determines whether the elbow is a qualified product or a defective product based on the measurement data, including: respectively judging the size relationship between the height of the elbow and a preset elbow height value, the size relationship between the circumferential weld height of the elbow and a preset circumferential weld height value, the size relationship between the pipe mouth diameter of the elbow and a preset pipe mouth diameter value, and the size relationship between the pipe mouth center distance of the elbow and a preset pipe mouth center distance value; if the absolute value of the difference between the height of the elbow and the preset elbow height value is less than a preset first tolerance, and the absolute value of the difference between the circumferential weld height of the elbow and the preset circumferential weld height value is less than a preset second tolerance, and the pipe mouth diameter of the elbow is less than the preset pipe mouth diameter; If the absolute value of the difference in diameter values ​​is less than the preset third tolerance, and the absolute value of the difference between the pipe mouth center distance of the elbow and the preset pipe mouth center distance value is less than the preset fourth tolerance, the elbow is determined to be a qualified product; if the absolute value of the difference between the height of the elbow and the preset elbow height value is greater than or equal to the preset first tolerance, or the absolute value of the difference between the circumferential weld height of the elbow and the preset circumferential weld height value is greater than or equal to the preset second tolerance, or the absolute value of the difference between the pipe mouth diameter of the elbow and the preset pipe mouth diameter value is greater than or equal to the preset third tolerance, or the absolute value of the difference between the pipe mouth center distance of the elbow and the preset pipe mouth center distance value is greater than or equal to the preset fourth tolerance, the elbow is determined to be a defective product.

[0016] In some embodiments, the determination unit is further configured to adjust the preset elbow height value, the preset ring weld height value, the preset pipe mouth diameter value, and the preset pipe mouth center distance value using the measurement data after determining that the elbow is a qualified product.

[0017] Matching the above-mentioned device, the present invention further provides an elbow screening and classification system, comprising: the above-mentioned elbow screening device.

[0018] In accordance with the above method, the present invention provides a storage medium on another aspect, wherein the storage medium includes a stored program, wherein when the program is executed, the device where the storage medium is located is controlled to execute the above-mentioned elbow screening method.

[0019] In accordance with the above method, the present invention provides a computer program product on another aspect, wherein the computer program product includes a computer program, and when the computer program product is processed and executed, the steps of the above elbow screening method are implemented.

[0020] The solution of the present invention is provided with a visual system, which includes: a first camera and a second camera; the first camera is used to collect a side view image of the elbow; the second camera is used to collect an upward view image of the elbow; the measurement data of the elbow is determined based on the side view image and the upward view image, and the elbow is determined to be a qualified product or a defective product based on the measurement data. Thus, by setting up a visual system to calculate the actual measurement data of the elbow, and judging whether the elbow is a qualified product based on the actual measurement data, automatic classification and screening of elbows is achieved, the efficiency of automated production of air conditioners is improved, defective elbows are prevented from being installed on air conditioners, and the air conditioners are ensured to have high product quality.

[0021] Other features and advantages of the present invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the present invention.

[0022] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 A schematic diagram of a process of an embodiment of a method for screening elbows of the present invention;

[0024] Figure 2 It is a structural schematic diagram of an embodiment of the screening device for elbows of the present invention;

[0025] Figure 3 A top view of the structure of the elbow screening and classification system of the present invention;

[0026] Figure 4 A side view of the structure of the elbow screening and classification system of the present invention;

[0027] Figure 5 is a schematic diagram of the monitoring position of the elbow;

[0028] Figure 6 It is a flowchart of the elbow measurement algorithm;

[0029] Figure 7 Schematic diagram of the elbow screening process.

[0030] In conjunction with the accompanying drawings, the reference numerals in the embodiments of the present invention are as follows:

[0031] 1-elbow; 2-feeding port; 3-rotating disk; 4-classification outlet; 5-laser sensor; 6-rear light source; 7-lower camera; 8-side camera; 9-upper light source; 102-acquisition unit; 104-determination unit. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the specific embodiments of the present invention and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0033] According to an embodiment of the present invention, a method for screening elbows is provided, and a visual system is provided, wherein the visual system comprises: a first camera and a second camera; the first camera is used to capture a side view image of the elbow, such as a side camera 8; the second camera is used to capture an upward view image of the elbow, such as a lower camera 7.

[0034] The visual system Figure 3 and Figure 4 As shown, it includes: a visual controller (not shown in the figure), a laser sensor 5, a side camera 8, a lower camera 7, a rear light source 6, and an upper light source 9. The laser sensor 5 is located upstream of the incoming material and is used to detect whether there is incoming material. Once a bend 1 is detected, a trigger signal is generated, and the distance between the laser sensor 5 and the detected bend 1 is detected, and the trigger signal and distance data are sent to the visual controller. After receiving the trigger signal, the visual controller sends a camera acquisition signal to the side camera 8 and the lower camera 7 at the same time. After receiving the acquisition signal, the side camera 8 acquires the side view image of the bend, and the lower camera 7 acquires the upward view image of the bend after receiving the acquisition signal. The rear light source 6 and the upper light source 9 are used to provide lighting when acquiring the side view image and the upward view image. After that, the side view image and the upward view image are sent to the visual controller to calculate the measurement data of the bend in the image. Among them, the distance detected by the laser sensor 5 is the distance from the plane where the laser sensor 5 and the side camera 8 are located to the plane where the bend is located.

[0035] After the elbow is placed on the counterclockwise rotating rotating disk 3 through the feed port 1, as the rotating disk 3 rotates, when the elbow rotates in front of the laser sensor 5, it is detected by the laser sensor 5, triggering the visual system and calculating the measurement data of the elbow through the collected image. The elbow is judged as a qualified product or a defective product based on the measurement data. When the elbow rotates to the classification discharge port 4 with the rotating disk, the airflow intensity and direction of the blowing organ are controlled to discharge qualified products and defective products from different discharge ports, thereby realizing automatic data measurement, screening and classification of the elbow.

[0036] like Figure 1 The schematic diagram of the flow chart of an embodiment of the method of the present invention is shown. The elbow screening method may include: step S110 to step S130.

[0037] In step S110, a side view image of the elbow captured by the first camera and a bottom view image of the elbow captured by the second camera are acquired.

[0038] In some embodiments, the measurement data includes: the height of the elbow, the circumferential weld height of the elbow, the pipe opening diameter of the elbow, and the pipe opening center distance of the elbow.

[0039] like Figure 5 The side view and bottom view of the elbow shown, the height of the elbow is L, the height of the bend ring weld is H, the diameter of the pipe mouth of the elbow is d, and the distance between the pipe mouth circles of the elbow is P. In addition, p0 is the vertex of the elbow, p1 is the lower edge point on the left side of the left bend ring weld, p2 is the lower edge point on the right side of the left bend ring weld, p3 is the lower edge point on the left side of the right bend ring weld, p4 is the lower edge point on the right side of the right bend ring weld, p5 is the center of the left bend ring weld, p6 is the center of the right bend ring weld, and l1 is the reference straight line at the bottom of the elbow.

[0040] In step S120, measurement data of the elbow is determined according to the side view image and the bottom view image.

[0041] In some embodiments, in step S120, the specific process of determining the measurement data of the elbow according to the side view image and the bottom view image includes: determining the height of the elbow and the circumferential weld height of the elbow according to the side view image, and determining the pipe mouth diameter and the pipe mouth center distance of the elbow according to the bottom view image.

[0042] Before determining the measurement data of the elbow based on the image, it is necessary to calculate the preset correction parameters. Since the measurement data of the elbow obtained by the measurement algorithm in the visual system is pixel coordinates, it needs to be converted into the real value under the world coordinates. This conversion mapping relationship is completed through camera calibration and coordinate conversion. Due to the elbow incoming process, there is a certain amount of distance deviation between the elbow plane and the calibration plane, so it is necessary to correct this distance deviation when determining the measurement data of the elbow based on the image. Therefore, the preset correction parameters are used to correct this distance deviation, that is, the role of the preset correction parameters is to correct the distance deviation between the elbow plane and the calibration plane, so that the measurement data is closer to the physical real value of the elbow.

[0043] The process of calculating the preset correction parameters is as follows: based on the side view image and the top view image, the distance data of the elbow obtained by the laser sensor are integrated, the least squares method is used to minimize the measurement error, and the position of the feature points obtained by image processing is calculated. and laser sensors Measure the distance and find the optimal fusion value The optimal fusion value is the preset correction parameter. The formula for minimizing the sum of squared errors is:

[0044]

[0045] The fusion value of each measurement point is calculated based on the optimal solution a and b obtained by solving the minimum sum of squared errors. The formula is:

[0046]

[0047] Then the optimal fusion value The data is fed back to the visual system to measure the elbow height, ring weld height, pipe mouth diameter, pipe mouth center distance and other data.

[0048] In some embodiments, the specific process of determining the height of the elbow and the height of the circumferential weld of the elbow according to the side view image includes: steps S210 to S280.

[0049] Step S210, performing distortion correction on the side view image.

[0050] Due to the vibration of the rotating disk rail, the plane where the elbow is located may not be in the same plane as the camera calibration plane, and there is a certain distance error. Therefore, it is necessary to integrate the distance data collected by the laser sensor to scale up and crop the image. At the same time, since the position of the elbow in the camera's field of view is not fixed and the camera has a certain degree of distortion, it is necessary to further correct the image coordinates. The distortion correction formula is as follows:

[0051]

[0052] Among them, (x, y) represents the image coordinates before distortion, (x d ,y d ) represents the coordinates of the distorted image, and k1, k2, k3, p1, and p2 represent the distortion coefficients.

[0053] Step S220, locating the features and position of the elbow in the side view image, and correcting the position of the elbow using preset correction parameters.

[0054] Select the template image where the small elbow is located, perform rough feature positioning, determine the approximate position of the elbow in the image, and output the template matching score match_score. At the same time, use the preset correction parameters calculated previously to correct the position of the elbow.

[0055] Step S230, select the bottom ROI area of ​​the elbow and determine the pixel coordinates of the reference straight line at the bottom of the elbow.

[0056] The ROI area at the bottom of the small elbow is selected, and the pixel-level edge information of the image is extracted by the pixel-level edge detection algorithm to complete the rough positioning of the edge point. The pixel-level edge information is subdivided according to the surface fitting method to obtain the sub-pixel edge coordinates to complete the fine positioning of the edge. Finally, the sub-pixel edge point coordinates are iteratively fitted by iterative reweighted least squares straight line fitting, and the detection of the bottom reference line of the elbow is finally completed. The bottom reference line is as follows: Figure 5 The l1 in .

[0057] Step S240, select the top ROI area of ​​the elbow and determine the pixel coordinates of the vertex of the elbow.

[0058] The apex of the elbow is Figure 5 Select the ROI area at the top of the elbow. Place caliper tools with the same angle as the ROI at equal distances in the area. Use the caliper tools to detect sub-pixel edge points in the area and calculate the distance of the edge points relative to the starting point of the ROI. The point with the closest distance is the vertex of the elbow.

[0059] Step S250, respectively select the left ring weld ROI area and the right ring weld ROI area of ​​the elbow, and determine the pixel coordinates of the first point and the second point of the left ring weld, and the pixel coordinates of the first point and the second point of the right ring weld.

[0060] like Figure 5 As shown in the figure, the first and second points of the left ring weld are p1 and p2 respectively, and the first and second points of the right ring weld are p3 and p4 respectively. Select the ROI area of ​​the left and right weld rings of the elbow. In this area, use the edge detection algorithm to detect the lower edge points of the left and right weld rings, and calculate the distance of the edge points relative to the bottom reference line. The point with the closest distance is the lower edge point of the small elbow weld ring.

[0061] Step S260, the pixel coordinates of the vertex of the elbow and the pixel coordinates of the reference straight line at the bottom of the elbow are substituted into a preset elbow height calculation formula to obtain the pixel coordinates of the height of the elbow.

[0062] The calculation formula for elbow height is:

[0063] L=DistancePointLine(p0,l0);

[0064] L is the pixel coordinate of the height of the elbow, p0 is the pixel coordinate of the vertex of the elbow, and l0 is the pixel coordinate of the reference straight line at the bottom of the elbow.

[0065] Step S270, the pixel coordinates of the first point and the second point of the left ring weld, the pixel coordinates of the first point and the second point of the right ring weld, and the pixel coordinates of the reference straight line at the bottom of the elbow are brought into a preset ring weld height calculation formula to obtain the pixel coordinates of the ring weld height of the elbow. The ring weld height calculation formula is:

[0066]

[0067] H is the pixel coordinate of the ring weld height of the elbow, p1 is the pixel coordinate of the first point of the left ring weld, p2 is the pixel coordinate of the second point of the left ring weld, p3 is the pixel coordinate of the first point of the right ring weld, p4 is the pixel coordinate of the second point of the right ring weld, and l0 is the pixel coordinate of the reference straight line at the bottom of the elbow.

[0068] Step S280, converting the pixel coordinates of the height of the elbow and the pixel coordinates of the height of the ring weld of the elbow into world coordinates respectively, to obtain the height of the elbow and the height of the ring weld of the elbow.

[0069] After obtaining the pixel coordinates of the measurement data, the pixel coordinates are converted into world coordinates and output, thereby determining whether the elbow is a qualified product.

[0070] In some embodiments, the specific process of determining the pipe opening diameter of the elbow and the pipe opening center distance of the elbow according to the bottom view image includes: steps S310 to S350.

[0071] Step S310, performing distortion correction on the bottom-view image.

[0072] The process of correcting the distortion of the upward-view image is the same as that of the side-view image, and will not be repeated here.

[0073] Step S320, locating the features and position of the elbow in the bottom-view image, and correcting the position of the elbow using preset correction parameters.

[0074] The manner of locating the features and position of the elbow in the bottom view image is the same as the manner of locating the features and position of the elbow in the side view image, and will not be repeated here.

[0075] Step S330, respectively select the inner circle and outer circle ROI areas of the first pipe mouth of the elbow and the inner circle and outer circle ROI areas of the second pipe mouth, and determine the pixel coordinates of the center of the first pipe mouth, the pixel coordinates of the center of the second pipe mouth, and the pixel coordinates of the pipe mouth diameter of the elbow.

[0076] Step S340, determining the pixel coordinates of the center distance of the pipe opening of the elbow according to the pixel coordinates of the center of the first pipe opening and the pixel coordinates of the center of the second pipe opening.

[0077] like Figure 5 As shown, the center of the first pipe opening is p5, the center of the second pipe opening is p6, and the diameter of the elbow is d. Select the inner and outer circle ROI areas of the small elbow pipe opening, and perform standard circle fitting based on the coordinates of the circle edge points in the selected annular ROI area. The algorithm principle is the same as the elbow bottom reference straight line detection, and only the least squares fitting method is different. The circle equation is as follows:

[0078] (x) 2 +(yb) 2 =r 2 ;

[0079] The calculation formula for minimizing the least squares circle fitting is:

[0080]

[0081] Where r is the radius of the pipe orifice, and the pipe orifice diameter d = 2r. The calculation formula for the center distance P is:

[0082] P=DistancePointPoint(p5,p6);

[0083] p5 is the pixel coordinate of the center of the first nozzle, and p6 is the pixel coordinate of the center of the second nozzle.

[0084] Step S350, converting the pixel coordinates of the pipe opening diameter of the elbow and the pixel coordinates of the pipe opening circle center distance of the elbow into world coordinates respectively, to obtain the pipe opening diameter of the elbow and the pipe opening circle center distance of the elbow.

[0085] The rotation matrix, translation vector, camera intrinsic parameter matrix, distortion coefficient, etc. calculated by the camera calibration algorithm are used to convert the measurement data under the pixel coordinates measured by the visual measurement algorithm into real physical world values.

[0086] By fusing laser sensor data with image data and adopting a method combining intelligent sensing technology with high-resolution image processing technology, real-time online measurement of the true value of the elbow size on the assembly line can be achieved.

[0087] Figure 6 The schematic diagram of the elbow measurement algorithm is shown in Figure 2. Figure 6 As shown, the method includes:

[0088] Step 1: After the glass turntable is loaded, when the laser sensor detects the elbow, the side camera and the lower camera are triggered to take pictures to obtain the side view image and the top view image.

[0089] Step 2, for the side view image, perform distortion correction on the side view image; select the elbow ROI area, perform template matching, perform feature coarse positioning, determine the approximate position of the elbow in the image, and perform position correction; select the ROI area at the bottom of the elbow nozzle, detect the bottom reference straight line of the elbow; select the ROI area at the top of the elbow, detect the top of the elbow, and calculate the elbow height L; select the ROI area of ​​the left and right welding rings, detect the lower edge of the welding ring, and calculate the height H of the welding ring; convert the pixel coordinates of the elbow height L and the welding ring height H into world coordinates, and output the world coordinates of the elbow height L and the welding ring height H.

[0090] Step 3, for the upward-looking image, perform distortion correction on the upward-looking image; select the elbow ROI area, perform template matching, perform feature coarse positioning, determine the approximate position of the elbow in the image, and perform position correction; select the original ROI area inside and outside the pipe mouth, detect the pipe mouth circle, calculate the left and right pipe mouth diameters d, determine the coordinates of the left and right pipe mouth centers, and calculate the pipe mouth center distance P; convert the pixel coordinates of the left and right pipe mouth diameters d and the pipe mouth center distance P into world coordinates, and output the world coordinates of the left and right pipe mouth diameters d and the pipe mouth center distance P.

[0091] In step S130, it is determined whether the elbow is a qualified product or a defective product according to the measurement data.

[0092] This solution calculates the actual measurement data of the elbow by setting up a visual system, and determines whether the elbow is qualified based on the actual measurement data, thereby realizing automatic classification and screening of elbows. This eliminates the need for manual switching of projects, reduces human intervention, improves the efficiency of automated production of air conditioners, prevents defective elbows from being installed on air conditioners, and ensures that the air conditioners have high product quality.

[0093] In some embodiments, in step S130, the specific process of determining whether the elbow is a qualified product or a defective product based on the measurement data includes: respectively judging the size relationship between the height of the elbow and a preset elbow height value, the size relationship between the circumferential weld height of the elbow and a preset circumferential weld height value, the size relationship between the pipe mouth diameter of the elbow and a preset pipe mouth diameter value, and the size relationship between the pipe mouth center distance of the elbow and a preset pipe mouth center distance value; if the absolute value of the difference between the height of the elbow and the preset elbow height value is less than a preset first tolerance, and the absolute value of the difference between the circumferential weld height of the elbow and the preset circumferential weld height value is less than a preset second tolerance, and the pipe mouth diameter of the elbow is less than a preset Assuming that the absolute value of the difference in the pipe mouth diameter values ​​is less than the preset third tolerance, and the absolute value of the difference between the pipe mouth center distance of the elbow and the preset pipe mouth center distance value is less than the preset fourth tolerance, the elbow is determined to be a qualified product; if the absolute value of the difference between the height of the elbow and the preset elbow height value is greater than or equal to the preset first tolerance, or the absolute value of the difference between the circumferential welding height of the elbow and the preset circumferential welding height value is greater than or equal to the preset second tolerance, or the absolute value of the difference between the pipe mouth diameter of the elbow and the preset pipe mouth diameter value is greater than or equal to the preset third tolerance, or the absolute value of the difference between the pipe mouth center distance of the elbow and the preset pipe mouth center distance value is greater than or equal to the preset fourth tolerance, the elbow is determined to be a defective product.

[0094] The current small elbow is matched with the five standard template elbows respectively, and the elbow model is distinguished according to the score. The higher the score, the more matching the elbow model. Specifically, the current elbow measurement value is compared with the preset elbow standard value to determine whether the elbow height is less than the tolerance value, whether the left and right weld rings of the elbow are missing, whether the height of the left and right outer weld rings is less than the tolerance, whether the pipe diameter is less than the tolerance, and whether the pipe center distance is less than the tolerance. If all the requirements are met, the current elbow is qualified and its measurement value is recorded; otherwise, the current elbow is defective and is ready for discarding.

[0095] In some embodiments, the method further includes: after determining that the elbow is a qualified product, using the measurement data to adjust a preset elbow height value, a preset ring weld height value, a preset pipe mouth diameter value, and a preset pipe mouth center distance value.

[0096] Due to differences in manufacturing processes, there is a certain amount of difference between the actual value distribution of each batch of elbow materials and the standard value of the drawing. Therefore, the mean and standard deviation of the cumulative measurement parameters (including elbow height, welding ring height, pipe mouth diameter, and pipe mouth center distance) of the current elbow model are calculated, and the Shapiro-Wilk test is used to test whether the cumulative measurement data conforms to the normal distribution. According to the results, real-time feedback is given and the standard value and qualified range of the screening parameters for each batch of elbows are dynamically adjusted.

[0097] By adaptively adjusting the screening parameter standards and qualified range according to the real-time measurement results, the differences in materials in different batches can be adapted, and the qualified and defective small elbows can be reasonably separated according to the size and shape of different models, so that the small elbow materials can be screened and classified more efficiently and intelligently.

[0098] Figure 7 The schematic diagram of the elbow screening process is as follows: Figure 7 As shown, the method includes:

[0099] Step 11, input the measured value of the elbow and initialize the standard value of the elbow.

[0100] Step 12, when there is no missing welding ring, and the absolute value of the difference between the elbow height, elbow welding ring, left and right welding ring heights, pipe mouth diameter, and pipe mouth center distance and the standard value is less than the tolerance, the elbow is qualified. At the same time, the average value and standard deviation of the cumulative measurement parameters of the current model elbow are calculated based on the measured value of the elbow, and the standard value of the elbow is dynamically adjusted.

[0101] Step 13, when the welding ring is missing, or the absolute value of the difference between the elbow height, elbow welding ring, left and right welding ring heights, pipe mouth diameter, and pipe mouth center distance and the standard value is greater than the tolerance, the elbow is a defective product and the elbow is discarded.

[0102] The technical solution of this embodiment is adopted, and a visual system is provided, which includes: a first camera and a second camera; the first camera is used to collect the side view image of the elbow; the second camera is used to collect the upward view image of the elbow; the measurement data of the elbow is determined according to the side view image and the upward view image, and the elbow is determined to be a qualified product or a defective product according to the measurement data. Thus, by setting up a visual system to calculate the actual measurement data of the elbow, and judging whether the elbow is a qualified product according to the actual measurement data, automatic classification and screening of elbows is realized, the efficiency of automated production of air conditioners is improved, defective elbows are prevented from being installed on air conditioners, and the air conditioners are ensured to have high product quality.

[0103] According to an embodiment of the present invention, a device for screening elbows corresponding to the method for screening elbows is also provided. A visual system is provided, and the visual system includes: a first camera and a second camera; the first camera is used to collect a side view image of the elbow, such as a side camera 8; the second camera is used to collect an upward view image of the elbow, such as a lower camera 7.

[0104] The visual system Figure 3 and Figure 4As shown, it includes: a visual controller (not shown in the figure), a laser sensor 5, a side camera 8, a lower camera 7, a rear light source 6, and an upper light source 9. The laser sensor 5 is located upstream of the incoming material and is used to detect whether there is incoming material. Once a bend 1 is detected, a trigger signal is generated, and the distance between the laser sensor 5 and the detected bend 1 is detected, and the trigger signal and distance data are sent to the visual controller. After receiving the trigger signal, the visual controller sends a camera acquisition signal to the side camera 8 and the lower camera 7 at the same time. After receiving the acquisition signal, the side camera 8 acquires the side view image of the bend, and the lower camera 7 acquires the upward view image of the bend after receiving the acquisition signal. The rear light source 6 and the upper light source 9 are used to provide lighting when acquiring the side view image and the upward view image. After that, the side view image and the upward view image are sent to the visual controller to calculate the measurement data of the bend in the image. Among them, the distance detected by the laser sensor 5 is the distance from the plane where the laser sensor 5 and the side camera 8 are located to the plane where the bend is located.

[0105] After the elbow is placed on the counterclockwise rotating rotating disk 3 through the feed port 1, as the rotating disk 3 rotates, when the elbow rotates in front of the laser sensor 5, it is detected by the laser sensor 5, triggering the visual system and calculating the measurement data of the elbow through the collected image. The elbow is judged as a qualified product or a defective product based on the measurement data. When the elbow rotates to the classification discharge port 4 with the rotating disk, the airflow intensity and direction of the blowing organ are controlled to discharge qualified products and defective products from different discharge ports, thereby realizing automatic data measurement, screening and classification of the elbow.

[0106] See also Figure 2 The structure diagram of an embodiment of the device of the present invention is shown in FIG. The elbow screening device may include: an acquisition unit 102 and a determination unit 104 .

[0107] The acquisition unit 102 is configured to acquire the side view image of the elbow acquired by the first camera and the bottom view image of the elbow acquired by the second camera. The specific functions and processing of the acquisition unit 102 refer to step S110.

[0108] In some embodiments, the measurement data includes: the height of the elbow, the circumferential weld height of the elbow, the pipe opening diameter of the elbow, and the pipe opening center distance of the elbow.

[0109] like Figure 5 The side view and bottom view of the elbow shown, the height of the elbow is L, the height of the bend ring weld is H, the diameter of the pipe mouth of the elbow is d, and the distance between the pipe mouth circles of the elbow is P. In addition, p0 is the vertex of the elbow, p1 is the lower edge point on the left side of the left bend ring weld, p2 is the lower edge point on the right side of the left bend ring weld, p3 is the lower edge point on the left side of the right bend ring weld, p4 is the lower edge point on the right side of the right bend ring weld, p5 is the center of the left bend ring weld, p6 is the center of the right bend ring weld, and l1 is the reference straight line at the bottom of the elbow.

[0110] The determination unit 104 is configured to determine the measurement data of the elbow according to the side view image and the bottom view image. The specific functions and processing of the determination unit 104 refer to step S120.

[0111] In some embodiments, the determination unit 104 determines the specific process of measuring the data of the elbow according to the side view image and the bottom view image, including: determining the height of the elbow and the circumferential weld height of the elbow according to the side view image, and determining the pipe mouth diameter and the pipe mouth center distance of the elbow according to the bottom view image.

[0112] Before determining the measurement data of the elbow based on the image, it is necessary to calculate the preset correction parameters. Since the measurement data of the elbow obtained by the measurement algorithm in the visual system is pixel coordinates, it needs to be converted into the real value under the world coordinates. This conversion mapping relationship is completed through camera calibration and coordinate conversion. Due to the elbow incoming process, there is a certain amount of distance deviation between the elbow plane and the calibration plane, so it is necessary to correct this distance deviation when determining the measurement data of the elbow based on the image. Therefore, the preset correction parameters are used to correct this distance deviation, that is, the role of the preset correction parameters is to correct the distance deviation between the elbow plane and the calibration plane, so that the measurement data is closer to the physical real value of the elbow.

[0113] The process of calculating the preset correction parameters is as follows: based on the side view image and the top view image, the distance data of the elbow obtained by the laser sensor are integrated, the least squares method is used to minimize the measurement error, and the position of the feature points obtained by image processing is calculated. and laser sensors Measure the distance and find the optimal fusion value The optimal fusion value is the preset correction parameter. The formula for minimizing the sum of squared errors is:

[0114]

[0115] The fusion value of each measurement point is calculated based on the optimal solution a and b obtained by solving the minimum sum of squared errors. The formula is:

[0116]

[0117] Then the optimal fusion value The data is fed back to the visual system to measure the elbow height, ring weld height, pipe mouth diameter, pipe mouth center distance and other data.

[0118] In some implementations, the specific process of the determination unit 104 determining the height of the elbow and the height of the ring weld of the elbow according to the side view image includes:

[0119] The determination unit 104 is further configured to perform distortion correction on the side view image.

[0120] Due to the vibration of the rotating disk rail, the plane where the elbow is located may not be in the same plane as the camera calibration plane, and there is a certain distance error. Therefore, it is necessary to integrate the distance data collected by the laser sensor to scale up and crop the image. At the same time, since the position of the elbow in the camera's field of view is not fixed and the camera has a certain degree of distortion, it is necessary to further correct the image coordinates. The distortion correction formula is as follows:

[0121]

[0122] Among them, (x, y) represents the image coordinates before distortion, (x d ,y d ) represents the coordinates of the distorted image, and k1, k2, k3, p1, and p2 represent the distortion coefficients.

[0123] The determination unit 104 is further specifically configured to locate the features and position of the elbow in the side view image, and to correct the position of the elbow using preset correction parameters.

[0124] Select the template image where the small elbow is located, perform rough feature positioning, determine the approximate position of the elbow in the image, and output the template matching score match_score. At the same time, use the preset correction parameters calculated previously to correct the position of the elbow.

[0125] The determination unit 104 is further configured to select the bottom ROI area of ​​the elbow and determine the pixel coordinates of the reference straight line at the bottom of the elbow.

[0126] The ROI area at the bottom of the small elbow is selected, and the pixel-level edge information of the image is extracted by the pixel-level edge detection algorithm to complete the rough positioning of the edge point. The pixel-level edge information is subdivided according to the surface fitting method to obtain the sub-pixel edge coordinates to complete the fine positioning of the edge. Finally, the sub-pixel edge point coordinates are iteratively fitted by iterative reweighted least squares straight line fitting, and the detection of the bottom reference line of the elbow is finally completed. The bottom reference line is as follows: Figure 5 The l1 in .

[0127] The determination unit 104 is further configured to select the top ROI area of ​​the elbow and determine the pixel coordinates of the vertex of the elbow.

[0128] The apex of the elbow is Figure 5Select the ROI area at the top of the elbow. Place caliper tools with the same angle as the ROI at equal distances in the area. Use the caliper tools to detect sub-pixel edge points in the area and calculate the distance of the edge points relative to the starting point of the ROI. The point with the closest distance is the vertex of the elbow.

[0129] The determination unit 104 is specifically configured to respectively select the left ring weld ROI area and the right ring weld ROI area of ​​the elbow, and determine the pixel coordinates of the first point and the second point of the left ring weld, and the pixel coordinates of the first point and the second point of the right ring weld.

[0130] like Figure 5 As shown in the figure, the first and second points of the left ring weld are p1 and p2 respectively, and the first and second points of the right ring weld are p3 and p4 respectively. Select the ROI area of ​​the left and right weld rings of the elbow. In this area, use the edge detection algorithm to detect the lower edge points of the left and right weld rings, and calculate the distance of the edge points relative to the bottom reference line. The point with the closest distance is the lower edge point of the small elbow weld ring.

[0131] The determination unit 104 is further specifically configured to substitute the pixel coordinates of the vertex of the elbow and the pixel coordinates of the reference straight line at the bottom of the elbow into a preset elbow height calculation formula to obtain the pixel coordinates of the height of the elbow.

[0132] The calculation formula for elbow height is:

[0133] L=DistancePointLine(p0,l0);

[0134] L is the pixel coordinate of the height of the elbow, p0 is the pixel coordinate of the vertex of the elbow, and l0 is the pixel coordinate of the reference straight line at the bottom of the elbow.

[0135] The determination unit 104 is further configured to bring the pixel coordinates of the first point and the second point of the left ring weld, the pixel coordinates of the first point and the second point of the right ring weld, and the pixel coordinates of the reference straight line at the bottom of the elbow into a preset ring weld height calculation formula to obtain the pixel coordinates of the ring weld height of the elbow. The ring weld height calculation formula is:

[0136]

[0137] H is the pixel coordinate of the ring weld height of the elbow, p1 is the pixel coordinate of the first point of the left ring weld, p2 is the pixel coordinate of the second point of the left ring weld, p3 is the pixel coordinate of the first point of the right ring weld, p4 is the pixel coordinate of the second point of the right ring weld, and l0 is the pixel coordinate of the reference straight line at the bottom of the elbow.

[0138] The determination unit 104 is further specifically configured to convert the pixel coordinates of the height of the elbow and the pixel coordinates of the height of the ring weld of the elbow into world coordinates respectively, so as to obtain the height of the elbow and the height of the ring weld of the elbow.

[0139] After obtaining the pixel coordinates of the measurement data, the pixel coordinates are converted into world coordinates and output, thereby determining whether the elbow is a qualified product.

[0140] In some implementations, the specific process of the determination unit 104 determining the pipe opening diameter of the elbow and the pipe opening center distance of the elbow according to the bottom view image includes:

[0141] The determination unit 104 is further configured to perform distortion correction on the bottom-view image.

[0142] The process of correcting the distortion of the upward-view image is the same as that of the side-view image, and will not be repeated here.

[0143] The determination unit 104 is further configured to locate the features and position of the elbow in the bottom-view image, and to correct the position of the elbow using preset correction parameters.

[0144] The manner of locating the features and position of the elbow in the bottom view image is the same as the manner of locating the features and position of the elbow in the side view image, and will not be repeated here.

[0145] The determination unit 104 is specifically configured to respectively select the inner circle and outer circle ROI areas of the first pipe mouth and the inner circle and outer circle ROI areas of the second pipe mouth, and determine the pixel coordinates of the center of the first pipe mouth, the pixel coordinates of the center of the second pipe mouth, and the pixel coordinates of the pipe mouth diameter of the elbow.

[0146] The determination unit 104 is further specifically configured to determine the pixel coordinates of the pipe opening center distance of the elbow according to the pixel coordinates of the first pipe opening center and the pixel coordinates of the second pipe opening center.

[0147] like Figure 5 As shown, the center of the first pipe opening is p5, the center of the second pipe opening is p6, and the diameter of the elbow is d. Select the inner and outer circle ROI areas of the small elbow pipe opening, and perform standard circle fitting based on the coordinates of the circle edge points in the selected annular ROI area. The algorithm principle is the same as the elbow bottom reference straight line detection, and only the least squares fitting method is different. The circle equation is as follows:

[0148] (x) 2 +(yb) 2 =r 2 ;

[0149] The calculation formula for minimizing the least squares circle fitting is:

[0150]

[0151] Where r is the radius of the pipe orifice, and the pipe orifice diameter d = 2r. The calculation formula for the center distance P is:

[0152] P=DistancePointPoint(p5,p6);

[0153] p5 is the pixel coordinate of the center of the first nozzle, and p6 is the pixel coordinate of the center of the second nozzle.

[0154] The determination unit 104 is further specifically configured to convert the pixel coordinates of the pipe mouth diameter of the elbow and the pixel coordinates of the pipe mouth center distance of the elbow into world coordinates respectively, so as to obtain the pipe mouth diameter of the elbow and the pipe mouth center distance of the elbow.

[0155] The rotation matrix, translation vector, camera intrinsic parameter matrix, distortion coefficient, etc. calculated by the camera calibration algorithm are used to convert the measurement data under the pixel coordinates measured by the visual measurement algorithm into real physical world values.

[0156] By fusing laser sensor data with image data and adopting a method combining intelligent sensing technology with high-resolution image processing technology, real-time online measurement of the true value of the elbow size on the assembly line can be achieved.

[0157] Figure 6 The schematic diagram of the elbow measurement algorithm is shown in Figure 2. Figure 6 As shown, the method includes:

[0158] Step 1: After the glass turntable is loaded, when the laser sensor detects the elbow, the side camera and the lower camera are triggered to take pictures to obtain the side view image and the top view image.

[0159] Step 2, for the side view image, perform distortion correction on the side view image; select the elbow ROI area, perform template matching, perform feature coarse positioning, determine the approximate position of the elbow in the image, and perform position correction; select the ROI area at the bottom of the elbow nozzle, detect the bottom reference straight line of the elbow; select the ROI area at the top of the elbow, detect the top of the elbow, and calculate the elbow height L; select the ROI area of ​​the left and right welding rings, detect the lower edge of the welding ring, and calculate the height H of the welding ring; convert the pixel coordinates of the elbow height L and the welding ring height H into world coordinates, and output the world coordinates of the elbow height L and the welding ring height H.

[0160] Step 3, for the upward-looking image, perform distortion correction on the upward-looking image; select the elbow ROI area, perform template matching, perform feature coarse positioning, determine the approximate position of the elbow in the image, and perform position correction; select the original ROI area inside and outside the pipe mouth, detect the pipe mouth circle, calculate the left and right pipe mouth diameters d, determine the coordinates of the left and right pipe mouth centers, and calculate the pipe mouth center distance P; convert the pixel coordinates of the left and right pipe mouth diameters d and the pipe mouth center distance P into world coordinates, and output the world coordinates of the left and right pipe mouth diameters d and the pipe mouth center distance P.

[0161] The determination unit 104 is further configured to determine whether the elbow is a qualified product or a defective product according to the measurement data. The specific functions and processing of the determination unit 104 refer to step S130.

[0162] This solution calculates the actual measurement data of the elbow by setting up a visual system, and determines whether the elbow is qualified based on the actual measurement data, thereby realizing automatic classification and screening of elbows. This eliminates the need for manual switching of projects, reduces human intervention, improves the efficiency of automated production of air conditioners, prevents defective elbows from being installed on air conditioners, and ensures that the air conditioners have high product quality.

[0163] In some embodiments, the determination unit 104 determines the specific process of whether the elbow is a qualified product or a defective product based on the measurement data, including: respectively judging the size relationship between the height of the elbow and a preset elbow height value, the size relationship between the circumferential weld height of the elbow and the preset circumferential weld height value, the size relationship between the pipe mouth diameter of the elbow and the preset pipe mouth diameter value, and the size relationship between the pipe mouth center distance of the elbow and the preset pipe mouth center distance value; if the absolute value of the difference between the height of the elbow and the preset elbow height value is less than the preset first tolerance, and the absolute value of the difference between the circumferential weld height of the elbow and the preset circumferential weld height value is less than the preset second tolerance, and the pipe mouth diameter of the elbow is less than the preset Assuming that the absolute value of the difference in the pipe mouth diameter values ​​is less than the preset third tolerance, and the absolute value of the difference between the pipe mouth center distance of the elbow and the preset pipe mouth center distance value is less than the preset fourth tolerance, the elbow is determined to be a qualified product; if the absolute value of the difference between the height of the elbow and the preset elbow height value is greater than or equal to the preset first tolerance, or the absolute value of the difference between the circumferential welding height of the elbow and the preset circumferential welding height value is greater than or equal to the preset second tolerance, or the absolute value of the difference between the pipe mouth diameter of the elbow and the preset pipe mouth diameter value is greater than or equal to the preset third tolerance, or the absolute value of the difference between the pipe mouth center distance of the elbow and the preset pipe mouth center distance value is greater than or equal to the preset fourth tolerance, the elbow is determined to be a defective product.

[0164] The current small elbow is matched with the five standard template elbows respectively, and the elbow model is distinguished according to the score. The higher the score, the more matching the elbow model. Specifically, the current elbow measurement value is compared with the preset elbow standard value to determine whether the elbow height is less than the tolerance value, whether the left and right weld rings of the elbow are missing, whether the height of the left and right outer weld rings is less than the tolerance, whether the pipe diameter is less than the tolerance, and whether the pipe center distance is less than the tolerance. If all the requirements are met, the current elbow is qualified and its measurement value is recorded; otherwise, the current elbow is defective and is ready for discarding.

[0165] In some embodiments, the determination unit 104 is further configured to adjust the preset elbow height value, the preset ring weld height value, the preset pipe mouth diameter value, and the preset pipe mouth center distance value using the measurement data after determining that the elbow is a qualified product.

[0166] Due to differences in manufacturing processes, there is a certain amount of difference between the actual value distribution of each batch of elbow materials and the standard value of the drawing. Therefore, the mean and standard deviation of the cumulative measurement parameters (including elbow height, welding ring height, pipe mouth diameter, and pipe mouth center distance) of the current elbow model are calculated, and the Shapiro-Wilk test is used to test whether the cumulative measurement data conforms to the normal distribution. According to the results, real-time feedback is given and the standard value and qualified range of the screening parameters for each batch of elbows are dynamically adjusted.

[0167] By adaptively adjusting the screening parameter standards and qualified range according to the real-time measurement results, the differences in materials in different batches can be adapted, and the qualified and defective small elbows can be reasonably separated according to the size and shape of different models, so that the small elbow materials can be screened and classified more efficiently and intelligently.

[0168] Figure 7 The schematic diagram of the elbow screening process is as follows: Figure 7 As shown, the method includes:

[0169] Step 11, input the measured value of the elbow and initialize the standard value of the elbow.

[0170] Step 12, when there is no missing welding ring, and the absolute value of the difference between the elbow height, elbow welding ring, left and right welding ring heights, pipe mouth diameter, and pipe mouth center distance and the standard value is less than the tolerance, the elbow is qualified. At the same time, the average value and standard deviation of the cumulative measurement parameters of the current model elbow are calculated based on the measured value of the elbow, and the standard value of the elbow is dynamically adjusted.

[0171] Step 13, when the welding ring is missing, or the absolute value of the difference between the elbow height, elbow welding ring, left and right welding ring heights, pipe mouth diameter, and pipe mouth center distance and the standard value is greater than the tolerance, the elbow is a defective product and the elbow is discarded.

[0172] Since the processing and functions implemented by the device of this embodiment basically correspond to the embodiments, principles and examples of the aforementioned method, for the details not fully described in this embodiment, please refer to the relevant descriptions in the aforementioned embodiments, and no further elaboration will be made here.

[0173] The technical solution of the present invention is adopted, and a visual system is provided, and the visual system includes: a first camera and a second camera; the first camera is used to collect the side view image of the elbow; the second camera is used to collect the upward view image of the elbow; the measurement data of the elbow is determined according to the side view image and the upward view image, and the elbow is determined to be a qualified product or a defective product according to the measurement data. Thus, by setting up a visual system to calculate the actual measurement data of the elbow, and judging whether the elbow is a qualified product according to the actual measurement data, automatic classification and screening of elbows is realized, the efficiency of automated production of air conditioners is improved, defective elbows are prevented from being installed on air conditioners, and the air conditioners are ensured to have high product quality.

[0174] According to an embodiment of the present invention, a bend screening and classification system corresponding to the bend screening device is also provided. The bend screening and classification system may include: the bend screening device described above.

[0175] Since the processing and functions implemented by the elbow screening and classification system of this embodiment basically correspond to the embodiments, principles and examples of the aforementioned device, for the details not exhaustive in the description of this embodiment, please refer to the relevant descriptions in the aforementioned embodiments and will not be repeated here.

[0176] The technical solution of the present invention is adopted, and a visual system is provided, and the visual system includes: a first camera and a second camera; the first camera is used to collect the side view image of the elbow; the second camera is used to collect the upward view image of the elbow; the measurement data of the elbow is determined according to the side view image and the upward view image, and the elbow is determined to be a qualified product or a defective product according to the measurement data. Thus, by setting up a visual system to calculate the actual measurement data of the elbow, and judging whether the elbow is a qualified product according to the actual measurement data, automatic classification and screening of elbows is realized, the efficiency of automated production of air conditioners is improved, defective elbows are prevented from being installed on air conditioners, and the air conditioners are ensured to have high product quality.

[0177] According to an embodiment of the present invention, a storage medium corresponding to the elbow screening method is also provided, wherein the storage medium includes a stored program, wherein when the program is run, the device where the storage medium is located is controlled to execute the elbow screening method described above.

[0178] Since the processing and functions implemented by the storage medium of this embodiment basically correspond to the embodiments, principles and examples of the aforementioned method, for the details not fully described in this embodiment, please refer to the relevant descriptions in the aforementioned embodiments, and no further elaboration will be made here.

[0179] The technical solution of the present invention is adopted, and a visual system is provided, and the visual system includes: a first camera and a second camera; the first camera is used to collect the side view image of the elbow; the second camera is used to collect the upward view image of the elbow; the measurement data of the elbow is determined according to the side view image and the upward view image, and the elbow is determined to be a qualified product or a defective product according to the measurement data. Thus, by setting up a visual system to calculate the actual measurement data of the elbow, and judging whether the elbow is a qualified product according to the actual measurement data, automatic classification and screening of elbows is realized, the efficiency of automated production of air conditioners is improved, defective elbows are prevented from being installed on air conditioners, and the air conditioners are ensured to have high product quality.

[0180] According to an embodiment of the present invention, a computer program product corresponding to the elbow screening method is also provided, wherein the computer program product comprises a computer program, and when the computer program product is processed and executed, the steps of the elbow screening method are implemented.

[0181] Since the processing and functions implemented by the computer program product of this embodiment basically correspond to the embodiments, principles and examples of the aforementioned method, for the details not fully described in this embodiment, please refer to the relevant descriptions in the aforementioned embodiments and will not be repeated here.

[0182] The technical solution of the present invention is adopted, and a visual system is provided, and the visual system includes: a first camera and a second camera; the first camera is used to collect the side view image of the elbow; the second camera is used to collect the upward view image of the elbow; the measurement data of the elbow is determined according to the side view image and the upward view image, and the elbow is determined to be a qualified product or a defective product according to the measurement data. Thus, by setting up a visual system to calculate the actual measurement data of the elbow, and judging whether the elbow is a qualified product according to the actual measurement data, automatic classification and screening of elbows is realized, the efficiency of automated production of air conditioners is improved, defective elbows are prevented from being installed on air conditioners, and the air conditioners are ensured to have high product quality.

[0183] In summary, it is easy for those skilled in the art to understand that, under the premise of no conflict, the above-mentioned advantageous methods can be freely combined and superimposed.

[0184] The above description is only an embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention shall be included in the scope of the claims of the present invention.

Claims

1. A method for screening elbows, characterized in that: A visual system is provided, and the visual system includes: a first camera and a second camera; the first camera is used to collect a side view image of the elbow; the second camera is used to collect a bottom view image of the elbow; The method comprises: Acquire a side view image of the elbow acquired by the first camera and a bottom view image of the elbow acquired by the second camera; Determining measurement data of the elbow according to the side view image and the bottom view image; The elbow is determined to be a qualified product or a defective product according to the measurement data.

2. The elbow screening method according to claim 1, characterized in that: The measurement data include: the height of the elbow, the circumferential welding height of the elbow, the pipe opening diameter of the elbow, and the pipe opening center distance of the elbow; Determining measurement data of the elbow according to the side view image and the bottom view image includes: The height of the elbow and the circumferential welding height of the elbow are determined according to the side view image, and the pipe opening diameter of the elbow and the pipe opening center distance of the elbow are determined according to the bottom view image.

3. The elbow screening method according to claim 2, characterized in that: Determining the height of the elbow and the height of the circumferential welding of the elbow according to the side view image includes: Performing distortion correction on the side view image; In the side view image, locate the features and position of the elbow, and correct the position of the elbow using preset correction parameters; Select the bottom ROI area of ​​the elbow and determine the pixel coordinates of the reference straight line at the bottom of the elbow; Select the top ROI area of ​​the elbow and determine the pixel coordinates of the vertex of the elbow; Select the left ring weld ROI area and the right ring weld ROI area of ​​the elbow respectively, and determine the pixel coordinates of the first point and the second point of the left ring weld, and the pixel coordinates of the first point and the second point of the right ring weld; Substituting the pixel coordinates of the vertex of the elbow and the pixel coordinates of the reference straight line at the bottom of the elbow into a preset elbow height calculation formula to obtain the pixel coordinates of the height of the elbow; Substitute the pixel coordinates of the first point and the second point of the left ring weld, the pixel coordinates of the first point and the second point of the right ring weld, and the pixel coordinates of the reference straight line at the bottom of the elbow into a preset ring weld height calculation formula to obtain the pixel coordinates of the ring weld height of the elbow; The pixel coordinates of the height of the elbow and the pixel coordinates of the height of the ring weld of the elbow are respectively converted into world coordinates to obtain the height of the elbow and the height of the ring weld of the elbow.

4. The elbow screening method according to claim 2, characterized in that: Determining the pipe opening diameter of the elbow and the pipe opening center distance of the elbow according to the bottom view image includes: Performing distortion correction on the bottom-view image; In the bottom-view image, locate the features and position of the elbow, and correct the position of the elbow using preset correction parameters; Select the inner circle and outer circle ROI areas of the first pipe opening and the inner circle and outer circle ROI areas of the second pipe opening respectively, and determine the pixel coordinates of the center of the first pipe opening, the pixel coordinates of the center of the second pipe opening, and the pixel coordinates of the pipe opening diameter of the elbow; Determine the pixel coordinates of the center distance of the pipe opening of the elbow according to the pixel coordinates of the center of the first pipe opening and the pixel coordinates of the center of the second pipe opening; The pixel coordinates of the pipe orifice diameter of the elbow and the pixel coordinates of the pipe orifice circle center distance of the elbow are respectively converted into world coordinates to obtain the pipe orifice diameter of the elbow and the pipe orifice circle center distance of the elbow.

5. The elbow screening method according to claim 2, characterized in that: Determining whether the elbow is a qualified product or a defective product according to the measurement data includes: Respectively determine the size relationship between the height of the elbow and the preset elbow height value, the size relationship between the girth weld height of the elbow and the preset girth weld height value, the size relationship between the pipe orifice diameter of the elbow and the preset pipe orifice diameter value, and the size relationship between the pipe orifice center distance of the elbow and the preset pipe orifice center distance value; If the absolute value of the difference between the height of the elbow and the preset elbow height value is less than the preset first tolerance, and the absolute value of the difference between the circumferential welding height of the elbow and the preset circumferential welding height value is less than the preset second tolerance, and the absolute value of the difference between the pipe orifice diameter of the elbow and the preset pipe orifice diameter value is less than the preset third tolerance, and the absolute value of the difference between the pipe orifice center distance of the elbow and the preset pipe orifice center distance value is less than the preset fourth tolerance, then the elbow is determined to be a qualified product; If the absolute value of the difference between the height of the elbow and the preset elbow height value is greater than or equal to the preset first tolerance, or the absolute value of the difference between the circumferential weld height of the elbow and the preset circumferential weld height value is greater than or equal to the preset second tolerance, or the absolute value of the difference between the pipe mouth diameter of the elbow and the preset pipe mouth diameter value is greater than or equal to the preset third tolerance, or the absolute value of the difference between the pipe mouth center distance of the elbow and the preset pipe mouth center distance value is greater than or equal to the preset fourth tolerance, then the elbow is determined to be a defective product.

6. The elbow screening method according to claim 5, characterized in that: Also includes: After determining that the elbow is a qualified product, the preset elbow height value, the preset ring weld height value, the preset pipe mouth diameter value, and the preset pipe mouth center distance value are adjusted using the measurement data.

7. A screening device for elbows, characterized in that: A visual system is provided, and the visual system includes: a first camera and a second camera; the first camera is used to collect a side view image of the elbow; the second camera is used to collect a bottom view image of the elbow; The device comprises: an acquisition unit, configured to acquire a side view image of the elbow acquired by the first camera and a bottom view image of the elbow acquired by the second camera; a determination unit configured to determine measurement data of the elbow according to the side view image and the bottom view image; The determination unit is further configured to determine whether the elbow is a qualified product or a defective product based on the measurement data.

8. An elbow screening and sorting system, characterized in that: include: The screening device for elbows as claimed in claim 7.

9. A storage medium, characterized in that: The storage medium includes a stored program, wherein when the program is executed, the device where the storage medium is located is controlled to execute the elbow screening method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images