Weld defect intelligent detection method based on high-definition image deep learning

By building a weld defect image database and multi-stage fine-tuning of the GLIP model, combined with multimodal data fusion technology, the problem that traditional weld inspection methods cannot identify internal defects is solved, and efficient and accurate weld defect detection is achieved.

CN120707537APending Publication Date: 2025-09-26GUANGXI UNIV
0 Cites 2 Cited by

Patent Information

Application Number
CN202510856252.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-06-25
Publication Date
2025-09-26

AI Technical Summary

Technical Problem

Existing weld defect detection methods cannot effectively identify internal defects in welds and lack the ability to identify complex defects. Traditional non-destructive testing methods rely on single modal data and find it difficult to achieve multi-dimensional quantitative analysis.

Method used

A high-quality weld defect image database is constructed, the GLIP model is used for two-stage fine-tuning, a multi-layer perceptron module is introduced for multimodal feature alignment, and cross-modal feature fusion is performed by combining image and ultrasonic data to achieve joint detection of internal and external defects in welds.

Benefits of technology

It significantly improves the automation, accuracy and robustness of weld defect detection, can simultaneously identify weld surface and internal defects, and enhances adaptability to complex working conditions.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention provides a weld defect intelligent detection method based on high-definition image deep learning, which comprises the following steps: S1, collecting a high-definition weld image, manually marking the selected image, and constructing a weld defect image database; s2, performing first fine tuning on the pre-training weight GLIP-L by adopting a GLIP model; s3, a self-made welding test piece is made, a high-definition camera and ultrasonic detection equipment are used for collecting a weld joint surface high-definition image of the self-made welding test piece and ultrasonic echo characteristic data of internal defects, and a high-definition weld joint image and ultrasonic multi-mode database is established; s4, introducing a multi-layer perceptron module into the GLIP model, constructing an image and ultrasonic multi-modal feature alignment mechanism, and performing second fine tuning to obtain a trained GLIP model; and S5, performing defect detection on the welding seam by using the trained GLIP model, and outputting a detection result. According to the invention, through multi-modal data fusion, the accuracy and robustness of weld defect detection are improved, and the method is suitable for automatic and accurate industrial detection scenes.
Need to check novelty before this filing date? Find Prior Art