Method and device for automatically segmenting and quantifying fatigue crack in structural strength test

By constructing the CrackDAM-Net network, combining local and global feature encoders and a hybrid attention mechanism, the balance problem between accuracy and speed in existing fatigue crack detection is solved, and efficient and accurate detection of crack segmentation and quantification is achieved.

CN120726341APending Publication Date: 2025-09-30XIDIAN UNIV +1
0 Cites 2 Cited by

Patent Information

Application Number
CN202510825859.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-06-19
Publication Date
2025-09-30

AI Technical Summary

Technical Problem

Existing fatigue crack detection methods have difficulty achieving an effective balance between accuracy and speed, and lack accurate quantification of crack length. In particular, the segmentation network suffers from severe loss of crack edge information in complex backgrounds, resulting in high computational complexity and difficulty meeting real-time detection requirements.

Method used

A fatigue crack segmentation and quantification network CrackDAM-Net is constructed, which adopts a parallel structure of local feature encoder and global information encoder, combines frequency domain enhancement with Mamba linear attention mechanism, integrates spatial, channel and pixel attention mechanisms, and performs crack segmentation and length quantization through multi-scale feature fusion and decoder.

Benefits of technology

It significantly improves the accuracy of crack segmentation and length measurement, reduces computational complexity, achieves a balance between real-time and precision crack detection, and meets the needs of industrial applications.

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

Abstract

The invention discloses a fatigue crack automatic segmentation and quantification method and device in a structural strength test, and the method comprises the steps: obtaining a material fatigue crack image, and constructing a material fatigue crack image data set; a fatigue crack segmentation and quantification network CrackDAM-Net is constructed; comprising the following steps: constructing a local feature encoder, a global information encoder, a multi-scale feature fusion module, a decoder module and a crack length automatic quantization module, and training a fatigue crack automatic segmentation and quantization network; and inputting a crack image to be detected into the fatigue crack segmentation and quantization network CrackDAM-Net, and carrying out crack segmentation and length quantization to obtain the fatigue crack length. According to the method, the calculation complexity of the model is reduced by constructing the fatigue crack segmentation and quantification network-CrackDAM-Net; the effective fusion of fine-grained details and coarse-grained information is realized, and the extraction effect of crack global information, the accuracy of crack segmentation and the precision of crack length measurement are improved.
Need to check novelty before this filing date? Find Prior Art