一种ALC板材的外观质量检测方法及系统

The ALC sheet appearance quality inspection method, which utilizes lidar and lens depth-of-field adjustment, filters out abnormal circles of confusion by taking advantage of the characteristics of the circle of confusion. Combined with statistical analysis and deep depth-of-field imaging, it solves the problem of high computational complexity in existing inspection systems and achieves efficient and accurate defect identification and detection.

CN121027116BActive Publication Date: 2026-07-17SHANDONG RASHIDUN PREFABRICATED CONSTR CO LTD

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
SHANDONG RASHIDUN PREFABRICATED CONSTR CO LTD
Filing Date
2025-09-24
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

The existing ALC sheet appearance quality inspection system suffers from high computational complexity and time cost due to the large and complex number of features contained in the entire image, making it unable to meet the needs of rapid production.

Method used

The distance between the camera and the board is measured by LiDAR, the lens focus point is adjusted and the depth of field is switched, the image is cropped and acquired, abnormal circles of confusion are screened using the characteristics of the circle of confusion, statistical analysis is performed and target areas are merged, and detailed images are obtained by combining deep depth of field shooting, and the model is input to identify the defect type.

Benefits of technology

It improves the accuracy and efficiency of defect identification, reduces the system's computing power requirements, and is adaptable to different specifications and types of ALC boards, exhibiting wide applicability and good adaptability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121027116B_ABST
    Figure CN121027116B_ABST
Patent Text Reader

Abstract

本发明公开了一种ALC板材的外观质量检测方法及系统,属于板材检测技术领域,具体包括:通过激光雷达测量相机与板材的距离,相机根据激光雷达反馈的距离,调整镜头的对焦点,使合焦平面与板材表面重合,并调整镜头景深为浅景深;对板材表面图像进行预处理,识别预处理后的表面图像中的弥散圆,并获取弥散圆的直径数据,检查直径数据的方差是否符合预设要求;对于不合格的板材,获取直径数据的节点直径,筛选出大于节点直径的直径数据,并将对应的弥散圆标记为异常弥散圆,将异常弥散圆的最小外接矩形标记为目标区域;调整为深景深,再次获取板材表面图像,裁切下目标区域对应的图像区域,将图像区域输入预设的模型中,输出对应类型结果。
Need to check novelty before this filing date? Find Prior Art