A method for detecting the welding quality of transposed conductors of transformers based on augmented reality technology

Abstract

The present invention provides a method for detecting the welding quality of transposed conductors of a transformer based on augmented reality technology, belonging to the technical field of transformer quality detection. The method includes obtaining an image of the welding area of the transposed conductors of a power transformer through an augmented reality device; using a pre-trained surface defect model of the transposed conductors to identify the image of the welding area of the transposed conductors of the power transformer, and screening out the transposed conductors without appearance surface quality defects; performing visual inspection of the dimensions of the transposed conductors on the transposed conductors without appearance surface quality defects, and determining the welding quality of the transposed conductors of the transformer based on the detection results, and the visual inspection of the dimensions of the transposed conductors is used to obtain the dimensions of the welding area of the transposed conductors. The present invention uses an augmented reality device for digital supervision of manufacturing, can achieve digital traceable supervision of "liberating hands", greatly saves the time spent on measuring the dimensions of transposed conductors, and eliminates the possibility of errors caused by human mistakes.

Description

Technical Field

[0001] The present invention belongs to the technical field of transformer quality inspection, and particularly relates to a method for inspecting the welding quality of transposed conductors of a transformer based on augmented reality technology. Background Art

[0002] During the coil winding process of a transformer, generally transposed conductors are used to wind an "S" bend. Using transposed conductors can significantly reduce load losses, reduce hot spot temperature rise, enhance mechanical strength, make the structure more compact and facilitate coil processing. However, if the manufacturing process parameters of the transposed conductors are not properly selected or the process control is not in place, it will bring great difficulties to the winding of the transformer winding, and even the winding cannot be carried out. According to the national standard regulations, the flat wires of transposed conductors are allowed to be welded, but it is necessary to ensure that the dimensions of the wide side and the narrow side after welding repair of the transposed conductors do not exceed 1.5 times the original, and the distance between the welding points is not less than 500 mm. At present, the supervision workers mainly measure the size of the welding part with a vernier caliper, and the process is complex and the efficiency is low. Summary of the Invention

[0003] In view of this, the present invention provides a method for inspecting the welding quality of transposed conductors of a transformer based on augmented reality technology, so as to efficiently and conveniently obtain the quality information of the welding part of the transposed conductors, reduce the influence of human subjective factors, and improve the traceability of information recording.

[0004] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0005] In a first aspect, the present invention provides a method for inspecting the welding quality of transposed conductors of a transformer based on augmented reality technology, including the following steps:

[0006] Obtain an image of the welding part of the transposed conductors of the power transformer through an augmented reality device;

[0007] Use a pre-trained surface defect model of the transposed conductors to identify the image of the welding part of the transposed conductors of the power transformer, and screen out the transposed conductors without appearance surface quality defects;

[0008] Perform visual inspection of the dimensions of the transposed conductors on the transposed conductors without appearance surface quality defects, and determine the welding quality of the transposed conductors of the transformer based on the detection results. The visual inspection of the dimensions of the transposed conductors is used to obtain the dimensions of the welding part of the transposed conductors.

[0009] Further, performing visual inspection of the dimensions of the transposed conductors on the transposed conductors without appearance surface quality defects specifically includes:

[0010] In the original image corresponding to the transposed conductors without appearance surface quality defects, use a first segmentation method to segment and obtain a first transposed conductor image, and the first transposed conductor image is a transposed conductor image that does not include the welding point;

[0011] Obtain the width of the transposed conductor in the first transposed conductor image;

[0012] In the original image corresponding to the transposed conductor without appearance surface quality defects, use the second segmentation method to segment and obtain the second transposed conductor image, and the second transposed conductor image is a transposed conductor image including the welding point;

[0013] Obtain the size of the welding point in the second transposed conductor image.

[0014] Furthermore, determine the welding quality of the transformer transposed conductor based on the detection result, specifically including:

[0015] Calculate the ratio of the welding point size to the transposed conductor width. If the ratio is within the set range, it is determined that the welding quality of the transformer transposed conductor is qualified; if the ratio is not within the set range, it is determined that the welding quality of the transformer transposed conductor is unqualified.

[0016] Furthermore, the set range is that the ratio is not greater than 50%.

[0017] Furthermore, the transposed conductor surface defect model is deployed on the server for appearance surface quality defect identification.

[0018] Furthermore, the augmented reality device further includes: a communication device;

[0019] The augmented reality device sends the image of the welding point of the power transformer transposed conductor to the server through the communication device.

[0020] Furthermore, the augmented reality device further includes: a portable display device;

[0021] The portable display device is used to display the visual inspection of the transposed conductor size and the welding quality of the transformer transposed conductor.

[0022] In a second aspect, the present invention provides a device for detecting the welding quality of a transformer transposed conductor based on augmented reality technology, including:

[0023] An image acquisition module, which acquires an image of the welding point of the power transformer transposed conductor through the augmented reality device;

[0024] An image recognition module, which is used to use a pre-trained transposed conductor surface defect model to recognize the image of the welding point of the power transformer transposed conductor and screen out the transposed conductors without appearance surface quality defects;

[0025] A visual inspection module, which is used to perform visual inspection of the transposed conductor size on the transposed conductor without appearance surface quality defects, determine the welding quality of the transformer transposed conductor based on the detection result, and the visual inspection of the transposed conductor size is used to obtain the size of the welding point of the transposed conductor.

[0026] Accordingly, the present invention further provides a computer device, which includes a processor and a memory:

[0027] The memory is used to store a computer program and send the instructions of the computer program to the processor;

[0028] The processor executes, according to the instructions of the computer program, a method for detecting the welding quality of transformer transposed conductors based on augmented reality technology as described in the first aspect.

[0029] Accordingly, the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements a method for detecting the welding quality of transformer transposed conductors based on augmented reality technology as described in the first aspect.

[0030] In summary, the present invention provides a method for detecting the welding quality of transformer transposed conductors based on augmented reality technology, including obtaining an image of the welding area of the transformer transposed conductors through an augmented reality device; using a pre-trained surface defect model of the transposed conductors to identify the image of the welding area of the transformer transposed conductors and screening out the transposed conductors without appearance surface quality defects; performing visual inspection on the dimensions of the transposed conductors without appearance surface quality defects, and determining the welding quality of the transformer transposed conductors based on the detection results. The visual inspection of the dimensions of the transposed conductors is used to obtain the dimensions of the welding area of the transposed conductors. The present invention uses an augmented reality device for digital supervision and manufacturing, can achieve digital traceable supervision and manufacturing of "liberating hands", greatly saves the time spent on measuring the dimensions of the transposed conductors, and eliminates the possibility of errors caused by human mistakes. Description of the Drawings

[0031] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0032] Figure 1 It is a flowchart of a method for detecting the welding quality of transformer transposed conductors based on augmented reality technology provided by an embodiment of the present invention;

[0033] Figure 2 It is a block diagram of the composition of a device for detecting the welding quality of transformer transposed conductors based on augmented reality technology provided by an embodiment of the present invention;

[0034] Figure 3 It is a block diagram of the composition of a computer device provided by an embodiment of the present invention. Detailed Embodiments

[0035] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described below 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 creative work are within the scope of protection of the present invention.

[0036] See also Figure 1 This embodiment provides a transformer transposed conductor welding quality detection method based on augmented reality technology, comprising the following steps:

[0037] S11: Acquire an image of a welding location of a transposed conductor of a power transformer through an augmented reality device;

[0038] S12: using the pre-trained transposed conductor surface defect model, the image of the transposed conductor welding part of the power transformer is recognized to screen out the transposed conductors without appearance surface quality defects;

[0039] S13: Perform visual inspection on the transposed conductor dimensions of the transposed conductors without appearance surface quality defects, and determine the welding quality of the transformer transposed conductors based on the inspection results. The visual inspection on the transposed conductor dimensions is used to obtain the dimensions of the transposed conductor welding points.

[0040] It should be noted that augmented reality technology is a technology that cleverly integrates virtual information with the real world. It widely uses a variety of technical means such as multimedia, three-dimensional modeling, real-time tracking and registration, intelligent interaction, and sensing. It simulates computer-generated virtual information such as text, images, three-dimensional models, music, and videos, and applies them to the real world. The two types of information complement each other, thereby achieving "enhancement" of the real world.

[0041] The transformer transposed conductor welding quality detection method proposed in this embodiment applies augmented reality technology to the transformer transposed conductor welding quality detection, uses an augmented reality device to obtain an image of the transposed conductor welding portion of the power transformer, and uses it to determine subsequent welding quality detection.

[0042] When the image of the welding part of the transposed conductor of the power transformer is collected and generated, the transposed conductor surface defect model is used to identify the appearance surface quality defects of the transposed conductor, and the transposed conductors without appearance surface quality defects are selected for inspection.

[0043] This embodiment provides a method for detecting the welding quality of transposed conductors of a transformer based on augmented reality technology. This method uses an augmented reality device for digital supervision, enabling "hands-free" digital traceable supervision, greatly saving the time spent on measuring the dimensions of transposed conductors and eliminating the possibility of errors caused by human mistakes.

[0044] In a preferred embodiment of the present invention, the augmented reality device further includes: a communication device;

[0045] The augmented reality device sends the image of the welded joint of the transposed conductors of the power transformer to the server through the communication device.

[0046] In a specific implementation, an image of the welded joint of the transposed conductors during the coil winding process of the power transformer is obtained based on the camera of the augmented reality device, and the image is transmitted to the server background through the built-in 5G communication. The augmented display device is a standard Android system and conducts 5G communication through the inserted SIM card. When the 5G signal is poor, it can automatically switch to 4G network communication to ensure efficient and uninterrupted remote communication. At the same time, to ensure the accuracy of subsequent measurements, during the binocular image shooting process, the captured pictures should be clear and distinguishable, without affecting subsequent detection and measurement, and the field of view angle should be large enough and the shooting distance should be appropriate.

[0047] To ensure the accuracy of subsequent visual inspections, the following regulations are required for the shooting process:

[0048] 1) Assume that the resolution of the captured picture is appropriate, the captured picture is clear and distinguishable, and it will not affect subsequent recognition;

[0049] 2) Assume that there is no jitter when taking the picture, and the captured picture is not blurred;

[0050] 3) Assume that the shooting field of view angle is large enough and the shooting distance is appropriate, and the captured picture includes the entire transposed conductor.

[0051] 4) Assume that the welded point of the transposed conductor is placed in the middle of the picture, and the transposed conductor is horizontally placed in the picture.

[0052] In a preferred embodiment of the present invention, the surface defect model of the transposed conductor is trained using the YOLO algorithm, and this model can also be deployed on the background server.

[0053] Use the YOLO algorithm on the background server to detect the appearance surface quality defects of transposed conductors, and judge whether the appearance surface of the transposed conductors is flat and free of burrs. The surface defect model of the transposed conductor is a pre-trained detection model. The surface defects of the transposed conductor include: surface defects such as burrs, cracks, pores, holes, and rust. The above defect samples and defect-free sample images form the appearance surface defect dataset of the transposed conductor, and are randomly divided into a training set, a test set, and a validation set according to a ratio of 8:1:1 for training the surface defect model of the transposed conductor.

[0054] In a preferred embodiment of the present invention, visual inspection of the dimensions of the transposed conductor is performed on the transposed conductor without appearance surface quality defects, specifically including:

[0055] S21: In the original image corresponding to the transposed conductor without appearance surface quality defects, use the first segmentation method to segment and obtain the first transposed conductor image, and the first transposed conductor image is a transposed conductor image that does not include the welding point;

[0056] S22: Obtain the width of the transposed conductor in the first transposed conductor image;

[0057] S23: In the original image corresponding to the transposed conductor without appearance surface quality defects, use the second segmentation method to segment and obtain the second transposed conductor image, and the second transposed conductor image is a transposed conductor image that includes the welding point;

[0058] S24: Obtain the size of the welding point in the second transposed conductor image.

[0059] This embodiment aims to perform quality inspection on the selected transposed conductors, and this quality inspection is determined based on the dimensions of the transposed conductors and the size of the welding points respectively. Therefore, this embodiment proposes a method for visual inspection of the dimensions of transposed conductors, and uses two segmentation methods to segment the required transposed conductor images from the images to facilitate obtaining the corresponding dimensions. Perform visual inspection of the dimensions of the transposed conductors with qualified appearance surface quality. According to the national standard requirements, the dimensions of the wide side and the narrow side of the transposed conductor after welding repair should not be greater than 1.5 times the original.

[0060] In a preferred embodiment of the present invention, the first segmentation method can adopt the HSV color space algorithm, and the second segmentation method can adopt the Grabcut graph cut algorithm. The following introduces the visual inspection of the dimensions of the transposed conductors using the two methods.

[0061] 1) Transposed conductor image segmentation: Use the HSV color space algorithm to segment the copper-colored transposed conductor from the scene for the transposed conductor with qualified appearance surface quality, and reasonably set the threshold to ensure that the copper-colored wire part that does not include the welding point is segmented.

[0062] The HSV color space algorithm is usually used to convert the RGB (Red, Green, Blue) color space to the HSV space. The HSV color space is widely used in the field of image processing, such as color filtering, object tracking, image segmentation, etc. Since it is more in line with human color perception, it is more effective than the RGB color space when dealing with color-related problems. This conversion involves the following steps: 1) Convert the R, G, B values in the RGB color space from the range of 0 - 255 to the range of 0 - 1; 2) Find the minimum and maximum values among the R, G, B values; 3) The calculation of hue depends on the maximum color value. If the maximum values are the same, the hue is 0. Otherwise, different formulas are calculated according to whether the maximum value is R, G, or B; 4) Saturation is the relative amount of the difference between the maximum and minimum RGB values. If the maximum value is 0 (i.e., black), the saturation is set to 0; 5) Value is directly equal to the maximum value among the RGB values.

[0063] 2) Visual measurement of the width of transposed conductors: Perform necessary preprocessing on the segmented image to convert the image into an image containing only black and white, where the transposed conductors are black and the background is white. Then, use horizontal projection to obtain the pixel values of each row, separately count the number of rows with pixel values greater than the threshold, and take the difference between the maximum value and the minimum value as the numerical value of the pixel points for the visual measurement of the width of the transposed conductors.

[0064] 3) Visual measurement of the size of the welding points of transposed conductors: Use the Grabcut graph cut algorithm on the original image to segment the transposed conductors from the complex background, and perform image preprocessing operations such as filtering and binarization on the image. Then, use horizontal projection to obtain the pixel values of each row, count the number of rows with pixel values greater than 0, and take the difference between the maximum value and the minimum value as the numerical value of the pixel points for the visual measurement of the size of the welding points of the transposed conductors.

[0065] In a preferred embodiment of the present invention, determining the welding quality of the transformer transposed conductors based on the detection results specifically includes:

[0066] Calculate the ratio of the size of the welding points to the width of the transposed conductors. If the ratio is within the set range, it is determined that the welding quality of the transformer transposed conductors is qualified; otherwise, it is unqualified. The set range can be that the ratio is not greater than 50%, that is, when the ratio is greater than 50%, the size of the welding points is unqualified.

[0067] In a preferred embodiment of the present invention, the augmented reality device further includes: a portable display device;

[0068] The portable display device is used to display the visual detection of the size of the transposed conductors and the welding quality of the transformer transposed conductors.

[0069] The measured data and warning information are transmitted back to the augmented reality device. After the optical-mechanical processing of the device completes imaging, light is coupled into the lens based on waveguide technology and enters the human eye through a series of refractions, enabling the operator to see the virtual information superimposed on the lens while also being able to see the real external world.

[0070] The present invention is applicable to transposed conductors of power transformers at various voltage levels and includes various transposed conductor welding methods, such as butt welding, inclined lap welding, stacked welding, etc., which are applicable to various actual situations, improving the practical use compatibility and efficiency.

[0071] Based on the same inventive concept, an embodiment of the present application also provides a device for detecting the welding quality of transposed conductors of a transformer based on augmented reality technology. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in the embodiment of the device for detecting the welding quality of transposed conductors of a transformer based on augmented reality technology provided below can refer to the limitations on the method for detecting the welding quality of transposed conductors of a transformer based on augmented reality technology in the above text, and will not be elaborated here.

[0072] Please refer to Figure 2 , the present invention provides a device for detecting the welding quality of transposed conductors of a transformer based on augmented reality technology, including:

[0073] An image acquisition module, which acquires an image of the welding joint of the transposed conductor of the power transformer through the augmented reality device;

[0074] An image recognition module, which is used to utilize a pre-trained surface defect model of the transposed conductor to recognize the image of the welding joint of the transposed conductor of the power transformer and screen out the transposed conductors without appearance surface quality defects;

[0075] A visual detection module, which is used to perform visual detection of the dimensions of the transposed conductor on the transposed conductor without appearance surface quality defects and determine the welding quality of the transposed conductor of the transformer based on the detection result. The visual detection of the dimensions of the transposed conductor is used to obtain the dimensions of the welding joint of the transposed conductor.

[0076] It should be noted that in a preferred embodiment of the present invention, the surface defect model of the transposed conductor is trained using the YOLO algorithm, and this model can also be deployed on the background server.

[0077] Use the YOLO algorithm on the background server to detect the appearance surface quality defects of transposed conductors, and judge whether the appearance surface of the transposed conductors is flat and free of burrs. The surface defect model of the transposed conductor is a pre-trained detection model. The surface defects of the transposed conductor include: surface defects such as burrs, cracks, pores, holes, and rust. The appearance surface defect dataset of the transposed conductor is composed of the above defect samples and defect-free samples, and is randomly divided into a training set, a test set, and a validation set according to a ratio of 8:1:1 for training the surface defect model of the transposed conductor.

[0078] In a preferred embodiment of the present invention, the vision detection module performs vision detection on the dimensions of the transposed conductor without appearance surface quality defects, specifically including:

[0079] S31: In the original image corresponding to the transposed conductor without appearance surface quality defects, use the first segmentation method to segment and obtain the first transposed conductor image, and the first transposed conductor image is a transposed conductor image that does not include the welding point;

[0080] S32: Obtain the width of the transposed conductor in the first transposed conductor image;

[0081] S33: In the original image corresponding to the transposed conductor without appearance surface quality defects, use the second segmentation method to segment and obtain the second transposed conductor image, and the second transposed conductor image is a transposed conductor image that includes the welding point;

[0082] S34: Obtain the size of the welding point in the second transposed conductor image.

[0083] This embodiment aims to perform quality detection on the selected transposed conductors. This quality detection is determined based on the dimensions of the transposed conductors and the size of the welding points respectively. Therefore, this embodiment proposes a vision detection method for the dimensions of the transposed conductors, and uses two segmentation methods respectively to segment the required transposed conductor images from the image to facilitate obtaining the corresponding dimensions. Perform vision detection on the dimensions of the transposed conductors with qualified appearance surface quality. According to the national standard requirements, the dimensions of the wide side and the narrow side of the transposed conductor after welding repair should not be greater than 1.5 times the original.

[0084] In a preferred embodiment of the present invention, the vision detection module determines the welding quality of the transformer transposed conductor based on the detection result, specifically including:

[0085] Calculate the ratio of the size of the welding point to the width of the transposed conductor. If the ratio is within the set range, it is determined that the welding quality of the transformer transposed conductor is qualified; otherwise, it is unqualified. The set range can be that the ratio is not greater than 50%, that is, when the ratio is greater than 50%, the size of the welding point is unqualified.

[0086] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the system is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of this application. The specific working process of the units and modules in the above system can refer to the corresponding process in the foregoing method embodiment and will not be elaborated here.

[0087] Please refer to Figure 3 , an embodiment of the present invention further provides a computer device 3, including: a memory 302, a processor 301, and a computer program 303 stored on the memory 302. When the computer program 303 is executed on the processor 301, it implements the method for detecting the welding quality of transformer transposition wires based on augmented reality technology as described in any one of the above methods.

[0088] The computer device 3 may be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The computer device 3 may include, but is not limited to, a processor 301 and a memory 302. Those skilled in the art can understand that Figure 3 merely an example of the computer device 3, which does not constitute a limitation on the computer device 3, and may include more or fewer components than shown in the figure, or combine some components, or different components. For example, it may also include input / output devices, network access devices, etc.

[0089] The so-called processor 301 may be a central processing unit (CPU), and the processor 301 may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0090] In some embodiments, the memory 302 may be an internal storage unit of the computer device 3, such as the hard disk or memory of the computer device 3. In other embodiments, the memory 302 may also be an external storage device of the computer device 3, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. equipped on the computer device 3. Further, the memory 302 may also include both the internal storage unit and the external storage device of the computer device 3. The memory 302 is used to store an operating system, application programs, a BootLoader, data, and other programs, such as the program code of the computer program. The memory 302 may also be used to temporarily store data that has been output or is to be output.

[0091] An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is run by a processor, it implements the method for detecting the welding quality of transformer transposition wires based on augmented reality technology as described in any one of the above methods.

[0092] In this embodiment, if the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above embodiment methods of the present application, a computer program can be used to instruct relevant hardware to complete. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, it can implement the steps of the above various method embodiments. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, an executable file, or some intermediate form, etc. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the photographing device / terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk, or an optical disc, etc. In some jurisdictions, according to legislation and patent practice, the computer-readable medium cannot be an electrical carrier signal and a telecommunication signal.

[0093] In the above embodiments, the descriptions of the various embodiments have their own emphases. For parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0094] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0095] In the embodiments disclosed in this application, it should be understood that the disclosed apparatus / terminal device and method can be implemented in other ways. For example, the apparatus / terminal device embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces. The indirect coupling or communication connection of the device or unit can be in an electrical, mechanical or other form.

[0096] The above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments or equivalently replace some of the technical features. These modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A transformer transposed conductor welding quality detection method based on augmented reality technology, characterized in that: The steps include: Acquire the image of the welding position of the transposed conductor of the power transformer through the augmented reality device; Using a pre-trained transposed conductor surface defect model, the image of the transposed conductor welding position of the power transformer is identified to screen out transposed conductors without appearance surface quality defects; Performing visual inspection of the transposed conductor size on the transposed conductor without appearance surface quality defects, and determining the welding quality of the transformer transposed conductor based on the inspection result, wherein the visual inspection of the transposed conductor size is used to obtain the size of the transposed conductor welding part; Determine the welding quality of the transformer transposed conductor based on the test results, including: The ratio of the welding point size to the transposed conductor width is calculated. If the ratio is within a set range, the welding quality of the transformer transposed conductor is determined to be qualified. If the ratio is not within the set range, the welding quality of the transformer transposed conductor is determined to be unqualified.

2. The transformer transposed conductor welding quality detection method based on augmented reality technology according to claim 1 is characterized in that: The transposed conductor without appearance surface quality defects is subjected to visual inspection of the transposed conductor size, including: In the original image corresponding to the transposed conductor without appearance surface quality defects, a first transposed conductor image is obtained by segmenting using a first segmentation method, wherein the first transposed conductor image is a transposed conductor image that does not include a welding point; Acquire the transposed conductor width in the first transposed conductor image; In the original image corresponding to the transposed conductor without appearance surface quality defects, a second transposed conductor image is obtained by segmenting using a second segmentation method, wherein the second transposed conductor image is a transposed conductor image including a welding point; The size of the welding point in the second transposed conductor image is obtained.

3. The transformer transposed conductor welding quality detection method based on augmented reality technology according to claim 1 is characterized in that: The setting range is that the ratio is not greater than 50%.

4. The transformer transposed conductor welding quality detection method based on augmented reality technology according to claim 1 is characterized in that: The transposed conductor surface defect model is deployed on a server.

5. The transformer transposed conductor welding quality detection method based on augmented reality technology according to claim 4 is characterized in that: The augmented reality device further includes: a communication device; The augmented reality device sends the image of the welding location of the transposed conductor of the power transformer to the server through the communication device.

6. The transformer transposed conductor welding quality detection method based on augmented reality technology according to claim 1 is characterized in that: The augmented reality device further includes: a portable display device; The portable display device is used to display the visual inspection of the transposed conductor size and the welding quality of the transformer transposed conductor.

7. A transformer transposed conductor welding quality detection device based on augmented reality technology, characterized in that: include: An image acquisition module, which acquires images of the welding locations of the transposed conductors of the power transformer through an augmented reality device; An image recognition module is used to recognize the image of the welding part of the transposed conductor of the power transformer by using a pre-trained transposed conductor surface defect model, and screen out transposed conductors without appearance surface quality defects; A visual inspection module, used to perform a visual inspection of the transposed conductor size on the transposed conductor without appearance surface quality defects, and determine the welding quality of the transformer transposed conductor based on the inspection result, wherein the visual inspection of the transposed conductor size is used to obtain the size of the transposed conductor welding part; Determine the welding quality of the transformer transposed conductor based on the test results, including: The ratio of the welding point size to the transposed conductor width is calculated. If the ratio is within a set range, the welding quality of the transformer transposed conductor is determined to be qualified. If the ratio is not within the set range, the welding quality of the transformer transposed conductor is determined to be unqualified.

8. A computer device, characterized in that: The device comprises a processor and a memory: The memory is used to store a computer program and send instructions of the computer program to the processor; The processor executes a transformer transposed conductor welding quality detection method based on augmented reality technology according to any one of claims 1 to 6 according to the instructions of the computer program.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the method for detecting welding quality of transformer transposed conductors based on augmented reality technology according to any one of claims 1 to 6 is implemented.

Images