Roller coaster track thermal deformation monitoring method based on infrared feature extraction

By using infrared feature extraction and adaptive anomaly detection, the problems of narrow coverage, poor real-time performance, and lack of early warning in roller coaster track thermal deformation monitoring have been solved, realizing real-time and accurate thermal deformation monitoring and early warning, and improving the operational safety of roller coaster tracks.

CN122451685APending Publication Date: 2026-07-24CHINA SPECIAL EQUIP INSPECTION & RES INST
0 Cites 0 Cited by

Patent Information

Application Number
CN202610520343.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-04-20
Publication Date
2026-07-24

AI Technical Summary

Technical Problem

Existing methods for monitoring thermal deformation of roller coaster tracks have limited coverage, poor real-time performance, and lack fatigue weakening modeling and graded early warning capabilities, resulting in the inability to identify potential structural risks in a timely manner and affecting the operational safety of amusement facilities.

Method used

Infrared feature extraction method is adopted, combined with multi-feature fusion and adaptive anomaly detection. Infrared thermal imaging technology is used to monitor the thermal deformation of the track in real time, construct a reference temperature field model, extract macroscopic temperature gradient, local hot spot topology and thermal pulse response features, use temperature strain conversion model to infer thermal deformation, and achieve adaptive early warning through an anomaly detector combining isolated forest and LSTM network.

Benefits of technology

It achieves non-contact, real-time, and high-precision thermal deformation sensing across the entire track, enabling the identification of potential structural risks during the initiation stage of thermal deformation anomalies, thus improving the operational safety level of amusement facilities, with an early warning response time of no more than 3 seconds.

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

Abstract

The invention discloses a roller coaster track thermal deformation monitoring method based on infrared feature extraction, and the method comprises the steps: building a reference temperature field model of each track section, collecting a track surface infrared image in real time during the operation of a train, and processing the infrared image to obtain a thermal radiation distribution diagram; extracting a macroscopic temperature gradient feature, a local hot spot topological feature and a thermal impulse response feature from the thermal radiation distribution diagram, inputting the features into a temperature strain conversion model, and deducing real-time thermal deformation and direction vector of each node; an anomaly detector combining an isolated forest algorithm and a long-short-term memory network is adopted to identify thermal deformation anomaly and calculate a comprehensive risk index, and yellow, orange and red three-level early warning is triggered according to a self-adaptive threshold value. Non-contact, real-time and high-precision thermal deformation monitoring and self-adaptive grading early warning of the whole section of the roller coaster track are achieved, and the operation safety level of recreation facilities is remarkably improved.
Need to check novelty before this filing date? Find Prior Art