一种基于机器视觉的非接触式井筒全深应变监测方法

By using a machine vision-based non-contact wellbore monitoring method, which utilizes a target and camera system to identify wellbore strain, the problem of not being able to obtain the full-depth deformation field of the wellbore inner wall in existing technologies is solved, enabling direct measurement and safe prediction of wellbore strain.

CN121346681BActive Publication Date: 2026-07-17CHINA UNIV OF MINING & TECH
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
CHINA UNIV OF MINING & TECH
Filing Date
2025-10-27
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

Existing methods for monitoring strain on the inner wall of wells cannot obtain the full-depth deformation field of the inner wall of the well, cannot detect strain anomalies at any point on the well wall in a timely manner, and are difficult to effectively guide the safety prediction and engineering management of the well wall.

Method used

A non-contact monitoring method based on machine vision is adopted. By installing a camera and placing targets inside the well, the target coordinates are identified using a sub-pixel corner detection algorithm and OpenCV functions. Combined with camera calibration and coordinate transformation, the change in target spacing is calculated to obtain micro-strain values.

Benefits of technology

It enables direct measurement of wellbore strain distribution, providing a scientific basis for wellbore rupture prevention and control, and improving the accuracy of wellbore safety prediction and the effectiveness of engineering control.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121346681B_ABST
    Figure CN121346681B_ABST
Patent Text Reader

Abstract

本发明公开了一种基于机器视觉的非接触式井筒全深应变监测方法，包括以下步骤：S1、在井筒内竖向滑动安装相机，并在井筒上相机视野内布置靶标，每个靶标蚀刻独有的二维码和序列号，按照深度段ID‑序列号编码，根据编码获得该靶标初始坐标；S2、使用亚像素角点检测算法，基于OpenCV中的`cornerSubPix`函数对靶标进行识别检测，获得各靶标中点靶心的像素坐标(u,v)；S3、利用S2中得到的像素坐标(u,v)，求取靶标在世界坐标系中的三维坐标；S4、根据S3获得的靶标在世界坐标系中的三维坐标，可计算出每两个相邻靶标的间距变化，从而计算出每两个相邻靶标间的微应变值。本发明可以直接测得立井井壁的应变分布，为井壁破裂防范治理措施方案设计提科学依据。
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Vehicle-mounted monocular camera distance and height measuring device based on vertical target

    CN103499337A

  • Tunnel deformation inspection system and method based on monocular pose estimation

    CN117606375A