Defect identification method and system based on new energy automobile profile

Abstract

The invention is suitable for the technical field of aluminum profile defect detection, and provides a defect identification method and system based on a new energy automobile profile, and the method comprises the steps: firstly, based on an image sensor, rapidly obtaining the internal image information and geometric dimension information of a cavity of a to-be-detected profile; then generating invisible defect detection result information according to a target detection algorithm and the internal image information of the cavity, then effectively generating size defect detection result information according to the geometric size information and preset reference size information, and finally determining the size defect of the cavity according to the invisible defect detection result information and the size defect detection result information. And defect comprehensive evaluation information is accurately generated. According to the method, efficient real-time monitoring can be carried out on the interior of the cavity of the aluminum profile, the invisible defects are accurately recognized, reliable capture of the invisible defects is achieved, continuous optimization of the aluminum profile production process and the overall quality is facilitated, and important guarantee is provided for safety and long-term reliability of key structural parts of new energy automobiles.

Description

Technical Field

[0001] This application relates to the technical field of aluminum profile defect detection, and more specifically, to a defect identification method and system based on new energy vehicle profiles. Background Technology

[0002] Since the quality of aluminum profiles for new energy vehicles directly affects the vehicle's lightweight design and energy efficiency, which in turn affects its driving range and energy consumption, it is crucial to accurately identify defects in aluminum profiles for new energy vehicles.

[0003] Currently, the quality assessment of aluminum profiles for new energy vehicles mainly relies on manual inspection. However, inspectors are prone to fatigue, which leads to decreased attention and affects the accuracy of the inspection. Furthermore, manual inspection is also affected by subjective judgment. Different inspectors may have different assessments of the same defect, resulting in poor inspection results, which needs further improvement. Summary of the Invention

[0004] Based on this, this application provides a defect identification method and system for new energy vehicle profiles to solve the problem of poor detection effect in the prior art.

[0005] In a first aspect, embodiments of this application provide a defect identification method based on new energy vehicle profiles, the method comprising: Based on a preset image sensor, image information and geometric dimension information of the cavity inside the profile to be inspected are acquired; Based on the preset target detection algorithm and the cavity interior image information, a hidden defect detection result information is generated, wherein the hidden defect detection result information is a first qualified information or a first defect existence information; Based on the geometric dimension information and the preset reference dimension information, dimension defect detection result information is generated, wherein the dimension defect detection result information is a second qualified information or a second defect-existing information; Based on the hidden defect detection results and the dimensional defect detection results, a comprehensive defect assessment is generated.

[0006] Compared with existing technologies, the beneficial effects are as follows: The defect identification method based on new energy vehicle profiles provided in this application allows the terminal device to quickly acquire the internal image information and geometric dimension information of the cavity of the profile to be inspected based on a preset image sensor. Then, based on a preset target detection algorithm and the internal image information of the cavity, it efficiently generates hidden defect detection result information. Next, based on the geometric dimension information and preset reference dimension information, it effectively generates dimensional defect detection result information. Finally, based on the hidden defect detection result information and the dimensional defect detection result information, it accurately generates comprehensive defect evaluation information, thereby achieving automatic and accurate judgment of the product quality of aluminum profiles for new energy vehicles, improving the detection effect, significantly improving the comprehensiveness and reliability of hidden defect detection inside the cavity of aluminum profiles, and solving the problem of poor detection effect to a certain extent.

[0007] Secondly, embodiments of this application provide a defect identification system based on new energy vehicle profiles, the system comprising: Cavity interior image information acquisition module: used to acquire cavity interior image information and geometric dimension information of the profile to be inspected based on a preset image sensor; Hidden defect detection result information generation module: used to generate hidden defect detection result information based on a preset target detection algorithm and the cavity interior image information, wherein the hidden defect detection result information is first qualified information or first defect existence information; Dimensional defect detection result information generation module: used to generate dimensional defect detection result information based on the geometric dimension information and preset reference dimension information, wherein the dimensional defect detection result information is a second qualified information or a second defective information; Defect Comprehensive Assessment Information Generation Module: Used to generate comprehensive defect assessment information based on the hidden defect detection results and dimensional defect detection results.

[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 defect identification method provided in an embodiment of this application; Figure 2 This is a flowchart illustrating step S200 in a defect identification method provided in an embodiment of this application; Figure 3 This is a flowchart illustrating step S300 in a defect identification method provided in an embodiment of this application; Figure 4 This is a flowchart illustrating step S400 in a defect identification method provided in an embodiment of this application; Figure 5 This is a flowchart illustrating the process after step S400 in a defect identification method provided in an embodiment of this application; Figure 6 This is a block diagram of a defect identification system provided in an embodiment of this application; Figure 7 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 defect identification method based on new energy vehicle profiles provided in this embodiment. In this embodiment, the execution subject of the defect identification 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, Personal Digital Assistants (PDAs), etc. This embodiment does not impose any restrictions on the specific type of terminal device.

[0018] Please see Figure 1 The defect identification method provided in this application includes, but is not limited to, the following steps: In S100, based on a preset image sensor, image information and geometric dimension information of the cavity inside the profile to be inspected are acquired.

[0019] Specifically, the terminal device can use a preset image sensor to capture images of the internal cavity of the profile to be inspected, quickly acquiring image information of the cavity. It can also use an infrared measuring device to obtain the geometric dimensions of the profile. The image sensor can be a preset miniature camera. The profile to be inspected is an aluminum profile used to describe whether there are any hidden defects. Hidden defects can include aluminum adhesion defects, scratches, peeling defects, abnormal roughness defects, and / or oil residue defects. Insufficient surface finish or wear of the aluminum profile mold can lead to aluminum adhesion defects. Hard particles entering the extrusion process with the aluminum material can lead to scratches. Inadequate cleaning of the extrusion cylinder surface or the presence of moisture or oil can lead to peeling defects. Low extrusion temperature resulting in poor aluminum material flow can lead to abnormal roughness defects. Oil residue in the mold can lead to oil residue defects.

[0020] Without loss of generality, the cavity interior image information is used to describe the image obtained by the image sensor taking pictures of the surface of the internal cavity of the profile to be inspected; the geometric dimension information is used to describe the specific dimensions of the profile to be inspected.

[0021] In S200, hidden defect detection results are generated based on the preset target detection algorithm and the image information inside the cavity.

[0022] Specifically, after the terminal device acquires the image information and geometric dimension information inside the cavity, the terminal device can generate hidden defect detection result information based on the preset target detection algorithm and the image information inside the cavity. The hidden defect detection result information is either first qualified information or first defective information.

[0023] In some possible implementations, to generate latent defect detection results information, please refer to [link / reference]. Figure 2 Step S200 includes, but is not limited to, the following steps: In S210, profile outline information is generated based on a preset contour extraction algorithm and the image information inside the cavity.

[0024] Specifically, after the terminal device acquires the image information and geometric dimension information inside the cavity, the terminal device can extract the contour lines in the image information inside the cavity based on a preset contour line extraction algorithm to quickly generate profile contour line information. The contour line extraction algorithm is the same as the target detection algorithm, and the contour line extraction algorithm can be the Suzuki algorithm.

[0025] In S220, based on the preset reference contour information, it is determined whether there are other contour lines besides the reference contour information in the profile contour information.

[0026] Specifically, after the terminal device generates profile outline information, it can determine whether there are other outlines besides the reference outline information based on the preset reference outline information.

[0027] In S220, if the profile outline information contains other outlines besides the reference outline information, the hidden defect detection result information is determined as the first existing defect information.

[0028] Specifically, if the profile outline information contains other outlines besides the reference outline information, it indicates that there are scratches on the surface of the profile to be inspected. Therefore, the terminal equipment can determine the hidden defect detection result information as the first defect information.

[0029] In S240, if the profile outline information does not contain any outlines other than the reference outline information, the hidden defect detection result information is determined as the first qualified information.

[0030] Specifically, if the profile outline information does not contain any outlines other than the reference outline information, it indicates that there are no scratches on the surface of the profile to be inspected. Therefore, the terminal equipment can determine the hidden defect detection result information as the first qualified information. In S300, dimensional defect detection result information is generated based on geometric dimension information and preset reference dimension information.

[0031] Specifically, after the terminal device generates the hidden defect detection result information, the terminal device can quickly generate the size defect detection result information based on the geometric size information and the preset reference size information. The size defect detection result information is either the second qualified information or the second defect information.

[0032] In some possible implementations, to generate dimensional defect detection results information, please refer to [link / reference]. Figure 3 Step S300 includes, but is not limited to, the following steps: In S310, the geometric dimension information is compared with the preset reference dimension information.

[0033] Specifically, the terminal device can compare geometric dimension information with preset reference dimension information, where the reference dimension information is the dimension corresponding to aluminum profiles that meet quality standards.

[0034] In S320, if the geometric dimension information is equal to the reference dimension information, then the dimension defect detection result information is determined as the second qualified information.

[0035] Specifically, if the geometric dimension information is equal to the reference dimension information, then the terminal equipment can determine the dimension defect detection result information as the second qualified information.

[0036] In S330, if the geometric dimension information is not equal to the reference dimension information, the dimension defect detection result information is determined as the second existing defect information.

[0037] Specifically, if the geometric dimension information is not equal to the reference dimension information, the terminal device can determine the dimension defect detection result information as the second existing defect information.

[0038] In S400, comprehensive defect assessment information is generated based on the results of hidden defect detection and dimensional defect detection.

[0039] Specifically, after the terminal device generates the dimensional defect detection result information, it can effectively generate comprehensive defect assessment information based on the hidden defect detection result information and the dimensional defect detection result information. The comprehensive defect assessment information includes qualified profile information, general abnormal information, or serious abnormal information. Qualified profile information describes that the product quality of the profile under test is qualified, general abnormal information describes that the product quality of the profile under test is generally unqualified, and serious abnormal information describes that the product quality of the profile under test is seriously unqualified.

[0040] In some possible implementations, to generate comprehensive defect assessment information, please refer to [link / reference]. Figure 4 Step S400 includes, but is not limited to, the following steps: In S410, if the hidden defect detection result is the first qualified information and the dimensional defect detection result is the second qualified information, then the comprehensive defect assessment information is determined to be qualified profile information.

[0041] Specifically, if the hidden defect detection result is the first qualified information and the dimensional defect detection result is the second qualified information, then the terminal equipment can efficiently determine the comprehensive defect assessment information as qualified profile information.

[0042] In S420, if the hidden defect detection result information is the first defect information and the dimensional defect detection result information is the second defect information, then the comprehensive defect assessment information is determined to be serious abnormal information; otherwise, the comprehensive defect assessment information is determined to be general abnormal information.

[0043] Specifically, if the hidden defect detection result indicates a first-degree defect and the dimensional defect detection result indicates a second-degree defect, the terminal device can quickly determine that the comprehensive defect assessment information is a serious anomaly. Otherwise, the terminal device can quickly determine that the comprehensive defect assessment information is a general anomaly. In some possible implementations, for the purpose of timely detection of abnormal aluminum profiles, please refer to [link / reference needed]. Figure 5 After step S400, the method further includes, but is not limited to, the following steps: In S500, if the comprehensive defect assessment information is classified as general abnormal information or serious abnormal information, a non-compliance warning message for the profile will be generated.

[0044] Specifically, if the comprehensive defect assessment information is classified as general or severe anomaly, the terminal device can generate a non-compliant profile warning message. In S510, a non-compliant profile notification message is sent to a designated terminal.

[0045] Specifically, after the terminal device generates a non-compliant profile notification, it can send the non-compliant profile notification to a designated terminal.

[0046] The implementation principle of the defect identification method for new energy vehicle profiles in this application embodiment is as follows: The terminal device can first quickly acquire the internal image information and geometric dimension information of the cavity of the profile to be inspected based on a preset image sensor. Then, according to the preset target detection algorithm and the internal image information of the cavity, it efficiently generates the hidden defect detection result information. Then, according to the geometric dimension information and the preset reference dimension information, it effectively generates the dimension defect detection result information. Finally, according to the hidden defect detection result information and the dimension defect detection result information, it accurately generates the comprehensive defect evaluation information, thereby realizing automatic and accurate judgment of the product quality of aluminum profiles for new energy vehicles, improving the detection effect, and significantly enhancing the comprehensiveness and reliability of the detection of hidden defects inside the cavity of aluminum profiles.

[0047] 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.

[0048] Embodiments of this application also provide a defect identification system based on new energy vehicle profiles. For ease of explanation, only the parts relevant to this application are shown, such as... Figure 6 As shown, the system 60 includes: Cavity interior image information acquisition module 61: used to acquire cavity interior image information and geometric dimension information of the profile to be inspected based on a preset image sensor; The hidden defect detection result information generation module 62 is used to generate hidden defect detection result information based on the preset target detection algorithm and cavity internal image information, wherein the hidden defect detection result information is the first qualified information or the first defect information. Dimensional defect detection result information generation module 63: used to generate dimensional defect detection result information based on geometric dimension information and preset reference dimension information, wherein the dimensional defect detection result information is a second qualified information or a second defective information; Defect Comprehensive Assessment Information Generation Module 64: Used to generate comprehensive defect assessment information based on the results of hidden defect detection and dimensional defect detection.

[0049] Optionally, the above-mentioned hidden defect detection result information generation module 62 includes: Profile contour information generation submodule: used to generate profile contour information based on the cavity interior image information using a preset contour extraction algorithm; Profile outline information judgment submodule: used to determine whether there are other outlines besides the reference outline information based on the preset reference outline information; The first defect information determination submodule is used to determine the hidden defect detection result information as the first defect information if the profile outline information has other outlines besides the reference outline information. The first qualified information determination submodule is used to determine the hidden defect detection result information as the first qualified information if there are no other contour lines besides the reference contour line information in the profile contour line information.

[0050] Optionally, the above-mentioned dimensional defect detection result information generation module 63 includes: Geometric dimension information comparison submodule: used to compare geometric dimension information with preset reference dimension information; The second qualified information determination submodule is used to determine the dimensional defect detection result information as the second qualified information if the geometric dimension information is equal to the reference dimension information. The second defect information determination submodule is used to determine the dimensional defect detection result as the second defect information if the geometric dimension information is not equal to the reference dimension information.

[0051] Optionally, the comprehensive defect assessment information can be qualified profile information, general anomaly information, or severe anomaly information; the aforementioned comprehensive defect assessment information generation module 64 includes: The qualified profile information determination submodule is used to determine the comprehensive defect assessment information as qualified profile information if the hidden defect detection result is the first qualified information and the dimensional defect detection result is the second qualified information. The severe anomaly information determination submodule is used to determine the comprehensive defect assessment information as severe anomaly information if the hidden defect detection result information is the first type of defect information and the dimensional defect detection result information is the second type of defect information; otherwise, it is determined as general anomaly information.

[0052] Optionally, the system 60 also includes: Profile non-compliance warning information generation module: Used to generate profile non-compliance warning information if the comprehensive defect assessment information is a general abnormality or a serious abnormality; Profile non-compliance warning message sending module: used to send profile non-compliance warning messages to designated terminals.

[0053] 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.

[0054] This application also provides a terminal device, such as... Figure 7As shown, the terminal device 70 of this embodiment includes: a processor 71, a memory 72, and a computer program 73 stored in the memory 72 and executable on the processor 71. When the processor 71 executes the computer program 73, it implements the steps in the above-described defect identification method embodiment, for example... Figure 1 Steps S100 to S400 are shown; or, when processor 71 executes computer program 73, it implements the functions of each module in the above-described device, for example... Figure 6 The functions of modules 61 to 64 are shown.

[0055] The terminal device 70 can be a desktop computer, laptop, handheld computer, cloud server, or other computing device, and includes, but is not limited to, a processor 71 and a memory 72. Those skilled in the art will understand that... Figure 7 This is merely an example of terminal device 70 and does not constitute a limitation on terminal device 70. It may include more or fewer components than shown, or combine certain components, or different components. For example, terminal device 70 may also include input / output devices, network access devices, buses, etc.

[0056] The processor 71 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.

[0057] The memory 72 can be an internal storage unit of the terminal device 70, such as the hard disk or memory of the terminal device 70. The memory 72 can also be an external storage device of the terminal device 70, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the terminal device 70. Furthermore, the memory 72 can include both internal storage units and external storage devices of the terminal device 70. The memory 72 can also store computer program 73 and other programs and data required by the terminal device 70. The memory 72 can also be used to temporarily store data that has been output or will be output.

[0058] 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.

[0059] 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 defect identification method based on new energy vehicle profiles, characterized in that, The method includes: Based on a preset image sensor, image information and geometric dimension information of the cavity inside the profile to be inspected are acquired; Based on the preset target detection algorithm and the cavity interior image information, a hidden defect detection result information is generated, wherein the hidden defect detection result information is a first qualified information or a first defect existence information; Based on the geometric dimension information and the preset reference dimension information, dimension defect detection result information is generated, wherein the dimension defect detection result information is a second qualified information or a second defect-existing information; Based on the hidden defect detection results and the dimensional defect detection results, a comprehensive defect assessment is generated.

2. The method according to claim 1, characterized in that, The step of generating hidden defect detection result information based on a preset target detection algorithm and the cavity interior image information includes: Based on a preset contour line extraction algorithm, profile contour line information is generated according to the image information inside the cavity; Based on the preset reference contour information, determine whether there are other contour lines besides the reference contour information in the profile contour information; If the profile outline information contains other outlines besides the reference outline information, then the hidden defect detection result information is determined to be the first defect information. If the profile outline information does not contain any outlines other than the reference outline information, then the hidden defect detection result information is determined to be the first qualified information.

3. The method according to claim 1, characterized in that, The step of generating dimensional defect detection result information based on the geometric dimension information and preset reference dimension information includes: Compare the geometric dimension information with the preset reference dimension information; If the geometric dimension information is equal to the reference dimension information, then the dimension defect detection result information is determined to be the second qualified information; If the geometric dimension information is not equal to the reference dimension information, then the dimension defect detection result information is determined to be the second defect information.

4. The method according to claim 1, characterized in that, The comprehensive defect assessment information includes qualified profile information, general anomaly information, or severe anomaly information; the generation of comprehensive defect assessment information based on the hidden defect detection results and dimensional defect detection results includes: If the hidden defect detection result information is the first qualified information and the dimensional defect detection result information is the second qualified information, then the comprehensive defect evaluation information is determined to be qualified profile information; If the hidden defect detection result information is a first defect information and the dimensional defect detection result information is a second defect information, then the comprehensive defect assessment information is determined to be a serious abnormality information; otherwise, the comprehensive defect assessment information is determined to be a general abnormality information.

5. The method according to claim 4, characterized in that, After generating comprehensive defect assessment information based on the hidden defect detection results and the dimensional defect detection results, the method further includes: If the comprehensive defect assessment information is classified as general abnormal information or severe abnormal information, a non-compliant profile warning message will be generated. Send a non-compliant information message about the profile to the designated terminal.

6. A defect identification system based on new energy vehicle profiles, characterized in that, The system includes: Cavity interior image information acquisition module: used to acquire cavity interior image information and geometric dimension information of the profile to be inspected based on a preset image sensor; Hidden defect detection result information generation module: used to generate hidden defect detection result information based on a preset target detection algorithm and the cavity interior image information, wherein the hidden defect detection result information is first qualified information or first defect existence information; Dimensional defect detection result information generation module: used to generate dimensional defect detection result information based on the geometric dimension information and preset reference dimension information, wherein the dimensional defect detection result information is a second qualified information or a second defective information; Defect Comprehensive Assessment Information Generation Module: Used to generate comprehensive defect assessment information based on the hidden defect detection results and dimensional defect detection results.

7. The system according to claim 6, characterized in that, The hidden defect detection result information generation module includes: Profile contour information generation submodule: used to generate profile contour information based on the cavity interior image information according to the preset contour extraction algorithm; Profile outline information judgment submodule: used to determine whether there are other outlines besides the reference outline information based on the preset reference outline information; First Defect Information Determination Submodule: If the profile outline information contains other outlines besides the reference outline information, then determine the hidden defect detection result information as the first defect information. First Qualification Information Determination Submodule: If the profile outline information does not contain any outlines other than the reference outline information, then the hidden defect detection result information is determined to be the first qualification information.

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