一种工业平板外壳生产控制方法

By acquiring images and performing contour geometry analysis under multiple lighting conditions, combined with spatial clustering risk indicators, the problem of distinguishing between real defects and structural interference on the surface of industrial flat panel shells was solved, enabling high-precision intelligent production control and quality diagnosis.

CN121767310BActive Publication Date: 2026-07-17ANHUI NUODAJIA INTELLIGENT MFG TECH CO LTD

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
ANHUI NUODAJIA INTELLIGENT MFG TECH CO LTD
Filing Date
2025-12-19
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

Existing technologies cannot effectively distinguish between real defects and structural interference on the surface of industrial flat panel shells, resulting in a high false alarm rate in automated control systems and making it difficult to achieve intelligent production control and quality diagnosis.

Method used

Multi-angle images of the surface of the shell to be inspected under at least three different lighting conditions are acquired. Transient interference and stable features are separated by pixel-level statistical analysis. The true defects are screened using the contour geometric regularity index, and a spatial clustering risk index is constructed for graded diagnosis and closed-loop control.

Benefits of technology

It achieves high-precision identification of real defects, reduces false alarm rate, improves the intelligence level and fault response speed of automated production lines, and can handle process drift and equipment failure in a differentiated manner.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121767310B_ABST
    Figure CN121767310B_ABST
Patent Text Reader

Abstract

本申请涉及智能制造技术领域,尤其涉及一种工业平板外壳生产控制方法,方法包括:采集外壳表面在多光照条件下的多角度图像,计算稳定特征图和瞬态干扰掩膜以分离瞬态干扰;对稳定特征图提取稳定轮廓,并计算各轮廓的几何规整度指标以评估其几何复杂度;基于瞬态干扰掩膜和几何规整度指标执行双重否决筛选以豁免瞬态干扰和规整结构,识别真实缺陷轮廓;综合评估缺陷的面积、不规整度和空间聚集性,计算空间聚集风险指标以判定风险等级,并执行分级闭环控制动作。通过本申请的技术方案,能够精确排除各类干扰,实现对真实缺陷的可靠检测和对生产过程的智能诊断控制。
Need to check novelty before this filing date? Find Prior Art