Road bridge and tunnel structure health state assessment method and system based on AI

By using the Kalman filter algorithm to calibrate spatial coordinates, the clustering algorithm to identify inflection points, and the linear interpolation to smooth curves, combined with a time series analysis model, the problem of damage point location drift in bridge and tunnel structural health monitoring was solved, enabling dynamic assessment and early warning of structural health status.

CN122154480APending Publication Date: 2026-06-05ANHUI WANTONG TECH
0 Cites 0 Cited by

Patent Information

Application Number
CN202610392170.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-03-27
Publication Date
2026-06-05

AI Technical Summary

Technical Problem

Existing technologies struggle to address data correlation issues caused by spatial displacement of damage points in bridge and tunnel structural health monitoring, leading to errors in damage development rate calculations and hindering accurate assessment of structural health status.

Method used

The spatial coordinates are calibrated in real time using the Kalman filter algorithm, the turning points are identified by the clustering algorithm, the residual error is corrected by the curve smoothing through linear interpolation, and the crack propagation trend is predicted by the time series analysis model to construct a full-process mapping.

Benefits of technology

It enables dynamic assessment and early warning of the health status of bridge and tunnel structures, ensures the continuity of the damage point location sequence and the integrity of data records, improves the accuracy of damage development rate calculation, and provides a scientific assessment of the remaining life of the structure.

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

Abstract

The invention provides an AI-based road bridge and tunnel structure health state assessment method and system, and the method comprises the steps: recognizing turning points through employing a clustering algorithm according to a continuous damage point position sequence, dividing a life cycle segment, and determining the boundaries of a stable segment, a degradation segment and an acceleration segment; acquiring expansion rate data in each life cycle section, and connecting the data among the sections through a linear interpolation method aiming at a curve jump position to obtain a smooth evolution curve; if the symmetric filling residual error exists in the evolution curve, the error source is judged by comparing the expansion rate difference of adjacent sections, and corrected curve parameters are obtained; extracting crack propagation characteristics from the corrected curve parameters, predicting an evolution trend by adopting a time sequence analysis model, and determining the mapping of the whole process of the crack from initiation to propagation; and judging whether the expansion rate is close to a preset critical threshold value or not according to the crack whole-process mapping to obtain a threshold value point of the residual life of the structure.
Need to check novelty before this filing date? Find Prior Art