A welding droplet data acquisition method and device, a storage medium and an electronic device

Abstract

The application provides a welding droplet data acquisition method and device, a storage medium and an electronic device. The method comprises the following steps: obtaining a droplet binary image according to a target image, the droplet binary image comprising first pixel points representing a droplet region and second pixel points representing a non-droplet region, the target image being an acquisition image of a target region, and the target region containing a droplet; and obtaining droplet information according to the droplet binary image, the droplet information comprising any one or more of area information, sphericity information, center position information and corresponding arc length information. The welding droplet data acquisition method provided by the application no longer depends on current, voltage and sound frequency information, directly processes the target image containing the droplet, obtains the droplet binary image, and thus obtains the droplet information, so that the entire physical change process of the droplet, such as the transition from small to large, can be directly obtained, which is relatively more intuitive and direct and convenient for users to refer to.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of image, in particular, to a welding droplet data acquisition method and device, a storage medium and an electronic device. BACKGROUND

[0002] The quality of the welding joint and the transition of the welding droplet are directly related, including the uniformity of the size of the droplet, the uniformity of the shape of the droplet, the droplet transition time and the arc time in short circuit transition welding, which have a crucial influence on the weld formation.

[0003] With the development of information technology, people pay more attention to the data analysis of welding quality, and make the previously vague concept data, visual and quantitative. Most of the data analysis of welding is focused on the electrical signal or acoustic signal in the welding process, such as the fluctuation of welding current and voltage, or the frequency interval of the sound generated in the welding process. These signal data are easy to collect, low in cost and convenient to process, which is the reason why they are generally selected and invested.

[0004] However, there is a difficult point in these data, which is that these data can only indirectly reflect the changes in the welding process, and cannot be directly linked to the physical meaning. Therefore, how to directly observe the welding process has become a difficult problem for those skilled in the art to overcome. SUMMARY

[0005] The purpose of the present application is to provide a welding droplet data acquisition method and device, a storage medium and an electronic device to at least partially improve the above problems.

[0006] In order to achieve the above purpose, the technical scheme adopted by the embodiments of the present application is as follows:

[0007] In a first aspect, the embodiments of the present application provide a welding droplet data acquisition method, which comprises:

[0008] Obtaining a droplet binary image according to a target image, wherein the droplet binary image includes first type of pixel points representing the droplet region and second type of pixel points representing the non-droplet region, the target image is a collection image of a target region, and the target region contains a droplet;

[0009] Obtaining droplet information according to the droplet binary image, wherein the droplet information includes any one or more of area information, sphericity information, center position information and corresponding arc length information.

[0010] In a second aspect, the embodiments of the present application provide a droplet transition stability acquisition method, which comprises:

[0011] According to the welding droplet data acquisition method, all target images in a target set are processed to obtain a droplet information set, wherein the target images in the target set are arranged in time sequence, and the droplet information in the droplet information set is arranged in time sequence.

[0012] According to the droplet information set, a variation coefficient corresponding to an arc burning time and an arc extinguishing time is obtained, wherein the arc burning time is a time length during which the area of the droplet continuously exceeds a preset area threshold, the arc extinguishing time is a time length during which the area of the droplet continuously is less than or equal to the preset area threshold, and the variation coefficient represents a fluctuation arc of the arc burning time and the arc extinguishing time, and the fluctuation arc represents the stability of the droplet transfer.

[0013] In a third aspect, an embodiment of the present application provides a welding droplet data acquisition device, and the device comprises:

[0014] An acquisition unit is configured to acquire a droplet binary image according to a target image, wherein the droplet binary image comprises first pixel points representing a droplet region and second pixel points representing a non-droplet region, the target image is a captured image of a target region, and the target region contains a droplet.

[0015] A processing unit is configured to acquire droplet information according to the droplet binary image, wherein the droplet information comprises any one or more of area information, sphericity information, center position information, and corresponding arc length information.

[0016] In a fourth aspect, an embodiment of the present application provides a droplet transfer stability acquisition device, and the device comprises:

[0017] An invoking unit is configured to process all target images in a target set according to the welding droplet data acquisition method to obtain a droplet information set, wherein the target images in the target set are arranged in time sequence, and the droplet information in the droplet information set is arranged in time sequence.

[0018] A calculation unit is configured to acquire a variation coefficient corresponding to an arc burning time and an arc extinguishing time according to the droplet information set, wherein the arc burning time is a time length during which the area of the droplet continuously exceeds a preset area threshold, the arc extinguishing time is a time length during which the area of the droplet continuously is less than or equal to the preset area threshold, and the variation coefficient represents a fluctuation arc of the arc burning time and the arc extinguishing time, and the fluctuation arc represents the stability of the droplet transfer.

[0019] In a fifth aspect, an embodiment of the present application provides a storage medium having a computer program stored thereon, and the computer program is executed by a processor to implement the above method.

[0020] In a sixth aspect, an electronic device is provided, and the electronic device includes a processor and a memory storing one or more programs. When the one or more programs are executed by the processor, the above-described method is implemented.

[0021] With respect to the prior art, the welding droplet data acquisition method, device, storage medium and electronic device provided by the embodiments of the present application include: acquiring a droplet binary image according to a target image, the droplet binary image including first type pixel points representing a droplet region and second type pixel points representing a non-droplet region, the droplet region being a continuous region, and the target image being a captured image of a target region containing a droplet; and acquiring droplet information according to the droplet binary image, the droplet information including any one or more of area information, sphericity information, center position information and corresponding arc length information. The welding droplet data acquisition method provided by the embodiments of the present application no longer relies on current, voltage and sound frequency information, directly processes the target image containing the droplet, acquires the droplet binary image, and thus acquires the droplet information, so that the entire physical change process of the droplet, such as from small to large and transition, can be directly acquired, which is relatively more intuitive and direct and is convenient for users to refer to.

[0022] In order to make the above objectives, characteristics and advantages of the present application more apparent and easy to understand, the following preferred embodiments are specifically described below, and the accompanying drawings are referred to for detailed description. BRIEF DESCRIPTION OF DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be considered as a limitation to the scope. For those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0024] Figure 1 The structural schematic diagram of the welding system provided by the embodiments of the present application is shown in the figure;

[0025] Figure 2 The structural schematic diagram of the electronic device provided by the embodiments of the present application is shown in the figure;

[0026] Figure 3 The flowchart of the welding droplet data acquisition method provided by the embodiments of the present application is shown in the figure;

[0027] Figure 4 The schematic diagram of a droplet binary image provided by the embodiments of the present application is shown in the figure;

[0028] Figure 5 The schematic diagram of the sub-step of S101 provided by the embodiments of the present application is shown in the figure;

[0029] Figure 6 A target gray scale image schematic diagram provided by an embodiment of the present application;

[0030] Figure 7 An edge contour extraction result schematic diagram provided by an embodiment of the present application;

[0031] Figure 8 A sub-step schematic diagram of S101-1 provided by an embodiment of the present application;

[0032] Figure 9 A target gray scale image schematic diagram provided by an embodiment of the present application after enhancement of gray scale contrast processing;

[0033] Figure 10 A sub-step schematic diagram of S101 provided by an embodiment of the present application;

[0034] Figure 11 A gray scale image schematic diagram provided by an embodiment of the present application without arc light;

[0035] Figure 12 A flowchart schematic diagram of a welding droplet data acquisition method provided by an embodiment of the present application;

[0036] Figure 13 A first sub-image and a second sub-image schematic diagram provided by an embodiment of the present application;

[0037] Figure 14 An image schematic diagram provided by an embodiment of the present application after dilation processing;

[0038] Figure 15 An image schematic diagram provided by an embodiment of the present application after erosion processing;

[0039] Figure 16 An image schematic diagram provided by an embodiment of the present application after thinning processing;

[0040] Figure 17 A contrast schematic diagram provided by an embodiment of the present application after edge removal processing;

[0041] Figure 18 A flowchart schematic diagram of a droplet transition stability acquisition method provided by an embodiment of the present application;

[0042] Figure 19a A macroscopic droplet size change schematic diagram provided by an embodiment of the present application;

[0043] Figure 19b A local droplet size change schematic diagram provided by an embodiment of the present application;

[0044] Figure 20a A macroscopic droplet shape change schematic diagram provided by an embodiment of the present application;

[0045] Figure 20b A local schematic diagram of the change of the shape of the molten droplet is provided for the embodiment of the present application;

[0046] Figure 21 A flow schematic diagram of the stability acquisition method of the molten droplet transition is provided for the embodiment of the present application;

[0047] Figure 22 A unit schematic diagram of the welding molten droplet data acquisition device is provided for the embodiment of the present application;

[0048] Figure 23 A unit schematic diagram of the stability acquisition device of the molten droplet transition is provided for the embodiment of the present application.

[0049] In the figure: 10 - processor; 11 - memory; 12 - bus; 13 - communication interface; 301 - acquisition unit; 302 - processing unit; 401 - calling unit; 402 - calculation unit. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme of the embodiments of the present application will be described clearly and completely below in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are some embodiments of the present application, rather than all the embodiments of the present application. The components of the embodiments of the present application described and shown in the drawings herein can be arranged and designed in various different configurations.

[0051] Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without making creative efforts, fall within the scope of protection of the present application.

[0052] It should be noted that: similar reference numerals and letters represent similar items in the following drawings, therefore, once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. Meanwhile, in the description of the present application, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0053] It is to be noted that, in the present document, the terms such as first and second, etc. are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Also, the terms "comprises", "comprising", or any other variations thereof are intended to cover a non-exclusive inclusion, so that a process, method, article, or apparatus that comprises a list of elements does not only include those elements but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without more limitations, an element defined by the statement "comprising a" does not exclude the existence of additional identical elements in the process, method, article, or apparatus that includes the stated element.

[0054] In the description of the present application, it should be noted that the terms "upper", "lower", "inner", "outer", etc. indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, or the orientation or positional relationship in which the product of the present application is usually placed, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application.

[0055] In the description of the present application, it should also be noted that, unless otherwise explicitly specified and limited, the terms "provided", "connected" should be understood broadly, for example, it can be a fixed connection, or a detachable connection, or an integral connection; it can be a mechanical connection, or an electrical connection; it can be a direct connection, or an indirect connection through an intermediate medium, or a communication inside two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0056] Some embodiments of the present application will be described in detail below with reference to the accompanying drawings. The following examples and features in the examples can be combined with each other without conflict.

[0057] With the development of high-speed photography technology and the improvement of computer operation speed, it is possible to directly extract pictures in the welding process and visually analyze the welding process. By directly analyzing the pictures in the welding process, the physical process of welding can be better and more intuitively reflected, which has a good guiding effect on improving the welding quality. Based on the direct extraction of pictures in the welding process, the short-circuiting transfer droplet is extracted, a welding droplet data acquisition method is proposed, the droplet information includes any one or more of the droplet size, droplet shape, droplet position, area information, sphericity information, center position information and corresponding arc length information, and the droplet information directly determines the transfer of the filler metal in the welding process, which has a good guiding effect on the welder.

[0058] Short-circuiting transfer refers to a kind of contact transfer, the droplet freely flies through the arc space, and the welding wire end and the molten pool do not directly contact. The welding arc is very short, the droplet has not grown up yet, and the molten pool is contacted, and the short-circuiting is formed. The arc is extinguished instantaneously, the short-circuiting current generates a large electromagnetic shrinkage force and surface tension, so that the droplet is quickly transferred to the molten pool, the arc is re-ignited, and the short-circuiting transfer process is formed. The arc of short-circuiting transfer is stable, and the spatter is small. This transfer form is widely used in thin plate welding of CO2 gas shielded welding. In the short-circuiting transfer welding process, the short-circuiting current rising speed, the peak value of the short-circuiting current and other parameters have a great influence on the welding stability, and therefore, the welding power supply should have appropriate stability and certain dynamic characteristics.

[0059] Optionally, in the scheme, the open source python language and the downloaded cv2 function library can be used to process the pictures, and the change of the droplet data can be visualized in the time domain space. Since the direct observation of the welding process is adopted, the method does not have the information loss and hiding caused by indirect measurement, and the judgment of the welding process is more objective and accurate.

[0060] Optionally, the welding system can acquire the welding picture. Figure 1 As shown in the figure, the welding system includes a welding machine, a backlight source, a welding station (welding robot + slide rail), a splash-proof glass, an arc light filter, an image acquisition module (for example, a high-speed camera) and an industrial computer.

[0061] The requirement of image data acquisition is to filter out the arc light and display the state of the droplet and the molten pool. In order to meet the above requirements, the backlight source can be a strong light source, and a high-brightness xenon lamp or a high-focusing laser light source can be selected. The power of the backlight source is 500w or more, and a condenser lens is arranged, and the light source irradiation direction points to the welding position.

[0062] Since welding is a moving process, high-speed photography is difficult to follow, so a combination of welding robot + slide rail is selected, in which the welding robot grabs the welding gun and keeps it in the welding position, and the slide rail has a welding clamp, which can move the welding workpiece horizontally, and the linear speed of welding is controlled by the slide rail, and the high-speed photography equipment is fixed, and the lens is aimed at the welding point, so as to ensure that the welding position always remains in the center of the high-speed photography shooting line of sight.

[0063] Optionally, the welding machine is electrically connected with the welding gun. The splash-proof glass is used for protecting the arc filter, the arc filter is used for filtering out the arc, and the light after filtering out the arc can enter the image acquisition module to complete imaging. The image acquisition module can transmit the generated welding image to the industrial computer.

[0064] In Figure 1 the welding system, the welding process is carried out (the welding machine is started, the welding is started, and the slide rail is uniformly moved), the backlight source and the high-speed camera are opened at the same time, and the image of the welding process is collected. The collection area contains the droplet. The frame number of high-speed photography can be 5000Hz, but it is not limited to this. After completing the preset number of welding data collection, the data is saved to the industrial computer, the data format is selected as a picture format (such as.bmp,.jpg,.png, etc.), and the preset number can be set according to user requirements.

[0065] The embodiment of the application provides an electronic device, which can be Figure 1 an industrial computer in the welding system, or can be a separate terminal device, such as a server or a computer device. Optionally, the server or the computer device is in communication connection with the industrial computer, and can receive the picture transmitted by the industrial computer.

[0066] Please refer to Figure 2 , a structural schematic diagram of the electronic device. The electronic device includes a processor 10, a memory 11 and a bus 12. The processor 10 and the memory 11 are connected through the bus 12, and the processor 10 is used for executing an executable module stored in the memory 11, such as a computer program.

[0067] The processor 10 can be an integrated circuit chip with processing capability. In the implementation process, the steps of the welding droplet data acquisition method can be completed by the integrated logic circuit of hardware in the processor 10 or the instructions in the form of software. The processor 10 described above can be a general processor, including a central processing unit (CPU), a network processor (NP), etc.; can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0068] The memory 11 can include a high-speed random access memory (RAM), and can also include a non-volatile memory, such as at least one disk memory.

[0069] The bus 12 can be an industry standard architecture (ISA) bus, a peripheral component interconnect (PCI) bus, an extended industry standard architecture (EISA) bus, etc. Figure 2 Only one bidirectional arrow is used to represent the bus 12, but it does not mean that there is only one bus 12 or only one type of bus 12.

[0070] The memory 11 is used to store programs, such as programs corresponding to the welding droplet data acquisition device. The welding droplet data acquisition device includes at least one software function module which can be stored in the memory 11 in the form of software or firmware or solidified in the operating system (OS) of the electronic device. After receiving an execution instruction, the processor 10 executes the program to implement the welding droplet data acquisition method.

[0071] Possibly, the electronic device provided by the embodiment of the present application further includes a communication interface 13. The communication interface 13 is connected with the processor 10 through the bus. The electronic device can acquire the welding image through the communication interface 13.

[0072] It should be understood that, Figure 2The structure shown is only a partial schematic diagram of the electronic device; the electronic device may also include components that are larger than... Figure 2 The more or fewer components shown, or having the same Figure 2 The different configurations shown. Figure 2 The components shown can be implemented using hardware, software, or a combination thereof.

[0073] The welding droplet data acquisition method provided in this application embodiment can be applied to, but is not limited to, [various applications]. Figure 2 For the specific process of the electronic devices shown, please refer to [link / reference]. Figure 3 The methods for acquiring welding droplet data include S101 and S109, which are described in detail below.

[0074] S101, Obtain the binary image of the molten droplet based on the target image.

[0075] The binary image of the molten droplet includes a first type of pixel representing the molten droplet region and a second type of pixel representing the non-molten droplet region. The molten droplet region can be a continuous region, and the target image is the acquired image of the target region, which contains the molten droplet.

[0076] Optionally, the target area is Figure 1 The image area acquired by the image acquisition module includes the molten droplets formed around the solder joint. Please refer to [link / reference]. Figure 4 , Figure 4 This is a schematic diagram of a binary image of a molten droplet provided in an embodiment of this application. The molten droplet region can be... Figure 4 The white area shown.

[0077] It should be understood that the binary image of the molten droplet consists of a first type of pixel and a second type of pixel. The first type of pixel is, for example, a pixel with a value of 1, and the second type of pixel is, for example, a pixel with a value of 0.

[0078] S109, obtain droplet information based on the binary image of the droplet.

[0079] The droplet information includes any one or more of the following: area information, sphericity information, center position information, and corresponding arc length information.

[0080] The welding droplet data acquisition method provided in this application no longer relies on information such as current, voltage, and sound frequency. It directly processes the target image containing the droplets to obtain a binary image of the droplets, thereby obtaining droplet information. It can directly obtain the entire physical change process of the droplets, such as from small to large and transition. Relatively speaking, it is more intuitive and direct, and easier for users to refer to.

[0081] In summary, the embodiment of the present application provides a welding droplet data acquisition method, comprising: acquiring a droplet binary image according to a target image, the droplet binary image comprising first pixel points representing a droplet region and second pixel points representing a non-droplet region, the droplet region being a continuous region, the target image being a collected image of a target region, and the target region containing a droplet; and acquiring droplet information according to the droplet binary image, the droplet information comprising any one or more of area information, sphericity information, center position information, and corresponding arc length information. The welding droplet data acquisition method provided by the present application no longer relies on current, voltage, sound frequency and other information, directly processes the target image containing the droplet, obtains the droplet binary image, and thus acquires the droplet information, so that the entire physical change process of the droplet, such as from small to large and transition, can be directly acquired, which is relatively more intuitive and direct and is convenient for users to refer to.

[0082] As to S101 in Figure 3 , the embodiment of the present application further provides a possible implementation manner, please refer to Figure 5 , S101 comprises S101-1 and S101-4, which are specifically described as follows.

[0083] S101-1, a target gray image corresponding to a target image is acquired.

[0084] Please refer to Figure 6 , Figure 6 for a target gray image schematic diagram provided by the embodiment of the present application.

[0085] It should be understood that the gray scale image, Gray Scale Image or Grey Scale Image is also called gray scale image. The white color and the black color are divided into several levels according to the logarithmic relationship, which is called gray scale. The gray scale is divided into 256 levels. By converting the target image into the target gray image, the data amount of the image data is reduced, which is convenient for subsequent calculation.

[0086] S101-4, the target gray image is processed according to an edge contour extraction algorithm to obtain a droplet binary image.

[0087] Optionally, all edges in the target gray image are extracted by the edge contour extraction algorithm canny, and the target gray image is converted into the droplet binary image.

[0088] Please refer to Figure 7 , Figure 7 for an edge contour extraction result schematic diagram provided by the embodiment of the present application.

[0089] As to S101-1 in Figure 5 , the embodiment of the present application further provides a possible implementation manner, please refer to Figure 8S101-1 includes S101-1A and S101-1B, which are specifically described as follows.

[0090] S101-1A, performing gray scale conversion on the current image to obtain a corresponding initial gray scale image.

[0091] S101-1B, performing enhanced gray scale contrast processing on the initial gray scale image to obtain a target gray scale image.

[0092] Please refer to Figure 9 , Figure 9 The target gray scale image after the enhanced gray scale contrast processing provided by the embodiments of the present application is shown in the following figure. Compared with Figure 6 the initial gray scale image provided, the target gray scale image after the enhanced gray scale contrast processing Figure 9 , the boundary points of the molten droplet region and the non-molten droplet region are more obvious, which is conducive to improving the accuracy of the obtained contour.

[0093] On the basis of Figure 5 , in order to further reduce the processing steps, the embodiments of the present application also provide a possible implementation manner, please refer to Figure 10 After S101-1, S101 further includes S101-2, S101-3 and S101-5, which are specifically described as follows.

[0094] S101-2, obtaining an average gray scale value of the target gray scale image.

[0095] Optionally, on the basis of the target gray scale image obtained in S101-1, the average gray scale value of the target gray scale image is obtained.

[0096] S101-3, determining whether the average gray scale value is less than a preset gray scale threshold value. If yes, S101-5 is executed; if no, S101-3 is executed.

[0097] Optionally, when the molten droplet is in the transition process and disappears, there is no arc light in this process, and the average gray scale value of the photo in this process is small, as shown in Figure 11 When the average gray scale value is less than the preset gray scale threshold value (for example, 0.045), it is determined that the process is in the state of short-circuit transition of the molten droplet, at this time, S101-5 can be executed to fill the target gray scale image to obtain a molten droplet binary image in which all pixel points are the second type of pixel points. Otherwise, when there is arc light, the molten droplet is in the change period, then S101-4 is executed to obtain change data of the molten droplet.

[0098] S101-5, filling the target gray scale image to obtain a molten droplet binary image in which all pixel points are the second type of pixel points.

[0099] Optionally, all data in the target gray image with an average gray value less than a preset gray threshold is deleted and replaced by a second type of pixel point (for example, 0), that is, a molten drop area of 0 and a molten drop sphericity of 0.

[0100] On the basis of Figure 5 , the present application further provides a possible implementation manner for how to further improve the accuracy of information in the molten drop binary image. Please refer to Figure 12 , after S101-4, the welding molten drop data acquisition method further includes S102, S103, S104, S105, S106, S107 and S108, which are specifically described as follows.

[0101] S102, according to a preset cutting line, the molten drop binary image is cut to obtain a first sub-image and a second sub-image.

[0102] The cutting line passes through the molten drop contour in the molten drop binary image.

[0103] It should be understood that, because the positions of the welding spot and the image acquisition module are relatively fixed, the position of the molten drop region in the target image acquired by the welding system shown in Figure 1 is also relatively fixed. Therefore, the coordinate information of the cutting line passing through the molten drop contour in the molten drop binary image can be preset.

[0104] For example, after the approximate position of the welding molten drop is determined manually, a horizontal line (parallel to the welding direction) that can pass through the molten drop is selected. The average horizontal coordinate of the molten drop can be obtained by adding the intersection horizontal coordinates of the line at both ends of the molten drop edge and dividing by 2. The line segment (i.e., the vertical direction) passing through the average horizontal coordinate and perpendicular to the welding direction can be used as the cutting line. In the possible implementation manner, the cutting line can also be a horizontal transverse line, which is not limited herein.

[0105] Please refer to Figure 13 , Figure 13 The first sub-image and the second sub-image provided by the present application are shown in the schematic diagram. It should be noted that the first sub-image and the second sub-image can be two separate pictures, or can be two different regions in the same picture as shown in Figure 13 , which is not limited herein.

[0106] As shown in Figure 13 , the first sub-image is Figure 13 the right region separated from the middle, and the second sub-image is Figure 13 the left region separated from the middle.

[0107] By cutting the molten drop binary image into the first sub-image and the second sub-image, subsequent filling operation processing is facilitated.

[0108] S103, performing inflation processing on the first sub-image and the second sub-image to increase thickness of lines of the droplet profile in the image.

[0109] Optionally, the inflation operation is performed on the first sub-image and the second sub-image, the inflation is in a vertical direction, a unit is a straight line, and an inflation coefficient is appropriately increased to close some profile lines with small gaps. Figure 14 As shown in Figure 14 The image after the inflation processing provided by the embodiment of the present application is shown in the following.

[0110] S104, performing erosion processing on the first sub-image and the second sub-image after the inflation processing to reduce the thickness of the lines of the droplet profile in the image.

[0111] It should be understood that, through the erosion processing, the line points caused by the inflation operation are removed. Figure 15 As shown in Figure 15 The image after the erosion processing provided by the embodiment of the present application is shown in the following.

[0112] S105, performing thinning processing on the first sub-image and the second sub-image after the erosion processing to make the thickness of the lines of the droplet profile in the image be in a preset thickness range.

[0113] It should be understood that, through the thinning processing, the purpose of simplifying the line segments is achieved. Figure 16 As shown in Figure 16 The image after the thinning processing provided by the embodiment of the present application is shown in the following.

[0114] S106, performing edge deletion processing on the first sub-image and the second sub-image after the thinning processing to delete the lines of the non-droplet profile in the image.

[0115] Optionally, on the basis of Figure 16 a straight line with a slope of 15-60° can be created on the picture of the left half of the droplet, the left side of the straight line can cover the edge feature line of the molten pool, and all line segment values on the left side of the straight line are changed to 0 to delete the lines of the non-droplet profile in the image. Figure 17 As shown in Figure 17 The contrast diagram after the edge deletion processing provided by the embodiment of the present application is shown in the following. In the diagram, Figure 17 the left side is the image before the edge deletion processing, Figure 17 and the right side is the image after the edge deletion processing.

[0116] It should be understood that the position of the droplet region is approximately fixed. In a possible implementation, a specified region range can be preset, and the lines outside the specified region range can be determined as the lines of the non-droplet profile.

[0117] S107, performing padding processing on the first sub-image and the second sub-image after the edge removal processing, so as to fill the lines of the droplet contour and the enclosed area of the cutting line in the image as the first type of pixel points.

[0118] Optionally, in the right image of the right side of the image, the left half of the droplet is filled, that is, the pixel point data at these positions is changed to the first type of pixel point (for example, 1). The left half of the droplet is filled, that is, the pixel point data at these positions is changed to the first type of pixel point (for example, 1). Figure 17

[0119] S108, splicing the first sub-image and the second sub-image after the padding processing to obtain a final droplet binary image.

[0120] Optionally, the first sub-image and the second sub-image are merged together, and a complete droplet binary image is obtained at this time, and the final droplet binary image is as shown in Figure 4 After S108, S109 can be performed.

[0121] On the basis of Figure 3 , for the content in S109, the present embodiment further provides a possible implementation manner, please refer to the following.

[0122] The cv2 built-in functions cv2.contourArea and Cv2.HoughCircles can be used to calculate the droplet area and the sphericity, and of course the center position and the arc length of the droplet can also be calculated, so as to complete the droplet information extraction.

[0123] Optionally, on the basis of the extracted droplet information, the arcing time, the arc extinguishing time and the transition frequency can be obtained, so as to accurately and intuitively judge the welding quality.

[0124] The present embodiment further provides a droplet transition stability acquisition method, applied to the electronic device described above, please refer to Figure 18 , the droplet transition stability acquisition method comprises S201 and S203, which are specifically described as follows.

[0125] S201, according to the welding droplet data acquisition method, processing all target images in the target set to obtain a droplet information set.

[0126] Among them, the target images in the target set are arranged in time sequence, and the droplet information in the droplet information set is arranged in time sequence.

[0127] ​Optionally, all target images in the target set are processed according to any one of the welding droplet data acquisition methods described above, and a droplet information set can be obtained.

[0128] The data in the droplet information set represent the change of the droplet data over time, which facilitates direct observation of the welding quality by the user.

[0129] In S203, a variation coefficient corresponding to the burning time and the extinguishing time is obtained according to the droplet information set.

[0130] The burning time is the length of time during which the area of the droplet is continuously greater than a preset area threshold, the extinguishing time is the length of time during which the area of the droplet is continuously less than or equal to the preset area threshold, and the variation coefficient represents the fluctuation amplitude of the burning time and the extinguishing time, which represents the stability of the droplet transfer. The preset area threshold is, for example, 0.05 or 0.1.

[0131] Optionally, the data in the droplet information set is plotted along the time domain to visualize the data, as shown in FIGS. 19 and 20. Figure 19a A macroscopic schematic diagram of the change in the size of the droplet is provided for the embodiments of the present application. Figure 19b A partial schematic diagram of the change in the size of the droplet is provided for the embodiments of the present application. Figure 20a A macroscopic schematic diagram of the change in the shape of the droplet is provided for the embodiments of the present application. Figure 20b A partial schematic diagram of the change in the shape of the droplet is provided for the embodiments of the present application.

[0132] Figure 19b The area indicated by the downward arrow symbol in FIG. 18 is the stage in which the droplet enters the short circuit transfer stage, and the area indicated by the upward arrow symbol is the stage in which the droplet gradually grows in the burning stage.

[0133] It should be understood that there are multiple burning times and multiple extinguishing times, and because the lengths of time are different, there is fluctuation, i.e., the variation coefficient. Optionally, the variation coefficients of the area, the sphericity, the burning time, and the extinguishing time of the droplet are calculated, and the stability and uniformity of the droplet transfer can be quantified.

[0134] Optionally, the variation amount of each complete stage (including the continuous burning stage and the extinguishing stage) can be obtained, the standard deviation is obtained by the obtained variation amount, and then the average value is divided, and thus the variation coefficient can be obtained.

[0135] The variation coefficient can eliminate the influence of different units and / or average numbers on the comparison of the variation degrees of two or more data, and the calculation formula is: variation coefficient = standard deviation / average number.

[0136] Optionally, the variation coefficient corresponding to the sphericity can be determined as the variation coefficient of the shape. The sphericity can be obtained by Cv2.HoughCircles.

[0137] On the basis of Figure 18 , the application embodiment also provides a possible implementation manner for how to improve the accuracy of the coefficient of variation, please refer to Figure 21 After S201, the method further includes: S202, which is specifically described as follows.

[0138] S202, mean filtering processing is performed on the droplet information set.

[0139] Optionally, the mean filtering manner is used to process the data in the droplet information set, so as to remove the data discontinuity problem caused by the abnormal picture, such as the data discontinuity problem caused by droplet breakage, molten pool splashing, instantaneous light change and the like.

[0140] Please refer to Figure 22 , Figure 22 A welding droplet data acquisition device is provided in the application embodiment, and optionally, the welding droplet data acquisition device is applied to the electronic device described above.

[0141] The welding droplet data acquisition device includes an acquisition unit 301 and a processing unit 302.

[0142] The acquisition unit 301 is configured to acquire a droplet binary image according to a target image, wherein the droplet binary image includes first-type pixel points representing a droplet region and second-type pixel points representing a non-droplet region, and the target image is a collection image of a target region containing a droplet.

[0143] The processing unit 302 is configured to acquire droplet information according to the droplet binary image, wherein the droplet information includes any one or more of area information, sphericity information, center position information and corresponding arc length information.

[0144] Optionally, the acquisition unit 301 can perform S101-S108 described above, and the processing unit 302 can perform S109 described above.

[0145] It should be noted that the welding droplet data acquisition device provided in the embodiment can perform the method process shown in the method process embodiment to achieve the corresponding technical effects. For brevity, the part not mentioned in the embodiment can refer to the corresponding content in the above-described embodiments.

[0146] Please refer to Figure 23 , Figure 23 A droplet transfer stability acquisition device is provided in the application embodiment, and optionally, the droplet transfer stability acquisition device is applied to the electronic device described above.

[0147] The droplet transfer stability acquisition device includes a calling unit 401 and a calculation unit 402.

[0148] Calling unit 401 is used to process all target images in the target set according to the welding droplet data acquisition method of any of the above items to obtain a droplet information set, wherein the target images in the target set are arranged in time sequence, and the droplet information in the droplet information set is arranged in time sequence;

[0149] The calculation unit 402 is used to obtain the coefficient of variation corresponding to the arc ignition time and the arc extinguishing time based on the molten droplet information set. The arc ignition time is the length of time during which the area of ​​the molten droplet is continuously greater than a preset area threshold, and the arc extinguishing time is the length of time during which the area of ​​the molten droplet is continuously less than or equal to a preset area threshold. The coefficient of variation represents the fluctuation arc of the arc ignition time and the arc extinguishing time, and the fluctuation arc characterizes the stability of the molten droplet transition.

[0150] Optionally, the calling unit 401 can execute S201 as described above, and the calculation unit 402 can execute S202 and S203 as described above.

[0151] It should be noted that the device for obtaining the stability of droplet transition provided in this embodiment can execute the method flow shown in the above-described method flow embodiment to achieve the corresponding technical effect. For the sake of brevity, any parts not mentioned in this embodiment can be referred to the corresponding content in the above-described embodiments.

[0152] This application also provides a storage medium storing computer instructions and programs. When read and executed, these instructions and programs perform the welding droplet data acquisition method and the droplet transition stability acquisition method described above. The storage medium may include memory, flash memory, registers, or a combination thereof.

[0153] The following provides an electronic device, which can be an industrial control computer, a standalone computer, or a server. This electronic device is as follows: Figure 2 As shown, the above-described method for acquiring welding droplet data and method for acquiring droplet transition stability can be implemented. Specifically, the electronic device includes: a processor 10, a memory 11, and a bus 12. The processor 10 may be a CPU. The memory 11 is used to store one or more programs. When one or more programs are executed by the processor 10, the welding droplet data acquisition method and the droplet transition stability acquisition method of the above embodiments are executed.

[0154] In the embodiments of the present disclosure, it should be understood that the disclosed apparatus and method can also be implemented in other manners. The embodiments described above are merely exemplary. For example, the flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architectures, functions and operation of the apparatus, method and computer program product according to the embodiments of the present disclosure. In this regard, each block in the flowcharts and block diagrams can represent a module, a segment or a portion of code which comprises one or more executable instructions for implementing the specified logic function. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur in a different order than that noted in the accompanying drawings. For example, two blocks noted in succession can actually be executed substantially concurrently or in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented by dedicated hardware-based systems which perform specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0155] In addition, the various functional modules in the embodiments of the present disclosure can be integrated together to form a separate part, or can exist independently, or two or more modules can be integrated to form a separate part.

[0156] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present disclosure can be embodied in the form of a software product, and the computer software product is stored in a storage medium, and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present disclosure. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media capable of storing program codes.

[0157] The above only describes the preferred embodiments of the present disclosure and is not intended to limit the present disclosure. For those skilled in the art, the present disclosure can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

[0158] It will be apparent to those skilled in the art that the application is not limited to the details of the above-exemplified embodiments and that the present application can be implemented in other particular forms without departing from the spirit or essential characteristics thereof. The embodiments should be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the above description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. No reference herein to any prior art is to be taken as an admission that the application is not entitled to antedate such prior art by virtue of prior application. Any reference to the use of a term in the singular herein shall be understood in the context to describe a particular example or embodiment of the application and should not be construed as limiting the scope of the application to that particular example or embodiment. Any reference to use of terms in the plural herein shall be understood as describing a particular example or embodiment of the application and should not be construed as limiting the scope of the application to that particular example or embodiment.

Claims

1. A method of acquiring welding droplet data, characterized by, The method comprises: According to the target image, a droplet binary image is obtained, wherein the droplet binary image comprises first type pixel points representing droplet regions and second type pixel points representing non-droplet regions, the target image is a collected image of a target region, and the target region contains a droplet; According to the droplet binary image, droplet information is obtained, wherein the droplet information comprises any one or more of area information, sphericity information, center position information, and corresponding arc length information; According to the target image, a droplet binary image is obtained, wherein the droplet binary image comprises first type pixel points representing droplet regions and second type pixel points representing non-droplet regions, the target image is a collected image of a target region, and the target region contains a droplet; After the target gray image is processed according to the edge contour extraction algorithm to obtain the droplet binary image, the method further comprises: According to a preset cutting line, the droplet binary image is cut to obtain a first sub-image and a second sub-image, wherein the cutting line passes through a droplet contour in the droplet binary image; The first sub-image and the second sub-image are dilated to increase the thickness of the droplet contour in the image; The first sub-image and the second sub-image after the dilatation are eroded to reduce the thickness of the droplet contour in the image; The first sub-image and the second sub-image after the erosion are thinned to make the thickness of the droplet contour in the image within a preset thickness range; The first sub-image and the second sub-image after the thinning are edge-removed to delete the non-droplet contour in the image; The first sub-image and the second sub-image after the edge-removal are filled to fill the droplet contour in the image and the enclosed area of the cutting line with the first type pixel points; The first sub-image and the second sub-image after the filling are spliced to obtain a final droplet binary image.

2. The welding droplet data acquisition method of claim 1, wherein, The target gray image corresponding to the target image is obtained, comprising: The current image is converted to gray to obtain a corresponding initial gray image; The initial gray image is enhanced in gray contrast to obtain the target gray image.

3. A method of obtaining stability of a droplet transfer, characterized by, The method comprises: According to the welding droplet data acquisition method of any one of claims 1 to 2, all target images in a target set are processed to obtain a droplet information set, wherein the target images in the target set are arranged in time sequence, and the droplet information in the droplet information set is arranged in time sequence. According to the set of droplet information, a variation coefficient corresponding to an arc burning time and an arc extinguishing time is obtained, wherein the arc burning time is a time length during which the area of the droplet is continuously greater than a preset area threshold, the arc extinguishing time is a time length during which the area of the droplet is continuously less than or equal to the preset area threshold, and the variation coefficient represents fluctuation radians of the arc burning time and the arc extinguishing time.

4. The method for acquiring stability of a droplet transfer according to Claim 3, wherein After obtaining the set of droplet information, the method further includes: performing mean filtering processing on the set of droplet information.

5. A welding droplet data acquisition apparatus characterized by comprising: The device includes: an acquisition unit configured to acquire a droplet binary image according to a target image, wherein the droplet binary image includes first pixel points representing a droplet region and second pixel points representing a non-droplet region, the target image is a captured image of a target region, and the target region includes the droplet; a processing unit configured to acquire droplet information according to the droplet binary image, wherein the droplet information includes any one or more of area information, sphericity information, center position information, and corresponding arc length information; The acquisition of the droplet binary image according to the target image includes: acquiring a target gray image corresponding to the target image; acquiring an average gray value of the target gray image; in a case where the average gray value is less than a preset gray threshold, performing padding on the target gray image to obtain a droplet binary image in which all pixel points are the second pixel points; and in a case where the average gray value is greater than or equal to the preset gray threshold, performing processing on the target gray image according to an edge contour extraction algorithm to obtain the droplet binary image. After the processing on the target gray image according to the edge contour extraction algorithm to obtain the droplet binary image, the welding droplet data acquisition device is further configured to: perform segmentation on the droplet binary image according to a preset cutting line to obtain a first sub-image and a second sub-image, wherein the cutting line passes through a droplet contour in the droplet binary image; perform dilation processing on the first sub-image and the second sub-image to increase the thickness of the line of the droplet contour in the image; perform erosion processing on the first sub-image and the second sub-image after the dilation processing to decrease the thickness of the line of the droplet contour in the image; perform thinning processing on the first sub-image and the second sub-image after the erosion processing to make the thickness of the line of the droplet contour in the image be within a preset thickness range; perform edge removal processing on the first sub-image and the second sub-image after the thinning processing to delete the line of the non-droplet contour in the image; perform padding processing on the first sub-image and the second sub-image after the edge removal processing to fill the line of the droplet contour and a surrounding area of the cutting line in the image with the first pixel points; and perform splicing on the first sub-image and the second sub-image after the padding processing to obtain a final droplet binary image.

6. A stability acquisition device for a droplet transfer, characterized by The device includes: The calling unit is configured to process all target images in a target set to obtain a droplet information set according to the welding droplet data acquisition method in any one of claims 1 to 2, wherein the target images in the target set are arranged in time sequence, and the droplet information in the droplet information set is arranged in time sequence; The computing unit is configured to obtain a coefficient of variation corresponding to an arc burning time and an arc extinguishing time according to the droplet information set, wherein the arc burning time is a length of time during which the area of a droplet is continuously greater than a preset area threshold, the arc extinguishing time is a length of time during which the area of the droplet is continuously less than or equal to the preset area threshold, and the coefficient of variation represents fluctuation radians of the arc burning time and the arc extinguishing time.

7. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program, when executed by a processor, implements the method of any one of claims 1-4.

8. An electronic device, comprising: The computer program product comprises: a processor and a memory configured to store one or more programs; when the one or more programs are executed by the processor, the method of any one of claims 1-4 is implemented.

Images