An industrial equipment detection method, device, equipment and medium

By identifying the skeleton nodes and edges of industrial equipment, generating the skeleton, and comparing the differences, the problem of low detection accuracy in existing technologies is solved, and higher precision industrial equipment detection is achieved.

CN122115378APending Publication Date: 2026-05-29HANGZHOU HAOLINK INTELLIGENT TECHNOLOGY CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
HANGZHOU HAOLINK INTELLIGENT TECHNOLOGY CO LTD
Filing Date
2026-02-11
Publication Date
2026-05-29

AI Technical Summary

Technical Problem

Existing technologies detect defects by comparing the differences in image pixel values ​​between industrial equipment and standard parts, resulting in low accuracy of the detection results.

Method used

By acquiring a group of images of the industrial equipment to be inspected, identifying the industrial equipment region in the images, generating skeleton nodes and edges to form the skeleton of the industrial equipment, and comparing the skeleton of the image to be inspected with the skeleton of the standard image to determine the skeleton difference value, so as to determine the qualification of the equipment.

Benefits of technology

It improves the accuracy of industrial equipment testing by comparing skeleton differences from multiple dimensions, thereby enhancing the reliability and precision of the test results.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122115378A_ABST
    Figure CN122115378A_ABST
Patent Text Reader

Abstract

The application discloses an industrial equipment detection method, device, equipment and medium. The method comprises the following steps: acquiring an image group of an industrial equipment to be detected, wherein the image group comprises a to-be-detected image and a standard image; identifying an industrial equipment region in each image in the image group; identifying a skeleton node in the industrial equipment region and generating a skeleton edge, and determining the skeleton node and the skeleton edge as an industrial equipment skeleton corresponding to the industrial equipment region; comparing the industrial equipment skeleton of the to-be-detected image with the industrial equipment skeleton of the standard image, and determining a skeleton difference value; and determining a qualified detection result of the industrial equipment to be detected according to the skeleton difference value. The embodiment of the application can improve the accuracy of industrial equipment detection.
Need to check novelty before this filing date? Find Prior Art