Solder ball non-qualified product identification and rejection system based on online monitoring

By analyzing the contour changes and edge responses of solder ball array images, and combining graph neural networks and convolutional neural networks, the accuracy problem of identifying micro-deformation on the surface of solder balls was solved, achieving high-precision identification and rejection of non-conforming solder balls, and improving the automation and stability of the detection system.

CN120823170APending Publication Date: 2025-10-21CHONGQING THREE GORGES UNIV +2
0 Cites 2 Cited by

Patent Information

Application Number
CN202510926093.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-07-05
Publication Date
2025-10-21

AI Technical Summary

Technical Problem

Existing technologies have difficulty effectively identifying local curvature mutations and morphological deviations caused by micro-deformations on the solder ball surface, resulting in missed detection of slight pits and low-contrast spots. They also fail to adapt to light disturbances and component changes in the detection environment, affecting the solder ball quality detection accuracy and welding reliability.

Method used

By combining graph neural networks and convolutional neural networks with contour change regions and edge response intensity matrices based on tin ball array images, grayscale changes and coordinate offsets between connection points are calculated to generate a structural representation map. A topological offset recognition set is extracted, non-conforming products are eliminated, and recognition parameters are optimized through motion tracking and weight update modules.

Benefits of technology

It significantly improves the accuracy of identifying local details on the surface of solder balls and the ability to determine boundaries, optimizes the accuracy of defect area identification and the real-time performance and stability of subsequent action responses, and improves the automation level of solder ball quality inspection.

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

Abstract

The invention relates to the technical field of surface optical defect detection, in particular to a tin ball unqualified product identification and rejection system based on online monitoring, which constructs a structure expression map based on linkage analysis of a contour change area, an edge response intensity matrix and a direction gradient mapping matrix and in combination with position difference and brightness fall between connection points. High-sensitivity capture of local details on the surface of the solder ball is realized, and the recognition precision and boundary judgment capability of irregular pit and spot areas are remarkably improved by calculating coordinate offset and boundary length change between connection points and combining a graph neural network. Through a multi-factor association adjustment mode of determining confidence, label disturbance frequency and historical deviation records, adaptive convergence of identification classification parameters and progressive optimization of an output matrix structure are realized, the identification precision of a flaw area is improved, and the real-time performance and stability of subsequent action response are optimized.
Need to check novelty before this filing date? Find Prior Art