A method and system for identifying defects in a diamond floor

CN120431071BActive Publication Date: 2026-05-26THE THIRD ENG CO LTD 25TH BUREAU CRCC +1
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
THE THIRD ENG CO LTD 25TH BUREAU CRCC
Filing Date
2025-05-09
Publication Date
2026-05-26

AI Technical Summary

Technical Problem

In existing technologies for detecting defects in corundum surfaces, insufficient defect sample size leads to poor training results for deep learning models, making it difficult to achieve high-precision defect detection.

Method used

By acquiring X-ray image samples, a first feature distribution and a second feature distribution are constructed. The features of valuable samples and regular samples are fused using a weighted summation method. Feature matching and model training are performed by combining local gradient accumulation values ​​and multi-scale dilated attention mechanisms, thereby expanding the scale of training data.

Benefits of technology

It improves the generalization ability and detection accuracy of the defect detection model, effectively alleviates the constraint of insufficient samples on model training, and optimizes the ability to identify defect features.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120431071B_ABST
    Figure CN120431071B_ABST
Patent Text Reader

Abstract

This application relates to a method and system for identifying defects in corundum-coated ground. The method constructs a first feature distribution and a second feature distribution based on image features from X-ray image samples. The first feature distribution refers to a comprehensive feature data distribution formed by fusion of valuable and conventional sample features through a weighted summation method. This balances the influence of different sample types on the feature space, and the combination of valuable and conventional samples can represent important information about the data distribution characteristics, accurately reflecting the data distribution. The second feature distribution represents the feature distribution of pixels. Combining the comprehensive expression of the two distributions and matching them in a database allows for the matching of a more accurate sample set of data distributions. Finally, based on the X-ray image samples and the matched sample set, the defect detection model is trained, improving the accuracy of the defect detection model training.
Need to check novelty before this filing date? Find Prior Art