Offset detection method for side-by-side pipelines at bottom of train

By acquiring image information of trains in both stationary and running states, and combining it with trend judgment and early warning steps, the problem of pipeline loosening that cannot be warned in advance in existing technologies has been solved, achieving efficient and accurate pipeline loosening risk detection and early warning.

CN121095237AActive Publication Date: 2025-12-09CRRC HANGZHOU DIGITAL TECH CO LTD
8 Cites 0 Cited by

Patent Information

Application Number
CN202511621707.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-11-07
Publication Date
2025-12-09
Estimated Expiration
2045-11-07

AI Technical Summary

Technical Problem

Existing technologies cannot provide early warnings when detecting loose parallel pipes under train carriages; they can only detect problems after the loosening has occurred, failing to provide risk prediction and lacking sufficient detection efficiency and accuracy.

Method used

By acquiring static reference image information of the train in a stationary state and dynamic image information in a running state, and combining trend judgment and loosening warning steps, early warning and accurate location of pipeline loosening risk can be achieved, including static reference information acquisition, dynamic information acquisition, trend judgment and loosening warning.

Benefits of technology

It enables early warning and precise location of the risk of loosening of pipelines under the train, improves detection efficiency and accuracy, avoids collision damage between pipelines, simplifies the calculation process, and quickly screens out high-risk pipelines.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention relates to the technical field of image processing, and discloses a train bottom side-by-side pipeline offset detection method, which comprises a static reference information acquisition step, a dynamic information acquisition step, a trend judgment step and a loosening early warning step. According to the method, images are collected through an image processing method in the train static link and the train operation link respectively, then whether the high risk of pipe section loosening exists or not is judged, early warning is conveniently conducted before loosening, maintenance personnel can intervene in maintenance in advance, pipeline damage caused by mutual collision between pipelines is avoided, and the maintenance efficiency is improved. Trend judgment is divided into a risk pre-screening link and a loosening trend score calculation link, in the risk pre-screening link, a preliminary score threshold value is calculated through partial data in advance and used for judging whether a high-risk pipe section exists or not, if the high-risk pipe section exists, a loosening trend score is calculated, high-risk pipelines can be screened out conveniently and rapidly, and the working efficiency is improved. The step of calculating the loose trend score is to improve the accuracy of risk assessment in combination with an actual operation scene.
Need to check novelty before this filing date? Find Prior Art