CN-121981968-A - Defect identification method and system based on new energy automobile profile

CN121981968ACN 121981968 ACN121981968 ACN 121981968ACN-121981968-A

Abstract

The application is suitable for the technical field of aluminum profile defect detection, and provides a defect identification method and a defect identification system based on a new energy automobile profile, wherein the method comprises the steps of rapidly acquiring cavity internal image information and geometric dimension information of the profile to be detected based on an image sensor, then carrying out detection according to a target detection algorithm and the cavity internal image information, and generating invisible defect detection result information, effectively generating dimension defect detection result information according to the geometric dimension information and the preset reference dimension information, and finally accurately generating defect comprehensive evaluation information according to the invisible defect detection result information and the dimension defect detection result information. The application can carry out high-efficiency real-time monitoring on the inside of the cavity of the aluminum profile, accurately identify the invisible defects, realize reliable capture of the invisible defects, is beneficial to continuously optimizing the production process and the overall quality of the aluminum profile, and provides important guarantee for the safety and the long-term reliability of key structural members of the new energy automobile.

Inventors

YANG SHUNMING
QIN XINFENG
LI SHAOJUN
ZOU WEICHENG

Assignees

广亚铝业有限公司

Dates

Publication Date: 20260505
Application Date: 20251231

Claims (9)

1. The defect identification method based on the new energy automobile profile is characterized by comprising the following steps of: Acquiring cavity internal image information and geometric dimension information of a section to be detected based on a preset image sensor; generating invisible defect detection result information according to a preset target detection algorithm and the image information in the cavity, wherein the invisible defect detection result information is first qualified information or first defect information; Generating size defect detection result information according to the geometric size information and preset reference size information, wherein the size defect detection result information is second qualified information or second defect information; and generating defect comprehensive evaluation information according to the invisible defect detection result information and the size defect detection result information.
2. The method of claim 1, wherein generating the invisible defect detection result information according to a predetermined target detection algorithm and the cavity interior image information comprises: Based on a preset contour line extraction algorithm, generating profile contour line information according to the cavity internal image information; judging whether profile contour information contains other contour lines except the reference contour line information or not based on preset reference contour line information; if the profile contour line information contains other contour lines except the reference contour line information, determining the invisible defect detection result information as first defect information; and if the profile contour line information does not have other contour lines except the reference contour line information, determining the invisible defect detection result information as first qualified information.
3. The method according to claim 1, wherein generating size defect detection result information according to the geometric size information and preset reference size information includes: comparing the geometric dimension information with preset reference dimension information; if the geometric dimension information is equal to the reference dimension information, determining that the dimension defect detection result information is second qualified information; and if the geometric dimension information is not equal to the reference dimension information, determining the dimension defect detection result information as second defect information.
4. The method of claim 1, wherein the defect review information is qualified profile information, general anomaly information, or severe anomaly information, and wherein the generating defect review information based on the invisible defect detection result information and the dimensional defect detection result information comprises: if the invisible defect detection result information is first qualified information and the size defect detection result information is second qualified information, determining that the defect comprehensive evaluation information is qualified section information; If the invisible defect detection result information is first defect information and the size defect detection result information is second defect information, determining that the defect comprehensive evaluation information is serious abnormal information, otherwise determining that the defect comprehensive evaluation information is general abnormal information.
5. The method of claim 4, wherein after generating defect review information from the invisible defect inspection result information and the dimensional defect inspection result information, the method further comprises: If the defect comprehensive evaluation information is general abnormal information or serious abnormal information, generating section bar non-compliance prompt information; And sending the section bar non-compliance prompt information to a specified terminal.
6. A defect identification system based on new energy automobile profiles, characterized in that the system comprises: The cavity internal image information acquisition module is used for acquiring cavity internal image information and geometric dimension information of the section to be detected based on a preset image sensor; The invisible defect detection result information generation module is used for generating invisible defect detection result information according to a preset target detection algorithm and the image information in the cavity, wherein the invisible defect detection result information is first qualified information or first defect information; The size defect detection result information generation module is used for generating size defect detection result information according to the geometric size information and preset reference size information, wherein the size defect detection result information is second qualified information or second defect information; and the defect comprehensive evaluation information generation module is used for generating defect comprehensive evaluation information according to the invisible defect detection result information and the size defect detection result information.
7. The system of claim 6, wherein the invisible defect detection result information generating module comprises: the profile contour line information generation sub-module is used for generating profile contour line information according to the image information in the cavity based on a preset contour line extraction algorithm; The profile contour line information judging sub-module is used for judging whether other contour lines except the reference contour line information exist in the profile contour line information or not based on preset reference contour line information; the first defect information determining submodule is used for determining that the invisible defect detection result information is first defect information if the profile contour information contains other contour lines except the reference contour line information; And the first qualified information determining submodule is used for determining the invisible defect detection result information as first qualified information if the profile contour information does not have other contour except the reference contour 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 the processor implements the steps of the method according to any of claims 1 to 5 when the computer program is executed.
9. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the method according to any one of claims 1 to 5.

Description

Defect identification method and system based on new energy automobile profile Technical Field The application relates to the technical field of aluminum profile defect detection, in particular to a defect identification method and system based on a new energy automobile profile. Background Because the quality of the new energy automobile aluminum profile is directly related to the light weight and energy efficiency of the vehicle, and further the endurance mileage and energy consumption are affected, it is important to accurately identify the defects of the new energy automobile aluminum profile. At present, quality judgment of the aluminum profile of the new energy automobile mainly depends on manual detection, but detection personnel are easy to fatigue, so that attention is reduced, the detection accuracy is further affected, manual detection is also affected by subjective judgment, different detection personnel can possibly produce differences in the evaluation of the same defect, and the problem of poor detection effect exists and needs to be further improved. Disclosure of Invention Based on the defect identification method and system based on the new energy automobile profile, the embodiment of the application provides a defect identification method and system based on the new energy automobile profile, and aims to solve the problem of poor detection effect in the prior art. In a first aspect, an embodiment of the present application provides a defect identification method based on a new energy automobile profile, where the method includes: Acquiring cavity internal image information and geometric dimension information of a section to be detected based on a preset image sensor; generating invisible defect detection result information according to a preset target detection algorithm and the image information in the cavity, wherein the invisible defect detection result information is first qualified information or first defect information; Generating size defect detection result information according to the geometric size information and preset reference size information, wherein the size defect detection result information is second qualified information or second defect information; and generating defect comprehensive evaluation information according to the invisible defect detection result information and the size defect detection result information. Compared with the prior art, the defect identification method based on the new energy automobile profile has the advantages that the terminal equipment can quickly acquire the cavity internal image information and the geometric dimension information of the profile to be detected based on the preset image sensor, then efficiently generate the invisible defect detection result information according to the preset target detection algorithm and the cavity internal image information, then effectively generate the dimension defect detection result information according to the geometric dimension information and the preset reference dimension information, and finally accurately generate the defect comprehensive evaluation information according to the invisible defect detection result information and the dimension defect detection result information, so that the product quality of the new energy automobile profile can be automatically and accurately judged, the detection effect can be improved, the comprehensiveness and the reliability of the invisible defect detection in the cavity of the aluminum profile can be greatly improved, and the problem that the current detection effect is poor can be solved to a certain extent. In a second aspect, an embodiment of the present application provides a defect identification system based on a new energy automobile profile, where the system includes: The cavity internal image information acquisition module is used for acquiring cavity internal image information and geometric dimension information of the section to be detected based on a preset image sensor; The invisible defect detection result information generation module is used for generating invisible defect detection result information according to a preset target detection algorithm and the image information in the cavity, wherein the invisible defect detection result information is first qualified information or first defect information; The size defect detection result information generation module is used for generating size defect detection result information according to the geometric size information and preset reference size information, wherein the size defect detection result information is second qualified information or second defect information; and the defect comprehensive evaluation information generation module is used for generating defect comprehensive evaluation information according to the invisible defect detection result information and the size defect detection result information. In a third aspect, an embodiment of the present application pro