Welding quality detection method and system based on new energy automobile aluminum profile

Abstract

The invention is suitable for the technical field of quality management, and provides a welding quality detection method and system based on a new energy automobile aluminum profile, and the method comprises the steps: obtaining the real-time welding line image information and reference welding line image information of a to-be-detected object based on a camera, and then carrying out the detection of the welding quality of the to-be-detected object through a target detection algorithm according to the real-time welding line image information; according to the method, real-time welding seam area information is accurately determined, meanwhile, reference welding seam area information is accurately determined according to reference welding seam image information, and finally, the real-time welding seam area information and the reference welding seam area information are obtained. According to the method, the welding quality result information can be effectively generated, so that manual detection links are reduced, the stability and consistency of the welding quality of the aluminum profile frame of the new energy automobile are effectively improved, the reliability of overall welding processing is remarkably enhanced, errors and uncertainty caused by human factors are reduced, and the production efficiency is improved. And the increasingly stringent quality standard requirements are met, so that the improvement of the production efficiency and the control of the cost are promoted.

Description

Technical Field

[0001] This application relates to the technical field of quality management, and more specifically, to a welding quality inspection method and system for aluminum profiles used in new energy vehicles. Background Technology

[0002] Because aluminum alloys have a density that is about one-third that of steel, and after proper design and advanced processing technology, they can not only provide sufficient structural strength and rigidity to meet the stringent requirements of new energy vehicles for vehicle body safety and durability, but also significantly reduce the overall vehicle weight, thereby improving range and energy efficiency. Therefore, aluminum alloys are increasingly widely used in new energy vehicles.

[0003] Currently, the quality inspection of aluminum profiles for new energy vehicles at their weld joints usually relies on manual methods, which is difficult to meet the high-precision and high-reliability welding quality requirements and has a low reliability problem, which needs to be further improved. Summary of the Invention

[0004] Based on this, this application provides a welding quality inspection method and system for aluminum profiles used in new energy vehicles, in order to solve the problem of low reliability in the prior art.

[0005] In a first aspect, embodiments of this application provide a method for inspecting the welding quality of aluminum profiles used in new energy vehicles, the method comprising: Based on a preset camera, real-time weld seam image information and reference weld seam image information of the object to be inspected are acquired; Based on a preset target detection algorithm, real-time weld area information is determined according to the real-time weld image information, and reference weld area information is determined according to the reference weld image information. Based on the real-time weld area information and the reference weld area information, weld quality result information is generated.

[0006] Compared with existing technologies, the beneficial effects are as follows: The welding quality inspection method based on aluminum profiles for new energy vehicles provided in this application allows the terminal device to first quickly acquire real-time weld seam image information and reference weld seam image information of the object to be inspected based on a camera. Then, using a target detection algorithm, the real-time weld seam area information is accurately determined based on the real-time weld seam image information, and the reference weld seam area information is accurately determined based on the reference weld seam image information. Finally, the welding quality result information is effectively generated based on the real-time weld seam area information and the reference weld seam area information. This reduces the need for manual inspection, helps meet the welding quality requirements of aluminum profile frames for new energy vehicles, significantly improves reliability, and to a certain extent solves the problem of low reliability currently.

[0007] Secondly, embodiments of this application provide a welding quality inspection system based on aluminum profiles for new energy vehicles, the system comprising: Weld seam image information acquisition module: used to acquire real-time weld seam image information and reference weld seam image information of the object to be inspected based on a preset camera; Weld area information determination module: used to determine real-time weld area information based on the real-time weld image information according to the preset target detection algorithm, and to determine reference weld area information according to the reference weld image information; Welding quality result information generation module: used to generate welding quality result information based on the real-time weld area information and the reference weld area information.

[0008] Thirdly, embodiments of this application provide a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method described in the first aspect above.

[0009] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method described in the first aspect above.

[0010] It is understood that the beneficial effects of the second to fourth aspects mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below.

[0012] Figure 1 This is a schematic flowchart of a welding quality inspection method provided in an embodiment of this application; Figure 2 This is a flowchart illustrating step S200 in a welding quality inspection method provided in an embodiment of this application; Figure 3 This is a schematic flowchart of step S300 in a welding quality inspection method provided in an embodiment of this application; Figure 4 This is a schematic diagram of the first process after step S300 in a welding quality inspection method provided in an embodiment of this application; Figure 5 This is a schematic diagram of the second process after step S300 in the welding quality inspection method provided in an embodiment of this application; Figure 6 This is a schematic diagram of a highlighted mark provided in an embodiment of this application; Figure 7 This is a block diagram of a welding quality inspection system provided in one embodiment of this application; Figure 8 This is a schematic diagram of a terminal device provided in an embodiment of this application. Detailed Implementation

[0013] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0014] In the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0015] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0016] To illustrate the technical solution described in this application, specific embodiments are provided below.

[0017] Please see Figure 1 , Figure 1 This is a flowchart illustrating the welding quality inspection method for aluminum profiles used in new energy vehicles, provided in this embodiment. In this embodiment, the entity executing the welding quality inspection method is a terminal device. It is understood that the types of terminal devices include, but are not limited to, mobile phones, tablets, laptops, Ultra-Mobile Personal Computers (UMPCs), netbooks, and Personal Digital Assistants (PDAs). This embodiment does not impose any restrictions on the specific type of terminal device.

[0018] Please see Figure 1The welding quality inspection method provided in this application includes, but is not limited to, the following steps: In S100, real-time weld seam image information and reference weld seam image information of the object to be inspected are acquired based on a preset camera.

[0019] Specifically, the terminal device can first acquire real-time weld seam image information and reference weld seam image information of the object to be inspected based on a preset camera. The object to be inspected can be an aluminum profile frame whose weld quality is to be inspected, or multiple aluminum profiles that make up the aluminum profile frame, or any multiple aluminum profiles used in new energy vehicles, or aluminum profiles with cavities. It should be noted that the specific size and shape of the aluminum profile are not limited.

[0020] Without loss of generality, real-time weld image information is used to describe images obtained by taking pictures of the weld seam of the object to be inspected; reference weld image information is used to describe images obtained by taking pictures of the weld seam of an aluminum profile frame of the same model as the object to be inspected, provided that the weld quality is qualified.

[0021] In S200, based on a preset target detection algorithm, real-time weld area information is determined according to real-time weld image information, and reference weld area information is determined according to reference weld image information.

[0022] Specifically, after the terminal device acquires real-time weld seam image information and reference weld seam image information, the terminal device can effectively determine the real-time weld seam area information based on the real-time weld seam image information and the reference weld seam area information based on the reference weld seam image information, using a preset target detection algorithm.

[0023] In some possible implementations, for determining the reference weld area information, please refer to [link / reference]. Figure 2 Step S200 includes, but is not limited to, the following steps: In S210, based on a preset edge detection algorithm, first outer contour edge information is generated according to real-time weld seam image information, and second outer contour edge information is generated according to reference weld seam area information.

[0024] Specifically, after the terminal device acquires real-time weld seam image information and reference weld seam image information, the terminal device can generate first outer contour edge information based on the real-time weld seam image information and second outer contour edge information based on the reference weld seam region information, using a preset edge detection algorithm. The edge detection algorithm can be based on the Sobel algorithm, the Prewitt algorithm, or the Zero-Crossing method. The first outer contour edge information is used to describe the edge contour lines in the real-time weld seam image information, and the second outer contour edge information is used to describe the edge contour lines in the reference weld seam region information.

[0025] In S220, based on a preset target detection algorithm, the first weld edge information is determined according to the first outer contour edge information, and the second weld edge information is determined according to the second outer contour edge information.

[0026] Specifically, after the terminal device generates the first outer contour edge information and the second outer contour edge information, the terminal device can determine the first weld edge information based on the first outer contour edge information and the second weld edge information based on the second outer contour edge information, according to a preset target detection algorithm. The target detection algorithm can be R-CNN algorithm, Faster R-CNN algorithm, or Mask R-CNN algorithm. The first weld edge information is used to describe the edge line corresponding to the weld in the real-time weld image information. The second weld edge information is used to describe the edge line corresponding to the weld in the reference weld area information.

[0027] In S230, real-time weld area information is generated based on the first weld edge information, and reference weld area information is generated based on the second weld edge information.

[0028] Specifically, after the terminal device determines the first weld edge information and the second weld edge information, the terminal device can generate real-time weld area information based on the first weld edge information, and at the same time generate reference weld area information based on the first weld edge information. The real-time weld area information is used to describe the closed area enclosed by the first weld edge information, and the reference weld area information is used to describe the closed area enclosed by the second weld edge information.

[0029] In S300, welding quality result information is generated based on real-time weld area information and reference weld area information.

[0030] Specifically, after the terminal device generates real-time weld area information and reference weld area information, the terminal device can accurately generate welding quality result information based on the real-time weld area information and reference weld area information. The welding quality result information is either quality qualified information or quality abnormal information. Quality qualified information is used to describe that the welding quality corresponding to the weld of the aluminum profile frame is qualified. Quality abnormal information is used to describe that the welding quality corresponding to the weld of the aluminum profile frame is abnormal.

[0031] In some possible implementations, for accurate generation of weld quality result information, please refer to [link / reference]. Figure 3 Step S300 includes, but is not limited to, the following steps: In S310, the overlapping area information is determined based on the real-time weld area information and the reference weld area information.

[0032] Specifically, the terminal device can effectively determine the overlapping area information based on the real-time weld area information and the reference weld area information. The overlapping area information is used to describe the area that overlaps between the real-time weld area information and the reference weld area information.

[0033] In S320, the overlapping area information is determined based on the overlapping area information, and the real-time weld area information is determined based on the real-time weld area information.

[0034] Specifically, after the terminal device determines the overlapping area information, it can determine the overlapping area area information based on the overlapping area information, and determine the real-time weld area area information based on the real-time weld area information. The overlapping area area information describes the area of ​​the overlapping area information, and the real-time weld area area information describes the area of ​​the real-time weld area information. It should be noted that even if both the overlapping area information and the real-time weld area information are irregular shapes, their areas can still be calculated using existing technologies, so this will not be elaborated upon.

[0035] In S330, the area overlap rate information is generated based on the overlapping area information and the real-time weld area information.

[0036] Specifically, after the terminal device determines the overlapping area information and the real-time weld area information, the terminal device can generate the area overlap rate information based on the overlapping area information and the real-time weld area information. The area overlap rate information can be the quotient of the overlapping area information divided by the real-time weld area information.

[0037] In S340, the region overlap rate information is compared with the preset overlap rate threshold information.

[0038] Specifically, after the terminal device generates the regional overlap rate information, the terminal device can compare the regional overlap rate information with the preset overlap rate threshold information. The specific value of the overlap rate threshold information can be predefined by the operation and maintenance personnel, such as 0.95.

[0039] In S350, if the regional overlap rate information is greater than or equal to the overlap rate threshold information, the welding quality result information is determined to be qualified; otherwise, the welding quality result information is determined to be abnormal.

[0040] Specifically, if the regional overlap rate information is greater than or equal to the overlap rate threshold information, the welding quality result information is determined to be of acceptable quality; if the regional overlap rate information is less than the overlap rate threshold information, the welding quality result information is determined to be of abnormal quality.

[0041] In some possible implementations, to facilitate the identification of areas where weld quality problems frequently occur, please refer to [link / reference needed]. Figure 4 If the welding quality result information is abnormal, then after step S300, the method further includes, but is not limited to, the following steps: In S400, real-time difference area information is generated based on the reference weld area information and the overlapping area information.

[0042] Specifically, the terminal device can generate real-time difference area information based on the reference weld area information and the overlapping area information. The real-time difference area information is used to describe the areas in the reference weld area information other than the overlapping area information.

[0043] In S410, information on multiple historical difference regions is obtained based on a preset sampling time period.

[0044] Specifically, after the terminal device generates real-time difference area information, the terminal device can obtain multiple historical difference area information based on a preset sampling time period. The specific duration of the sampling time period can be predefined by the operation and maintenance personnel, such as three days or one week. The historical difference area information is used to describe the areas where welding quality problems occurred in the historical welding process within the sampling time period.

[0045] In S420, it is determined whether the real-time difference area information overlaps with a specified number of historical difference area information.

[0046] Specifically, after the terminal device acquires multiple historical difference area information, the terminal device can determine whether the real-time difference area information overlaps with a specified number of historical difference area information. The specific number of historical difference area information can be predefined by the operation and maintenance personnel, such as five or ten.

[0047] In S430, if the real-time difference area information overlaps with a specified number of historical difference area information, then the real-time difference area information is determined to be the core defect area information.

[0048] Specifically, if the real-time difference area information overlaps with a specified number of historical difference area information, it indicates that the welding area corresponding to the real-time difference area information frequently has welding quality problems. Therefore, the terminal device can determine the real-time difference area information as the core defect area information, which is conducive to the operation and maintenance personnel to optimize the welding process in a targeted manner.

[0049] In some possible implementations, to facilitate the optimization of welding processes using big data, please refer to [link / reference]. Figure 5 After step S300, the method further includes, but is not limited to, the following steps: In S500, the object number information of the object to be detected is obtained.

[0050] Specifically, the terminal device can obtain the object number information of the object to be detected, whereby the object number information is used to describe the unique number of the object to be detected.

[0051] In S510, based on real-time difference region information, the real-time weld seam image information is marked to generate difference marked image information.

[0052] For example, please refer to Figure 6 After the terminal device obtains the object number information, it can mark the real-time weld image information based on the real-time difference region information, highlighting the real-time difference region information in the real-time weld image information. Figure 6 The area selected by the rectangle is quickly used to generate difference marker image information.

[0053] In S520, a comparison image set is generated based on the difference marker image information and the reference weld image information.

[0054] Specifically, after the terminal device generates the difference mark image information, the terminal device can generate comparison image set information based on the difference mark image information and the reference weld image information. The comparison image set information is used to describe the image set containing the difference mark image information and the reference weld image information.

[0055] In S530, object number information and comparison image set information are sent to the designated terminal.

[0056] Specifically, after the terminal device generates the comparison image set information, the terminal device can send the object number information and the comparison image set information to the designated terminal, where the designated terminal is used to describe the corresponding terminal of the operation and maintenance personnel.

[0057] The implementation principle of the welding quality inspection method for aluminum profiles of new energy vehicles in this application embodiment is as follows: The terminal device can first quickly acquire real-time weld seam image information and reference weld seam image information of the object to be inspected based on a camera. Then, using a target detection algorithm, the real-time weld seam area information is accurately determined based on the real-time weld seam image information. At the same time, the reference weld seam area information is accurately determined based on the reference weld seam image information. Finally, the welding quality result information is effectively generated based on the real-time weld seam area information and the reference weld seam area information. This reduces the manual inspection process, meets the requirements for high-precision and high-reliability welding quality, and significantly improves reliability.

[0058] It should be noted that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0059] Embodiments of this application also provide a welding quality inspection system based on aluminum profiles for new energy vehicles. For ease of explanation, only the parts relevant to this application are shown, such as... Figure 7 As shown, the system 70 includes: Weld seam image information acquisition module 71: used to acquire real-time weld seam image information and reference weld seam image information of the object to be inspected based on a preset camera; Weld area information determination module 72: is used to determine real-time weld area information based on a preset target detection algorithm and real-time weld image information, and to determine reference weld area information based on reference weld image information; Welding quality result information generation module 73: used to generate welding quality result information based on real-time weld area information and reference weld area information.

[0060] Optionally, the weld area information determination module 72 mentioned above includes: Outer contour edge information generation submodule: Based on a preset edge detection algorithm, it generates first outer contour edge information according to real-time weld image information, and generates second outer contour edge information according to reference weld area information; Weld edge information determination submodule: used to determine the first weld edge information based on the first outer contour edge information and the second weld edge information based on the second outer contour edge information, according to the preset target detection algorithm; The weld area information generation submodule is used to generate real-time weld area information based on the first weld edge information and to generate reference weld area information based on the second weld edge information. The real-time weld area information is used to describe the closed area enclosed by the first weld edge information, and the reference weld area information is used to describe the closed area enclosed by the second weld edge information.

[0061] Optionally, the welding quality result information can be either quality qualified information or quality abnormal information; the aforementioned welding quality result information generation module 73 includes: Overlapping area information determination submodule: used to determine overlapping area information based on real-time weld area information and reference weld area information; The area information determination submodule is used to determine the area information of overlapping areas based on the overlapping area information, and to determine the area information of real-time weld seam areas based on the real-time weld seam area information. The regional overlap rate information generation submodule is used to generate regional overlap rate information based on the overlapping area information and the real-time weld area information. Regional overlap rate information comparison submodule: used to compare regional overlap rate information with preset overlap rate threshold information; The welding quality result information determination submodule is used to determine the welding quality result information as qualified if the regional overlap rate information is greater than or equal to the overlap rate threshold information, and otherwise determine the welding quality result information as abnormal.

[0062] Optionally, if the welding quality result information is abnormal, the system 70 further includes: Real-time difference region information generation module: used to generate real-time difference region information based on the reference weld region information and the overlapping region information. The real-time difference region information is used to describe the region in the reference weld region information other than the overlapping region information. Historical difference area information acquisition module: used to acquire information on multiple historical difference areas based on a preset sampling time period; Real-time difference region information judgment module: used to determine whether the real-time difference region information overlaps with a specified number of historical difference region information; Core Defect Area Information Determination Module: If the real-time difference area information overlaps with a specified number of historical difference area information, then the real-time difference area information is determined to be the core defect area information.

[0063] Optionally, the system 70 also includes: Object ID Information Acquisition Module: Used to acquire the object ID information of the object to be detected; Difference Marking Image Information Generation Module: Used to mark real-time weld seam image information based on real-time difference region information, and generate difference marking image information; Image set information generation module: used to generate comparison image set information based on difference marker image information and reference weld image information; Object ID Information Sending Module: Used to send object ID information and comparison image set information to a designated terminal.

[0064] It should be noted that the information interaction and execution process between the above modules are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, which will not be repeated here.

[0065] This application also provides a terminal device, such as... Figure 8 As shown, the terminal device 80 of this embodiment includes: a processor 81, a memory 82, and a computer program 83 stored in the memory 82 and executable on the processor 81. When the processor 81 executes the computer program 83, it implements the steps in the above-described welding quality inspection method embodiment, for example... Figure 1 Steps S100 to S300 are shown; or, when processor 81 executes computer program 83, it implements the functions of each module in the above-described device, for example... Figure 7The functions of modules 71 to 73 are shown.

[0066] The terminal device 80 can be a desktop computer, laptop, handheld computer, cloud server, or other computing device, and includes, but is not limited to, a processor 81 and a memory 82. Those skilled in the art will understand that... Figure 8 This is merely an example of terminal device 80 and does not constitute a limitation on terminal device 80. It may include more or fewer components than shown, or combine certain components, or different components. For example, terminal device 80 may also include input / output devices, network access devices, buses, etc.

[0067] The processor 81 can be a central processing unit (CPU), or 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 can be a microprocessor or any conventional processor, etc.

[0068] The memory 82 can be an internal storage unit of the terminal device 80, such as a hard disk or memory of the terminal device 80. The memory 82 can also be an external storage device of the terminal device 80, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the terminal device 80. Furthermore, the memory 82 can include both internal storage units and external storage devices of the terminal device 80. The memory 82 can also store computer program 83 and other programs and data required by the terminal device 80. The memory 82 can also be used to temporarily store data that has been output or will be output.

[0069] One embodiment of this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable medium can include any entity or device capable of carrying computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, 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, etc.

[0070] The above are all preferred embodiments of this application, and are not intended to limit the scope of protection of this application. Therefore, all equivalent changes made in accordance with the methods, principles and structures of this application should be covered within the scope of protection of this application.

Claims

1. A method for detecting the welding quality of a new energy vehicle aluminum profile, characterized in that, The method includes: Based on a preset camera, real-time weld seam image information and reference weld seam image information of the object to be inspected are acquired; Based on a preset target detection algorithm, real-time weld area information is determined according to the real-time weld image information, and reference weld area information is determined according to the reference weld image information. Based on the real-time weld area information and the reference weld area information, weld quality result information is generated.

2. The method according to claim 1, characterized in that, The preset target detection algorithm determines real-time weld region information based on the real-time weld image information and determines reference weld region information based on the reference weld image information, including: Based on a preset edge detection algorithm, first outer contour edge information is generated according to the real-time weld image information, and second outer contour edge information is generated according to the reference weld area information. Based on a preset target detection algorithm, the first weld edge information is determined according to the first outer contour edge information, and the second weld edge information is determined according to the second outer contour edge information. Based on the first weld edge information, the real-time weld area information is generated, and based on the second weld edge information, the reference weld area information is generated. The real-time weld area information is used to describe the closed area enclosed by the first weld edge information, and the reference weld area information is used to describe the closed area enclosed by the second weld edge information.

3. The method according to claim 1, characterized in that, The welding quality result information is either quality qualified information or quality abnormal information; the step of generating welding quality result information based on the real-time weld area information and the reference weld area information includes: Based on the real-time weld area information and the reference weld area information, the overlapping area information is determined; Based on the overlapping area information, the overlapping area area information is determined, and based on the real-time weld area information, the real-time weld area area information is determined. Based on the overlapping area information and the real-time weld area information, the area overlap rate information is generated; Compare the region overlap rate information with the preset overlap rate threshold information; If the overlap rate information of the region is greater than or equal to the overlap rate threshold information, then the welding quality result information is determined to be qualified; otherwise, the welding quality result information is determined to be abnormal.

4. The method according to claim 3, characterized in that, If the weld quality result information is abnormal, then after generating the weld quality result information based on the real-time weld area information and the reference weld area information, the method further includes: Based on the reference weld area information and the overlapping area information, real-time difference area information is generated, wherein the real-time difference area information is used to describe the area in the reference weld area information other than the overlapping area information. Based on a preset sampling time period, information on multiple historical difference areas is obtained; Determine whether the real-time difference region information overlaps with a specified number of historical difference region information; If the real-time difference region information overlaps with a specified number of historical difference region information, then the real-time difference region information is determined to be core defect region information.

5. The method according to claim 4, characterized in that, After generating weld quality result information based on the real-time weld area information and the reference weld area information, the method further includes: Obtain the object number information of the object to be detected; Based on the real-time difference region information, the real-time weld image information is marked to generate difference marked image information; Based on the difference marker image information and the reference weld image information, a comparison image set information is generated; The object number information and the comparison image set information are sent to the designated terminal.

6. A welding quality inspection system based on aluminum profiles for new energy vehicles, characterized in that, The system includes: Weld seam image information acquisition module: used to acquire real-time weld seam image information and reference weld seam image information of the object to be inspected based on a preset camera; Weld area information determination module: used to determine real-time weld area information based on the real-time weld image information according to the preset target detection algorithm, and to determine reference weld area information according to the reference weld image information; Welding quality result information generation module: used to generate welding quality result information based on the real-time weld area information and the reference weld area information.

7. The system according to claim 6, characterized in that, The welding quality result information is either quality qualified information or quality abnormal information; the welding quality result information generation module includes: Overlapping area information determination submodule: used to determine overlapping area information based on the real-time weld area information and the reference weld area information; The area information determination submodule is used to determine the area information of the overlapping area based on the overlapping area information, and to determine the area information of the real-time weld area based on the real-time weld area information. Regional overlap rate information generation submodule: used to generate regional overlap rate information based on the overlapping region area information and the real-time weld area information; Regional overlap rate information comparison submodule: used to compare the regional overlap rate information with the preset overlap rate threshold information; The welding quality result information determination submodule is used to determine the welding quality result information as qualified if the overlap rate information of the region is greater than or equal to the overlap rate threshold information, and otherwise determine the welding quality result information as abnormal.

8. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 5.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 5.

Images