PCB defect detection method and system based on adaptive multiple submodels

Through the adaptive multi-sub-model system, the priority and feature training of PCB defect detection are dynamically adjusted, which solves the problems of high-frequency defect detection delay and low resource utilization in the existing technology, and realizes efficient and accurate PCB defect detection.

CN120707492AActive Publication Date: 2025-09-26EAST CHINA JIAOTONG UNIVERSITY
5 Cites 2 Cited by

Patent Information

Application Number
CN202510784548.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-06-12
Publication Date
2025-09-26
Estimated Expiration
2045-06-12

AI Technical Summary

Technical Problem

Existing PCB defect detection methods suffer from high-frequency defect detection delays, low resource utilization, poor small sample defect detection results, and threshold judgment reliance on manual experience, which can easily lead to missed detections or false detections.

Method used

An adaptive multi-sub-model system is adopted, which dynamically adjusts the priority order of sub-models through dynamic priority control, feature sharing mechanism and uncertainty assessment, combined with reinforcement agent learning and Bayesian network, uses gradient mask mechanism for specificity training, and improves detection accuracy through confidence screening and cascade control.

Benefits of technology

It achieves rapid response to high-frequency defects, accurate identification of small sample defects and efficient use of computing resources, meeting the high real-time and high robustness quality inspection requirements in industrial scenarios, reducing the computing burden and improving detection efficiency and accuracy.

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

Abstract

The invention discloses a PCB defect detection method and system based on adaptive multiple submodels, and the method comprises the steps: collecting an image of the surface of a PCB through a high-resolution camera, and carrying out the preprocessing of the image; performing dynamic priority decision through reinforcement learning, and reasonably selecting the priority of the sub-model according to the equipment state and the load of the computing resource; yOLOv8 is adopted as a backbone network, a plurality of sub-models work in parallel, and the sub-models are trained in combination with gradient masks; realizing multi-stage cascade detection by adopting a confidence threshold screening and variance analysis mode, and reversely optimizing parameters of the model according to a batch statistical result; and according to the recall rate and the false detection rate of each detection, optimizing the sub-model through an incremental training mechanism. According to the method, the adaptive multiple sub-models are provided, and through a dynamic priority control and feature sharing mechanism, the high accuracy is ensured, the detection strategy is dynamically adjusted, the calculation burden is reduced, and efficient and accurate PCB defect detection is realized.
Need to check novelty before this filing date? Find Prior Art