Weld intelligent defect detection model training method, detection method and electronic equipment

By combining the YOLOv8 object detection network with the PPO reinforcement learning model, an intelligent weld defect detection model was constructed, which solved the problem of high false alarm rate in weld defect detection and achieved high-precision, low-false-alarm automated detection.

CN122199516BActive Publication Date: 2026-07-21CHONGQING UNIV +1
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
CHONGQING UNIV
Filing Date
2026-04-21
Publication Date
2026-07-21

AI Technical Summary

Technical Problem

Existing weld defect detection methods rely on manual interpretation, resulting in a high false alarm rate. Furthermore, existing automatic detection methods have a high false alarm rate in complex industrial scenarios, requiring manual verification and failing to effectively reduce false positives.

Method used

The YOLOv8 object detection network is combined with the PPO reinforcement learning model. By constructing a reinforcement learning environment and using reward calculation rules, the intelligent weld defect detection model is trained to optimize the adaptive decision-making of candidate boxes, delete false positive boxes and retain reliable candidate boxes.

Benefits of technology

It significantly reduces the number of false alarms, improves detection accuracy and recall, maintains high detection precision and reliability, reduces the false deletion of true cases, and enhances the integrity of detection results.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122199516B_ABST
    Figure CN122199516B_ABST
Patent Text Reader

Abstract

The present application belongs to the technical field of machine vision, and provides a welding seam intelligent defect detection model training method, a detection method and an electronic device. The training method comprises: training a target detection network using a welding seam X-ray image sample set to obtain a target detection model; obtaining a preliminary detection result of each welding seam X-ray image using the target detection model; constructing a state of a reinforcement learning environment using each welding seam X-ray image and the preliminary detection result thereof; calculating an immediate reward value of each action in a set of actions performed in each state according to a reward calculation rule; forming a triple consisting of each state, the action performed in the state and the immediate reward value of the action; a plurality of triples form an experience pool; training a PPO reinforcement learning model using the experience pool; and sequentially connecting the target detection model and a policy network of the PPO reinforcement learning model to obtain a welding seam intelligent defect detection model. The present application can effectively reduce the number of false positives while maintaining a high recall rate.
Need to check novelty before this filing date? Find Prior Art