High-pressure oil pipe surface and internal defect integrated intelligent detection system based on machine vision

By simultaneously acquiring and unfolding texture processing, combined with eddy current testing and ultrasonic thickness measurement, coaxial correlation identification and accurate verification of defects on the inner and outer walls of high-pressure oil pipes were achieved. This solved the problems of false detection, missed detection and low verification efficiency in existing technologies, and improved the reliability of the test results.

CN122409503APending Publication Date: 2026-07-17

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Filing Date
2026-05-12
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

Existing technologies are insufficient for the coaxial correlation identification and accurate verification of defects on the inner and outer walls of high-pressure oil pipes, and suffer from problems such as false detection, missed detection, and low verification efficiency.

Method used

The clamping acquisition module synchronously acquires images of the inner and outer walls of the high-pressure oil pipe. The unfolding texture module performs brightness equalization and directional texture extraction. Combined with the trajectory registration module, defect segments are generated. The fixed-point verification module is used for eddy current testing, ultrasonic thickness measurement, and penetrant imaging to achieve coaxial correlation identification and accurate verification of defects on the inner and outer walls.

Benefits of technology

It enables continuous correlation judgment of defects on the inner and outer walls of high-pressure oil pipes, reduces the risk of misidentification of machining textures, and improves the efficiency of verification and the reliability of detection results.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122409503A_ABST
    Figure CN122409503A_ABST
Patent Text Reader

Abstract

本发明公开了融合机器视觉的高压油管表面与内部缺陷一体化智能检测系统,涉及缺陷检测技术领域,包括,夹持采集模块,驱动高压油管旋转并推进同轴照明内窥镜,利用明场光源、线阵相机和内窥镜同步采集外壁图像、内壁图像及位置同步信号,得到内外壁同轴图像带;展开纹理模块,按位置同步信号展开内外壁同轴图像带,并进行金属表面亮度均衡和方向纹理提取,得到疑似缺陷纹理带;对疑似缺陷纹理带依次进行结构张量主纹理方向计算、候选纹理段归并和霍夫变换连接,得到外壁视觉缺陷片段和内壁视觉缺陷片段。本发明通过亮度均衡、方向纹理提取、结构张量主方向计算及霍夫变换连接,提高线状裂纹、腐蚀剥落、划伤及疑似贯穿轨迹的提取稳定性。
Need to check novelty before this filing date? Find Prior Art